[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CADD41JHSJ6B5523P7JB66":3,"skill-same:01M6CADD41JHSJ6B5523P7JB66":80},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":23,"publishedAt":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":57,"commitSha":58,"skillDirectory":59,"forksCount":60,"repositoryHtmlUrl":61,"repositoryHomepageUrl":62,"ownerHtmlUrl":63,"ownerBlogUrl":64,"ownerDescription":65,"updatedAt":66,"install":67,"resources":79},"01M6CADD41JHSJ6B5523P7JB66","flow-hypercare-monitoring",null,"Orchestrate hypercare monitoring period with 24\u002F7 support, SLO tracking, and rapid issue response","jmagly\u002Faiwg","jmagly","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F1159087?v=4","01M6C10AK8N2WCSQN11FYGTJWN","Joseph Magly","01M6C10AQ8A2RMED1Y1BSVY7NF",229,"MIT","https:\u002F\u002Fgithub.com\u002Fjmagly\u002Faiwg\u002Fblob\u002Fmain\u002Fagentic\u002Fcode\u002Fplugins\u002Fsdlc\u002Fskills\u002Fflow-hypercare-monitoring\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"flow","flow hypercare monitoring","monitoring","hypercare","task","standard","true","sonnet","project","interactive","coding","issue","write","read","directory","support","text","orchestration","orchestrate","slo","2026-11-10 10:12:30",false,"---\nnamespace: aiwg\nname: flow-hypercare-monitoring\nplatforms: [all]\ndescription: Orchestrate hypercare monitoring period with 24\u002F7 support, SLO tracking, and rapid issue response\ncommandHint:\n  argumentHint: '[hypercare-duration-days] [project-directory] [--guidance \"text\"] [--interactive]'\n  allowedTools: 'Task, Read, Write, Glob, TodoWrite'\n  model: sonnet\n  category: sdlc-orchestration\n  orchestration: true\n  modelRole: coding\n  modelTier: standard\n---\n\n> **Declarative Flow (#1539):** This flow's orchestration is now also expressed as a\n> declarative YAML Flow at `flows\u002Fflow-hypercare-monitoring.playbook.yaml` (source of truth for the step\n> sequence + gates). This SKILL.md remains the discoverable trigger surface and prose\n> reference. See epic #1534.\n\n# Hypercare Monitoring Flow\n\n**You are the Core Orchestrator** for the post-deployment hypercare monitoring period.\n\n## Your Role\n\n**You orchestrate multi-agent workflows. You do NOT execute bash scripts.**\n\nWhen the user requests this flow (via natural language or explicit command):\n\n1. **Interpret the request** and confirm understanding\n2. **Read this template** as your orchestration guide\n3. **Extract agent assignments** and workflow steps\n4. **Delegate agents with the current provider-native orchestration mechanism** in the correct sequence\n5. **Synthesize results** and finalize artifacts\n6. **Report completion** with summary\n\n## Hypercare Overview\n\n**Definition**: Hypercare is an elevated support period immediately following production deployment, characterized by heightened monitoring, rapid response, and intensive issue resolution.\n\n**Typical Duration**: 7-14 days (configurable based on release complexity and risk)\n\n**Focus Areas**:\n- Production stability and SLO compliance\n- Rapid incident identification and response\n- User adoption and feedback collection\n- Support team enablement\n- Smooth transition to business-as-usual operations\n\n**Exit Criteria**:\n- Zero P0 (Critical) incidents in last 48 hours\n- Zero P1 (High) incidents in last 24 hours\n- All SLOs met for 72 consecutive hours\n- User adoption metrics trending positive\n- Support team ready for standard operations\n- Hypercare report complete and approved\n\n**Expected Duration**: 7-14 days (typical), 20-30 minutes orchestration\n\n## Natural Language Triggers\n\nUsers may say:\n- \"Start hypercare\"\n- \"Begin hypercare period\"\n- \"Post-launch monitoring\"\n- \"24\u002F7 support period\"\n- \"Activate hypercare monitoring\"\n- \"Launch post-deployment support\"\n\nYou recognize these as requests for this orchestration flow.\n\n## Parameter Handling\n\n### Hypercare Duration Parameter\n\n**Purpose**: Specify hypercare period length\n\n**Examples**:\n```\n\u002Fflow-hypercare-monitoring 7 .\n\u002Fflow-hypercare-monitoring 14 .\n```\n\n**Default**: 7 days (low-risk deployments), 14 days (high-risk deployments)\n\n### --guidance Parameter\n\n**Purpose**: User provides upfront direction to tailor hypercare priorities\n\n**Examples**:\n```\n--guidance \"Focus on security monitoring, financial transaction integrity critical\"\n--guidance \"Performance is key, sub-200ms p95 response time SLO\"\n--guidance \"First production launch, team needs extra support and documentation\"\n--guidance \"High-traffic deployment, anticipate 100K daily active users\"\n```\n\n**How to Apply**:\n- Parse guidance for keywords: security, performance, compliance, scale, team experience\n- Adjust agent assignments (add security-gatekeeper, performance-engineer for specific focuses)\n- Modify monitoring depth (lightweight vs comprehensive based on complexity)\n- Influence priority ordering (stability vs. adoption focus)\n\n### --interactive Parameter\n\n**Purpose**: You ask 5-8 strategic questions to understand project context\n\n**Questions to Ask** (if --interactive):\n\n```\nI'll ask 8 strategic questions to tailor hypercare to your needs:\n\nQ1: What are your top priorities for hypercare?\n    (e.g., stability validation, user adoption, performance monitoring)\n\nQ2: What's the deployment risk level?\n    (Helps determine monitoring intensity and duration)\n\nQ3: What are your critical SLOs?\n    (Availability, response time, error rate targets)\n\nQ4: What's your expected user volume?\n    (Helps set alert thresholds and capacity monitoring)\n\nQ5: What's your support team's experience level?\n    (Influences runbook detail and escalation paths)\n\nQ6: What are your biggest concerns about this deployment?\n    (These become focus areas for monitoring and validation)\n\nQ7: Are there regulatory or compliance requirements?\n    (e.g., HIPAA, SOC2, PCI-DSS - affects audit logging and security monitoring)\n\nQ8: What's your incident response capability?\n    (24\u002F7 on-call? Business hours? Helps plan escalation and response)\n\nBased on your answers, I'll adjust:\n- Monitoring intensity (alert thresholds, dashboard focus)\n- Agent assignments (add specialized monitoring agents)\n- Exit criteria strictness (standard vs. elevated)\n- Support team guidance level (detailed runbooks vs. minimal)\n```\n\n**Synthesize Guidance**: Combine answers into structured guidance string for execution\n\n## Artifacts to Generate\n\n**Primary Deliverables**:\n- **Hypercare Team Roster**: Roles, on-call rotation, contacts → `.aiwg\u002Fdeployment\u002Fhypercare-team-roster.md`\n- **Production Health Dashboard**: Real-time monitoring config → `.aiwg\u002Fdeployment\u002Fproduction-dashboard-config.md`\n- **Alert Escalation Matrix**: Severity definitions and response SLAs → `.aiwg\u002Fdeployment\u002Falert-escalation-matrix.md`\n- **Daily Hypercare Standups**: Status reports (daily) → `.aiwg\u002Fdeployment\u002Fhypercare-standup-{YYYY-MM-DD}.md`\n- **Incident Response Logs**: All P0\u002FP1 incidents → `.aiwg\u002Fdeployment\u002Fincidents\u002Fincident-{ID}.md`\n- **Risk Retirement Report**: Validation evidence → `.aiwg\u002Frisks\u002Fhypercare-risk-validation.md`\n- **Hypercare Exit Report**: Final status and transition plan → `.aiwg\u002Freports\u002Fhypercare-exit-report.md`\n\n**Supporting Artifacts**:\n- SLO tracking logs (hourly updates)\n- User adoption metrics (daily updates)\n- Support ticket analysis (daily summary)\n- Post-incident reviews (PIRs) for all P0\u002FP1\n- Corrective action tracker\n\n## Multi-Agent Orchestration Workflow\n\n### Step 1: Establish Hypercare Team and Schedule\n\n**Purpose**: Create dedicated support structure with clear ownership and 24\u002F7 coverage\n\n**Your Actions**:\n\n1. **Read Deployment Context**:\n   ```\n   Read:\n   - .aiwg\u002Fdeployment\u002Foperational-readiness-review.md (team assignments, contacts)\n   - .aiwg\u002Fdeployment\u002Fslo-sli-definition.md (SLO targets, monitoring approach)\n   - .aiwg\u002Fdeployment\u002Fincident-response-runbook.md (escalation paths)\n   ```\n\n2. **Launch Hypercare Planning Agents** (parallel):\n   ```\n   # Agent 1: Operations Manager\n   Task(\n       subagent_type=\"operations-manager\",\n       description=\"Create hypercare team roster and on-call rotation\",\n       prompt=\"\"\"\n       Read ORR team assignments and contacts\n\n       Create Hypercare Team Roster:\n\n       ## Core Team\n       - Hypercare Lead: {name} (overall coordination, daily standups)\n       - On-Call Engineers: {rotation-schedule} (24\u002F7 coverage)\n       - Reliability Engineer: {name} (SLO monitoring, performance analysis)\n       - Support Lead: {name} (user-facing issues, ticket triage)\n       - DevOps Engineer: {name} (rapid deployment, rollback authority)\n\n       ## Extended Team\n       - Product Owner: {name} (prioritization, user impact)\n       - Security Gatekeeper: {name} (security incidents)\n       - Component Owners: {list by component}\n\n       Create 24\u002F7 On-Call Rotation ({duration} days):\n       - Primary on-call schedule (8-hour shifts or daily rotation)\n       - Backup on-call contacts\n       - Escalation path (P0\u002FP1\u002FP2\u002FP3 response procedures)\n\n       Schedule Daily Standups:\n       - Time: {suggest optimal time}\n       - Duration: 30 minutes\n       - Attendees: Core team (mandatory), Extended team (optional)\n\n       Save to: .aiwg\u002Fdeployment\u002Fhypercare-team-roster.md\n       \"\"\"\n   )\n\n   # Agent 2: Reliability Engineer\n   Task(\n       subagent_type=\"reliability-engineer\",\n       description=\"Configure production monitoring and alerting\",\n       prompt=\"\"\"\n       Read SLO\u002FSLI definitions\n\n       Configure Production Health Dashboard:\n\n       ## Key Metrics (Auto-Refresh: 30s)\n\n       **Availability**\n       - Current Uptime: {percentage}% (Target: ≥99.9%)\n       - Service Health: {GREEN | YELLOW | RED}\n       - Failed Health Checks: {count}\n\n       **Performance (Last 5 min)**\n       - Response Time (p50\u002Fp95\u002Fp99): {value}ms\n       - Throughput: {requests-per-second} req\u002Fs\n       - Target: p95 \u003C {SLA}ms\n\n       **Errors (Last 5 min)**\n       - Error Rate: {percentage}% (Target: \u003C0.1%)\n       - 4xx\u002F5xx Errors: {count}\n       - Database Errors: {count}\n\n       **Business Metrics**\n       - Active Users (Current): {count}\n       - Successful Transactions: {count}\n       - Transaction Success Rate: {percentage}%\n\n       **Infrastructure**\n       - CPU\u002FMemory Utilization: {percentage}%\n       - Disk I\u002FO, Network Traffic\n\n       Define alert thresholds for P0\u002FP1\u002FP2\u002FP3 severity levels\n\n       Save to: .aiwg\u002Fdeployment\u002Fproduction-dashboard-config.md\n       \"\"\"\n   )\n\n   # Agent 3: Support Lead\n   Task(\n       subagent_type=\"support-lead\",\n       description=\"Define alert escalation and incident response\",\n       prompt=\"\"\"\n       Read incident response runbook\n\n       Create Alert Escalation Matrix:\n\n       ## P0 (Critical) - Page Immediately\n       - Availability \u003C99%\n       - Error rate >1%\n       - All instances down\n       - Security breach detected\n\n       Action: Page on-call engineer + Hypercare Lead\n       Response SLA: Immediate acknowledgment, 15 min time-to-engage\n\n       ## P1 (High) - Alert Within 5 Minutes\n       - Availability \u003C99.5%\n       - Error rate >0.5%\n       - Response time p95 >2x SLA\n\n       Action: Alert on-call engineer via Slack + SMS\n       Response SLA: 30 min acknowledgment, 1 hour time-to-mitigation\n\n       ## P2 (Medium) - Alert Within 30 Minutes\n       - Availability \u003C99.9%\n       - Error rate >0.1%\n       - Resource utilization >80%\n\n       Action: Alert on-call engineer via Slack\n       Response SLA: 4 hours\n\n       ## P3 (Low) - Log and Review\n       - Minor performance degradation\n       - Non-critical errors\n\n       Action: Create ticket for review\n       Response SLA: 1 business day\n\n       Document incident response workflow (5 phases):\n       1. Detection (Target: \u003C5 min)\n       2. Triage (Target: \u003C15 min)\n       3. Investigation (P0=30min, P1=1h)\n       4. Mitigation (P0=1h, P1=4h)\n       5. Resolution (P0=2h, P1=8h)\n       6. Post-Incident Review (Within 48h)\n\n       Save to: .aiwg\u002Fdeployment\u002Falert-escalation-matrix.md\n       \"\"\"\n   )\n   ```\n\n3. **Synthesize Hypercare Setup Plan**:\n   ```\n   # You do this directly (no agent needed)\n\n   Read all hypercare planning artifacts\n\n   Validate completeness:\n   - Team roster: All roles assigned?\n   - On-call rotation: 24\u002F7 coverage confirmed?\n   - Monitoring: All SLOs tracked?\n   - Escalation: Response SLAs defined?\n\n   Create dedicated communication channel: #hypercare-{project-name}-{YYYY-MM}\n   ```\n\n**Communicate Progress**:\n```\n✓ Initialized hypercare setup\n⏳ Establishing hypercare team and monitoring...\n  ✓ Hypercare team roster created (Core + Extended teams)\n  ✓ 24\u002F7 on-call rotation scheduled ({duration} days)\n  ✓ Production dashboard configured (5 metric categories)\n  ✓ Alert escalation matrix defined (P0\u002FP1\u002FP2\u002FP3)\n✓ Hypercare infrastructure ready: .aiwg\u002Fdeployment\u002F\n```\n\n### Step 2: Monitor Production Stability and SLOs (Daily)\n\n**Purpose**: Continuously validate production system meets SLO targets and stability expectations\n\n**Your Actions**:\n\n1. **Launch SLO Monitoring Agents** (automated, repeat daily):\n   ```\n   # Agent 1: Reliability Engineer (Daily SLO Report)\n   Task(\n       subagent_type=\"reliability-engineer\",\n       description=\"Generate daily SLO compliance report\",\n       prompt=\"\"\"\n       Read production metrics from monitoring dashboard\n       Read SLO definitions: .aiwg\u002Fdeployment\u002Fslo-sli-definition.md\n\n       Generate Daily SLO Report:\n\n       ## SLO Tracking (Updated Hourly)\n\n       ### Availability SLO\n       - Target: ≥99.9% uptime\n       - Current (24h): {percentage}%\n       - Current (7d): {percentage}%\n       - Error Budget Remaining: {percentage}%\n       - Status: {ON TARGET | AT RISK | EXCEEDED}\n\n       ### Performance SLO\n       - Target: p95 response time \u003C{value}ms\n       - Current p95 (24h): {value}ms\n       - Current p95 (7d): {value}ms\n       - Status: {ON TARGET | AT RISK | EXCEEDED}\n\n       ### Error Rate SLO\n       - Target: \u003C0.1% error rate\n       - Current (24h): {percentage}%\n       - Current (7d): {percentage}%\n       - Status: {ON TARGET | AT RISK | EXCEEDED}\n\n       ### Throughput SLO\n       - Target: Handle {value} req\u002Fs\n       - Current Peak: {value} req\u002Fs\n       - Current Average: {value} req\u002Fs\n       - Status: {ON TARGET | AT RISK | EXCEEDED}\n\n       Calculate Error Budget Burn Rate:\n       - Monthly error budget: {value} minutes downtime allowed\n       - Hypercare period budget: {value} minutes\n       - Current burn rate: {value} minutes consumed\n       - Budget remaining: {percentage}%\n       - Assessment: {HEALTHY | MONITOR | CRITICAL}\n\n       If CRITICAL: Recommend incident freeze, focus on stability\n       If MONITOR: Recommend increased monitoring, defer risky changes\n\n       Save to: .aiwg\u002Fdeployment\u002Fslo-report-{YYYY-MM-DD}.md\n       \"\"\"\n   )\n\n   # Agent 2: Support Lead (Daily Support Analysis)\n   Task(\n       subagent_type=\"support-lead\",\n       description=\"Analyze user adoption and support tickets\",\n       prompt=\"\"\"\n       Read support ticket system\n       Read user analytics\n\n       Generate User Adoption Dashboard:\n\n       ### Active Users\n       - DAU (Daily Active Users): {count} (Target: >{target})\n       - WAU\u002FMAU: {count}\n       - User Growth Rate: {+\u002F-percentage}%\n\n       ### Feature Adoption (New Features)\n       For each new feature:\n       - Total Users: {count}\n       - Users Engaged: {count} ({percentage}%)\n       - Adoption Rate: {percentage}% (Target: >{target}%)\n       - Trend: {INCREASING | STABLE | DECREASING}\n\n       ### Support Ticket Analysis\n       - Total Tickets (24h): {count}\n       - By Category: Bug Reports, How-To, Performance, etc.\n       - Critical Issues: {count} (blockers)\n       - Average Response Time: {value}h (Target: \u003C{SLA}h)\n\n       ### User Feedback Summary\n       - Sentiment: {POSITIVE | NEUTRAL | NEGATIVE} ({percentage}%)\n       - Top Issues: {list top 3}\n       - Top Praises: {list top 3}\n\n       Flag Critical User Blockers (if any)\n\n       Save to: .aiwg\u002Fdeployment\u002Fuser-adoption-{YYYY-MM-DD}.md\n       \"\"\"\n   )\n   ```\n\n2. **Incident Tracking** (on-demand per incident):\n   ```\n   # When incident detected:\n   Task(\n       subagent_type=\"devops-engineer\",\n       description=\"Document and respond to incident {incident-ID}\",\n       prompt=\"\"\"\n       Incident detected: {incident-description}\n       Severity: {P0 | P1 | P2 | P3}\n\n       Follow Incident Response Workflow:\n\n       1. Detection (\u003C5 min):\n          - Alert acknowledged\n          - Initial severity assessment\n          - Create incident channel: #incident-{YYYY-MM-DD}-{ID}\n\n       2. Triage (\u003C15 min):\n          - Gather evidence (logs, metrics, user reports)\n          - Identify affected systems\u002Fusers\n          - Estimate business impact\n          - Engage Component Owners\n          - Update severity if needed\n\n       3. Investigation (P0=30min, P1=1h):\n          - Review logs\u002Fmetrics for root cause\n          - Check recent deployments\u002Fchanges\n          - Reproduce in non-prod if possible\n          - Identify probable root cause\n\n       4. Mitigation (P0=1h, P1=4h):\n          - Execute mitigation (rollback\u002Fhotfix\u002Fconfig change)\n          - Validate effectiveness\n          - Monitor for regression\n\n       5. Resolution (P0=2h, P1=8h):\n          - Confirm fully resolved\n          - Validate SLOs back to normal\n          - Close incident\n\n       Document incident timeline and actions\n\n       Save to: .aiwg\u002Fdeployment\u002Fincidents\u002Fincident-{ID}.md\n\n       If P0\u002FP1: Schedule post-incident review within 48h\n       \"\"\"\n   )\n   ```\n\n**Communicate Progress** (daily update):\n```\n✓ Hypercare Day {N} of {duration}\n⏳ Monitoring production stability...\n  ✓ SLO compliance: {percentage}% of SLOs met (target: 100%)\n  ✓ Incidents (24h): {count} total (P0: {count}, P1: {count}, P2: {count})\n  ✓ User adoption: {percentage}% ({trend})\n  ✓ Support tickets: {count} (Trend: {↑\u002F→\u002F↓})\n✓ Daily reports: .aiwg\u002Fdeployment\u002Fslo-report-{date}.md, user-adoption-{date}.md\n```\n\n### Step 3: Conduct Daily Hypercare Standups\n\n**Purpose**: Maintain team alignment, surface issues early, coordinate rapid response\n\n**Your Actions**:\n\n1. **Generate Daily Standup Report** (automated):\n   ```\n   Task(\n       subagent_type=\"operations-manager\",\n       description=\"Generate daily hypercare standup report\",\n       prompt=\"\"\"\n       Read daily reports:\n       - .aiwg\u002Fdeployment\u002Fslo-report-{YYYY-MM-DD}.md\n       - .aiwg\u002Fdeployment\u002Fuser-adoption-{YYYY-MM-DD}.md\n       - .aiwg\u002Fdeployment\u002Fincidents\u002F* (all open\u002Frecent incidents)\n\n       Create Daily Standup Agenda:\n\n       ## Hypercare Daily Standup - Day {N} of {duration}\n\n       **Date**: {YYYY-MM-DD}\n       **Facilitator**: {Hypercare Lead}\n\n       ### 1. Production Health Review (5 min)\n       **Presented by**: Reliability Engineer\n\n       - Availability: {percentage}% (Target: ≥99.9%) - {STATUS}\n       - Performance: p95 {value}ms (Target: \u003C{SLA}ms) - {STATUS}\n       - Error Rate: {percentage}% (Target: \u003C0.1%) - {STATUS}\n       - Error Budget: {percentage}% remaining - {STATUS}\n\n       Overall Health: {GREEN | YELLOW | RED}\n\n       ### 2. Incident Summary (Last 24h) (10 min)\n       **Presented by**: On-Call Engineer\n\n       Total Incidents: {count}\n       - P0 (Critical): {count} - {list titles if any}\n       - P1 (High): {count} - {list titles if any}\n       - P2 (Medium): {count}\n       - P3 (Low): {count}\n\n       Key Incidents:\n       For each P0\u002FP1:\n       - Incident-ID: {title}\n       - Status: {Open\u002FResolved\u002FClosed}\n       - Impact: {user-count} users, {duration} minutes\n       - Root Cause: {brief description}\n       - Action Items: {list}\n\n       Patterns\u002FTrends: {emerging issues or recurring problems}\n\n       ### 3. User Feedback Review (5 min)\n       **Presented by**: Support Lead\n\n       - Support Tickets (24h): {count} (Trend: {↑\u002F→\u002F↓})\n       - Critical User Issues: {count}\n       - Top Complaints: {list top 3}\n       - Top Praises: {list top 3}\n       - Sentiment: {POSITIVE | NEUTRAL | NEGATIVE}\n\n       Blockers for Users: {list critical issues}\n\n       ### 4. SLO\u002FSLI Status (5 min)\n       **Presented by**: Reliability Engineer\n\n       | SLO | Target | Current (24h) | Status |\n       |-----|--------|---------------|--------|\n       | Availability | ≥99.9% | {percentage}% | {✓\u002F⚠\u002F✗} |\n       | Response Time | p95\u003C{value}ms | {value}ms | {✓\u002F⚠\u002F✗} |\n       | Error Rate | \u003C0.1% | {percentage}% | {✓\u002F⚠\u002F✗} |\n       | Throughput | >{value} req\u002Fs | {value} req\u002Fs | {✓\u002F⚠\u002F✗} |\n\n       ### 5. Action Items and Blockers (5 min)\n\n       Open Action Items:\n       | Action | Owner | Due Date | Status |\n       |--------|-------|----------|--------|\n       {list open actions}\n\n       New Blockers:\n       {list blockers requiring escalation}\n\n       Tomorrow's On-Call: {name} (taking over at {HH:MM})\n\n       ---\n\n       Overall Status: {GREEN | YELLOW | RED}\n\n       Key Decisions Made:\n       {list decisions from standup}\n\n       New Action Items:\n       {list new actions assigned}\n\n       Save to: .aiwg\u002Fdeployment\u002Fhypercare-standup-{YYYY-MM-DD}.md\n       \"\"\"\n   )\n   ```\n\n2. **Weekly Summary** (if hypercare > 7 days):\n   ```\n   # On Day 7, 14, etc.:\n   Task(\n       subagent_type=\"operations-manager\",\n       description=\"Generate weekly hypercare summary\",\n       prompt=\"\"\"\n       Read all daily standups for week: .aiwg\u002Fdeployment\u002Fhypercare-standup-*.md\n\n       Create Weekly Summary:\n\n       ## Hypercare Week {N} Summary\n\n       **Week**: {date-range}\n       **Overall Status**: {GREEN | YELLOW | RED}\n\n       ### Production Stability\n       - Availability: {percentage}% (Target: ≥99.9%)\n       - Total Incidents: {count} (P0: {count}, P1: {count})\n       - MTTR: {value} min\n       - SLO Compliance: {percentage}%\n\n       ### User Adoption\n       - Active Users: {count} ({+\u002F-percentage}% vs. previous week)\n       - Feature Adoption: {percentage}%\n       - User Sentiment: {POSITIVE | NEUTRAL | NEGATIVE}\n\n       ### Support Health\n       - Support Tickets: {count} ({+\u002F-percentage}% vs. previous week)\n       - Critical Issues: {count}\n       - Response Time: {value}h (Target: \u003C{SLA}h)\n\n       ### Accomplishments\n       {list accomplishments}\n\n       ### Challenges\n       {list challenges}\n\n       ### Next Week Focus\n       {list focus areas}\n\n       Save to: .aiwg\u002Freports\u002Fhypercare-week-{N}-summary.md\n       \"\"\"\n   )\n   ```\n\n**Communicate Progress**:\n```\n⏳ Conducting daily standup...\n✓ Daily standup report generated: .aiwg\u002Fdeployment\u002Fhypercare-standup-{date}.md\n  - Overall Health: {GREEN | YELLOW | RED}\n  - Key Decisions: {count}\n  - New Action Items: {count}\n  - Escalations: {count}\n```\n\n### Step 4: Post-Incident Reviews (For P0\u002FP1 Incidents)\n\n**Purpose**: Document root cause and corrective actions for all critical incidents\n\n**Your Actions**:\n\n1. **For Each P0\u002FP1 Incident** (within 48h of resolution):\n   ```\n   Task(\n       subagent_type=\"reliability-engineer\",\n       description=\"Conduct post-incident review for {incident-ID}\",\n       prompt=\"\"\"\n       Read incident log: .aiwg\u002Fdeployment\u002Fincidents\u002Fincident-{ID}.md\n\n       Create Post-Incident Review (PIR):\n\n       ## Post-Incident Review: {Incident-ID}\n\n       **Date**: {YYYY-MM-DD}\n       **Severity**: {P0\u002FP1\u002FP2\u002FP3}\n       **Duration**: {detection-to-resolution}\n       **Impact**: {user-count} users, {downtime-minutes} minutes downtime\n\n       ### Incident Summary\n       {1-2 sentence description of what happened}\n\n       ### Timeline\n       | Time | Event | Actor |\n       |------|-------|-------|\n       {incident timeline from detection to resolution}\n\n       ### Root Cause\n       {Detailed technical root cause analysis}\n\n       ### Contributing Factors\n       1. {Factor 1 - e.g., insufficient testing}\n       2. {Factor 2 - e.g., monitoring gap}\n       3. {Factor 3 - e.g., unclear runbook}\n\n       ### Corrective Actions\n       | Action | Owner | Due Date | Status |\n       |--------|-------|----------|--------|\n       {list corrective actions to prevent recurrence}\n\n       ### Lessons Learned\n       - What went well: {list}\n       - What could improve: {list}\n       - Process changes needed: {list}\n\n       Save to: .aiwg\u002Fdeployment\u002Fincidents\u002Fpir-{ID}.md\n\n       Update incident log with PIR link\n       Track corrective actions in action tracker\n       \"\"\"\n   )\n   ```\n\n**Communicate Progress**:\n```\n⏳ Conducting post-incident reviews...\n✓ PIR complete: Incident-{ID} ({title})\n  - Root cause: {summary}\n  - Corrective actions: {count} assigned\n  - Status: Tracking to completion\n```\n\n### Step 5: Validate Exit Criteria and Generate Hypercare Report\n\n**Purpose**: Ensure production is stable and support team is ready before ending hypercare\n\n**Your Actions**:\n\n1. **Validate Exit Criteria** (on final day or when user requests):\n   ```\n   Task(\n       subagent_type=\"operations-manager\",\n       description=\"Validate hypercare exit criteria\",\n       prompt=\"\"\"\n       Read all hypercare artifacts\n\n       Validate Hypercare Exit Criteria:\n\n       ## Hypercare Exit Criteria Validation\n\n       **Hypercare Period**: Day {N} of {duration}\n       **Validation Date**: {YYYY-MM-DD}\n\n       ### Production Stability\n       - [ ] Zero P0 (Critical) incidents in last 48 hours\n       - [ ] Zero P1 (High) incidents in last 24 hours\n       - [ ] All SLOs met for 72 consecutive hours\n         - [ ] Availability ≥99.9%\n         - [ ] Response time p95 \u003C{SLA}ms\n         - [ ] Error rate \u003C0.1%\n         - [ ] Throughput >{target} req\u002Fs\n       - [ ] Error budget healthy: >{percentage}% remaining\n       - [ ] No open P0\u002FP1 incidents\n\n       ### User Adoption\n       - [ ] User adoption trending positive ({percentage}% growth)\n       - [ ] Feature adoption >{target}% for critical features\n       - [ ] User sentiment majority positive (≥70%)\n       - [ ] Support ticket volume stable or decreasing\n       - [ ] No critical user blockers unresolved\n\n       ### Support Readiness\n       - [ ] Support team trained and confident\n       - [ ] Runbooks validated (all common issues documented)\n       - [ ] Escalation paths tested and effective\n       - [ ] Knowledge base updated with hypercare learnings\n       - [ ] On-call rotation transitioned to standard support\n\n       ### Documentation Complete\n       - [ ] Hypercare report completed\n       - [ ] Post-incident reviews completed (all P0\u002FP1)\n       - [ ] Corrective actions tracked (assigned, due dates set)\n       - [ ] Lessons learned documented\n       - [ ] Runbooks updated\n\n       Overall Exit Criteria Status: {PASS | CONDITIONAL | FAIL}\n       Decision: {END HYPERCARE | EXTEND HYPERCARE | ESCALATE}\n\n       Save to: .aiwg\u002Freports\u002Fhypercare-exit-criteria.md\n       \"\"\"\n   )\n   ```\n\n2. **Generate Hypercare Exit Report** (comprehensive final report):\n   ```\n   Task(\n       subagent_type=\"operations-manager\",\n       description=\"Generate comprehensive hypercare exit report\",\n       prompt=\"\"\"\n       Read all hypercare artifacts:\n       - .aiwg\u002Fdeployment\u002Fhypercare-team-roster.md\n       - .aiwg\u002Fdeployment\u002Fslo-report-*.md (all days)\n       - .aiwg\u002Fdeployment\u002Fuser-adoption-*.md (all days)\n       - .aiwg\u002Fdeployment\u002Fhypercare-standup-*.md (all days)\n       - .aiwg\u002Fdeployment\u002Fincidents\u002F*.md (all incidents)\n       - .aiwg\u002Freports\u002Fhypercare-exit-criteria.md\n\n       Generate Hypercare Exit Report:\n\n       # Hypercare Report: {Project-Name}\n\n       **Hypercare Period**: {start-date} to {end-date} ({duration} days)\n       **Report Date**: {YYYY-MM-DD}\n       **Report Author**: {Hypercare Lead}\n\n       ## Executive Summary\n\n       {2-3 sentence summary of hypercare outcomes}\n\n       Overall Status: {SUCCESS | SUCCESS WITH CONDITIONS | CHALLENGES}\n\n       Key Metrics:\n       - Availability: {percentage}%\n       - Total Incidents: {count} (P0: {count}, P1: {count})\n       - User Adoption: {percentage}%\n       - Support Tickets: {count}\n\n       ## Production Stability Summary\n\n       ### SLO Performance\n       | SLO | Target | Achieved | Status |\n       |-----|--------|----------|--------|\n       {SLO compliance table}\n\n       SLO Compliance Rate: {percentage}%\n\n       ### Incident Summary\n       Total Incidents: {count}\n       - P0 (Critical): {count}\n       - P1 (High): {count}\n       - P2 (Medium): {count}\n       - P3 (Low): {count}\n\n       Key Metrics:\n       - MTTD (Mean Time to Detect): {value} min\n       - MTTA (Mean Time to Acknowledge): {value} min\n       - MTTR (Mean Time to Resolve): {value} min\n\n       Major Incidents:\n       For each P0\u002FP1:\n       - Incident-ID: {title}\n         - Date, Duration, Impact, Root Cause, Resolution\n         - Corrective Actions: {count} assigned\n\n       ### Performance Trends\n       - Response Time: {IMPROVED | STABLE | DEGRADED} ({+\u002F-percentage}% vs. pre-deployment)\n       - Error Rate: {IMPROVED | STABLE | DEGRADED}\n       - Resource Utilization: {HEALTHY | CONCERNING}\n\n       ## User Adoption Summary\n\n       ### Adoption Metrics\n       - Active Users: {count} ({+\u002F-percentage}% vs. pre-deployment)\n       - Feature Adoption: {percentage}% (Target: >{target}%)\n       - User Retention (Day 14): {percentage}%\n\n       ### User Feedback\n       - Total Feedback Items: {count}\n       - Sentiment: {percentage}% positive\n       - Net Promoter Score: {value}\n\n       Top Praises: {list top 3}\n       Top Complaints: {list top 3 with resolution status}\n\n       ## Support Summary\n\n       ### Ticket Volume\n       - Total Support Tickets: {count}\n       - Daily Average: {count} tickets\u002Fday\n       - Trend: {DECREASING | STABLE | INCREASING}\n\n       ### Support Performance\n       - Average Response Time: {value}h (Target: \u003C{SLA}h) - {✓\u002F⚠\u002F✗}\n       - First Contact Resolution: {percentage}%\n\n       ### Support Team Readiness\n       - Team Confidence Level: {HIGH | MEDIUM | LOW}\n       - Runbook Completeness: {percentage}%\n\n       ## Lessons Learned\n\n       ### What Went Well\n       {list successes}\n\n       ### What Could Improve\n       {list improvements}\n\n       ### Process Recommendations\n       {list recommendations for future deployments}\n\n       ## Corrective Actions\n\n       Total Actions Identified: {count}\n\n       | Action | Category | Owner | Due Date | Status |\n       |--------|----------|-------|----------|--------|\n       {corrective actions table}\n\n       ## Handover to Standard Support\n\n       ### Transition Plan\n       - [ ] Standard on-call rotation activated (starting {date})\n       - [ ] Support runbooks transferred\n       - [ ] Knowledge base published\n       - [ ] Support team training complete\n       - [ ] Escalation paths updated for BAU\n\n       ### Post-Hypercare Monitoring\n       - Duration: {duration} days continued close monitoring\n       - Responsible: {Support Lead}\n       - Review Cadence: Weekly check-ins for {duration} weeks\n\n       ## Conclusion\n\n       {2-3 sentence summary and readiness for standard support}\n\n       Recommendation: {END HYPERCARE | EXTEND HYPERCARE}\n\n       Signoff:\n       - Hypercare Lead: {name} - {date}\n       - Reliability Engineer: {name} - {date}\n       - Support Lead: {name} - {date}\n       - Product Owner: {name} - {date}\n       - Project Manager: {name} - {date}\n\n       Save to: .aiwg\u002Freports\u002Fhypercare-exit-report.md\n       \"\"\"\n   )\n   ```\n\n3. **Present Exit Summary to User**:\n   ```\n   # You present this directly (not via agent)\n\n   Read .aiwg\u002Freports\u002Fhypercare-exit-report.md\n\n   Present summary:\n   ─────────────────────────────────────────────\n   Hypercare Monitoring Period Complete\n   ─────────────────────────────────────────────\n\n   **Hypercare Period**: {start-date} to {end-date} ({duration} days)\n   **Overall Status**: {SUCCESS | SUCCESS WITH CONDITIONS | CHALLENGES}\n\n   **Key Metrics**:\n   ✓ Availability: {percentage}% (Target: ≥99.9%)\n   ✓ Total Incidents: {count} (P0: {count}, P1: {count})\n   ✓ User Adoption: {percentage}% of target\n   ✓ Support Readiness: Team confident and ready\n\n   **Exit Criteria Status**:\n   ✓ Production Stability: {PASS | CONDITIONAL | FAIL}\n   ✓ User Adoption: {PASS | CONDITIONAL | FAIL}\n   ✓ Support Readiness: {PASS | CONDITIONAL | FAIL}\n   ✓ Documentation: {PASS | CONDITIONAL | FAIL}\n\n   **Decision**: {END HYPERCARE | EXTEND HYPERCARE | ESCALATE}\n\n   **Artifacts Generated**:\n   - Hypercare Team Roster (.aiwg\u002Fdeployment\u002Fhypercare-team-roster.md)\n   - Production Dashboard Config (.aiwg\u002Fdeployment\u002Fproduction-dashboard-config.md)\n   - Alert Escalation Matrix (.aiwg\u002Fdeployment\u002Falert-escalation-matrix.md)\n   - Daily Standup Reports (.aiwg\u002Fdeployment\u002Fhypercare-standup-*.md, {count} files)\n   - SLO Reports (.aiwg\u002Fdeployment\u002Fslo-report-*.md, {count} files)\n   - User Adoption Reports (.aiwg\u002Fdeployment\u002Fuser-adoption-*.md, {count} files)\n   - Incident Logs (.aiwg\u002Fdeployment\u002Fincidents\u002F*.md, {count} files)\n   - Post-Incident Reviews (.aiwg\u002Fdeployment\u002Fincidents\u002Fpir-*.md, {count} files)\n   - Hypercare Exit Report (.aiwg\u002Freports\u002Fhypercare-exit-report.md)\n\n   **Next Steps**:\n   - Review hypercare exit report with stakeholders\n   - Obtain formal signoffs (5 required signatures)\n   - If END HYPERCARE: Transition to standard support (run handoff workflow)\n   - If EXTEND HYPERCARE: Address gaps, continue monitoring\n   - If ESCALATE: Executive decision required\n\n   **Transition to Standard Support**:\n   - Standard on-call rotation activated: {date}\n   - Continued monitoring period: {duration} days\n   - Weekly check-ins scheduled\n\n   ─────────────────────────────────────────────\n   ```\n\n**Communicate Progress**:\n```\n⏳ Validating hypercare exit criteria...\n✓ Exit criteria validated: {PASS | CONDITIONAL | FAIL}\n✓ Hypercare Exit Report generated: .aiwg\u002Freports\u002Fhypercare-exit-report.md\n✓ Transition plan documented\n```\n\n## Quality Gates\n\nBefore marking workflow complete, verify:\n- [ ] Hypercare team established with 24\u002F7 coverage\n- [ ] Production monitoring operational (dashboards, alerts)\n- [ ] Daily standups conducted and documented\n- [ ] All P0\u002FP1 incidents have post-incident reviews\n- [ ] SLO compliance tracked daily\n- [ ] User adoption monitored and reported\n- [ ] Exit criteria validated\n- [ ] Hypercare exit report complete and approved\n- [ ] Transition to standard support planned\n\n## User Communication\n\n**At start**: Confirm understanding and list activities\n\n```\nUnderstood. I'll orchestrate the hypercare monitoring period.\n\nHypercare Duration: {duration} days\nHypercare Period: {start-date} to {estimated-end-date}\n\nThis will establish:\n- Hypercare team roster and 24\u002F7 on-call rotation\n- Production health monitoring dashboards\n- Alert escalation and incident response procedures\n- Daily standup coordination\n- SLO tracking and user adoption monitoring\n- Post-incident review process\n- Hypercare exit criteria validation\n\nI'll coordinate multiple agents for comprehensive monitoring and support.\nExpected setup: 20-30 minutes.\n\nStarting orchestration...\n```\n\n**During**: Update progress with clear indicators\n\n```\n✓ = Complete\n⏳ = In progress\n❌ = Error\u002Fblocked\n⚠️ = Warning\u002Fattention needed\n```\n\n**Daily**: Provide daily status summary\n\n```\nHypercare Day {N} of {duration}: {GREEN | YELLOW | RED}\n\nProduction Health:\n✓ Availability: {percentage}% (Target: ≥99.9%)\n✓ Performance: p95 {value}ms (Target: \u003C{SLA}ms)\n{⚠️ | ✓} Error Rate: {percentage}% (Target: \u003C0.1%)\n\nIncidents (24h):\n- P0: {count}\n- P1: {count}\n- P2: {count}\n\nUser Adoption: {percentage}% ({trend})\n\nDaily reports: .aiwg\u002Fdeployment\u002Fhypercare-standup-{date}.md\n```\n\n**At end**: Summary report (see Step 5.3 above)\n\n## Error Handling\n\n**If P0 Incident During Hypercare**:\n```\n❌ Critical incident detected - immediate response initiated\n\nIncident: {incident-ID} - {title}\nSeverity: P0 (Complete outage \u002F Data loss \u002F Security breach)\nImpact: {user-count} users affected\n\nActions:\n1. On-call engineer + Hypercare Lead paged\n2. Incident war room created: #incident-{date}-{ID}\n3. Executive Sponsor notified\n4. Status page updated\n\nResponse Timeline:\n- Detection: {timestamp}\n- Acknowledgment: {timestamp} (Target: Immediate)\n- Time-to-engage: {minutes} min (Target: \u003C15 min)\n\nCurrent Status: {INVESTIGATING | MITIGATING | RESOLVED}\n\nImpact on Exit Criteria: P0 incident resets 48h \"zero critical incidents\" requirement\n\nMonitoring incident response...\n```\n\n**If SLO Breach**:\n```\n⚠️ SLO breach detected - immediate investigation required\n\nSLO Breached: {SLO-name}\n- Target: {target-value}\n- Current: {actual-value}\n- Duration: {duration} (continuous breach)\n\nImpact:\n- Error budget consumed: {percentage}%\n- User impact: {description}\n\nActions:\n1. Reliability Engineer investigating root cause\n2. Metrics and logs under review\n3. Mitigation plan in progress\n\nIf breach persists >24h: Recommend extending hypercare period\nIf error budget critically low: Recommend incident freeze\n\nMonitoring for improvement...\n```\n\n**If User Adoption Low**:\n```\n⚠️ User adoption below target\n\nCurrent Adoption: {percentage}% (Target: >{target}%)\nGap: {percentage} points\n\nAnalysis:\n- Top User Issues: {list issues}\n- Support Ticket Themes: {list themes}\n- Potential Blockers: {list blockers}\n\nActions:\n1. Product Owner engaged for adoption analysis\n2. Support team reviewing common user issues\n3. Documentation and training gaps identified\n\nDecision Point:\n- If blockers identified: Prioritize fixes, may extend hypercare\n- If education needed: Launch awareness campaign\n- If feature not valuable: Escalate to stakeholders\n\nImpact on Exit Criteria: User adoption trend must improve before exit approval\n```\n\n**If Support Team Overwhelmed**:\n```\n⚠️ Support team capacity exceeded\n\nSupport Volume: {count} tickets\u002Fday (Capacity: {capacity})\nTeam Status: {STRESSED | OVERWHELMED}\n\nRoot Cause Analysis:\n- Top Issue Categories: {list categories with counts}\n- Product Bugs vs User Education: {ratio}\n\nImmediate Relief Actions:\n1. Additional support staff brought in (temp)\n2. Engineering team handling overflow tickets\n3. Workarounds created for top issues\n4. FAQ and self-service guides published\n\nMitigation:\n- Deploy hotfixes for high-frequency bugs\n- Update documentation for common questions\n- Additional training sessions scheduled\n\nImpact on Exit Criteria: Support team must be confident and staffed before exit\n```\n\n**If Exit Criteria Not Met**:\n```\n⚠️ Hypercare exit criteria not met - extension recommended\n\nExit Criteria Status: {FAIL | CONDITIONAL}\n\nGaps Identified:\n{list unmet criteria with details}\n\nRecommendation: {EXTEND HYPERCARE | CONDITIONAL EXIT | ESCALATE}\n\nExtension Plan:\n- Additional Duration: {days} days\n- Focus Areas: {list areas needing improvement}\n- Re-validation Date: {date}\n\nEscalating to user for decision...\n```\n\n## Success Criteria\n\nThis orchestration succeeds when:\n- [ ] Hypercare team established with 24\u002F7 coverage\n- [ ] Production monitoring operational (dashboards, alerts, SLO tracking)\n- [ ] Daily standups conducted for entire hypercare period\n- [ ] All incidents documented and P0\u002FP1 incidents have PIRs\n- [ ] SLO compliance ≥95% (all SLOs met for 72+ consecutive hours)\n- [ ] Zero P0\u002FP1 incidents in final 48\u002F24 hours\n- [ ] User adoption trending positive (≥target%)\n- [ ] Support team ready and confident\n- [ ] Exit criteria validated: PASS or CONDITIONAL PASS\n- [ ] Hypercare exit report complete and approved\n- [ ] Transition to standard support planned and executed\n\n## Metrics to Track\n\n**During orchestration, track**:\n- SLO compliance rate: % of SLOs met (target: 100% for 72h before exit)\n- Incident frequency: # of P0\u002FP1\u002FP2\u002FP3 incidents (target: P0\u002FP1 = 0 in final 48\u002F24h)\n- Mean time to detect (MTTD): Minutes from incident to detection (target: \u003C5 min)\n- Mean time to resolve (MTTR): Minutes from detection to resolution (target: P0 \u003C120 min, P1 \u003C480 min)\n- Error budget burn rate: % of monthly budget consumed (target: \u003C50% during hypercare)\n- User adoption rate: % of target users actively engaged (target: ≥70%)\n- Support ticket volume: # of tickets\u002Fday (target: decreasing trend)\n- Support response time: Hours to first response (target: \u003CSLA)\n\n## References\n\n**Templates** (via $AIWG_ROOT):\n- Operational Readiness Review: `agentic\u002Fcode\u002Fframeworks\u002Fsdlc-complete\u002Ftemplates\u002Freliability\u002Foperational-readiness-review-template.md`\n- SLO\u002FSLI Definition: `agentic\u002Fcode\u002Fframeworks\u002Fsdlc-complete\u002Ftemplates\u002Freliability\u002Fslo-sli-template.md`\n- Incident Response Runbook: `agentic\u002Fcode\u002Fframeworks\u002Fsdlc-complete\u002Ftemplates\u002Fdeployment\u002Fsupport-runbook-template.md`\n- Support Plan: `agentic\u002Fcode\u002Fframeworks\u002Fsdlc-complete\u002Ftemplates\u002Fdeployment\u002Fsupport-runbook-template.md`\n\n**Related Flows**:\n- Gate Check: `commands\u002Fflow-gate-check.md`\n- Handoff Checklist: `commands\u002Fflow-handoff-checklist.md`\n- Deployment Workflow: `commands\u002Fflow-deployment-workflow.md`\n\n**SDLC Phase Context**:\n- Phase: Transition (Deployment → Operations)\n- Milestone: Hypercare Complete (transition to BAU support)\n","> **Declarative Flow (#1539):** This flow's orchestration is now also expressed as a\n> declarative YAML Flow at `flows\u002Fflow-hypercare-monitoring.playbook.yaml` (source of truth for the step\n> sequence + gates). This SKILL.md remains the discoverable trigger surface and prose\n> reference. See epic #1534.\n\n# Hypercare Monitoring Flow\n\n**You are the Core Orchestrator** for the post-deployment hypercare monitoring period.\n\n## Your Role\n\n**You orchestrate multi-agent workflows. You do NOT execute bash scripts.**\n\nWhen the user requests this flow (via natural language or explicit command):\n\n1. **Interpret the request** and confirm understanding\n2. **Read this template** as your orchestration guide\n3. **Extract agent assignments** and workflow steps\n4. **Delegate agents with the current provider-native orchestration mechanism** in the correct sequence\n5. **Synthesize results** and finalize artifacts\n6. **Report completion** with summary\n\n## Hypercare Overview\n\n**Definition**: Hypercare is an elevated support period immediately following production deployment, characterized by heightened monitoring, rapid response, and intensive issue resolution.\n\n**Typical Duration**: 7-14 days (configurable based on release complexity and risk)\n\n**Focus Areas**:\n- Production stability and SLO compliance\n- Rapid incident identification and response\n- User adoption and feedback collection\n- Support team enablement\n- Smooth transition to business-as-usual operations\n\n**Exit Criteria**:\n- Zero P0 (Critical) incidents in last 48 hours\n- Zero P1 (High) incidents in last 24 hours\n- All SLOs met for 72 consecutive hours\n- User adoption metrics trending positive\n- Support team ready for standard operations\n- Hypercare report complete and approved\n\n**Expected Duration**: 7-14 days (typical), 20-30 minutes orchestration\n\n## Natural Language Triggers\n\nUsers may say:\n- \"Start hypercare\"\n- \"Begin hypercare period\"\n- \"Post-launch monitoring\"\n- \"24\u002F7 support period\"\n- \"Activate hypercare monitoring\"\n- \"Launch post-deployment support\"\n\nYou recognize these as requests for this orchestration flow.\n\n## Parameter Handling\n\n### Hypercare Duration Parameter\n\n**Purpose**: Specify hypercare period length\n\n**Examples**:\n```\n\u002Fflow-hypercare-monitoring 7 .\n\u002Fflow-hypercare-monitoring 14 .\n```\n\n**Default**: 7 days (low-risk deployments), 14 days (high-risk deployments)\n\n### --guidance Parameter\n\n**Purpose**: User provides upfront direction to tailor hypercare priorities\n\n**Examples**:\n```\n--guidance \"Focus on security monitoring, financial transaction integrity critical\"\n--guidance \"Performance is key, sub-200ms p95 response time SLO\"\n--guidance \"First production launch, team needs extra support and documentation\"\n--guidance \"High-traffic deployment, anticipate 100K daily active users\"\n```\n\n**How to Apply**:\n- Parse guidance for keywords: security, performance, compliance, scale, team experience\n- Adjust agent assignments (add security-gatekeeper, performance-engineer for specific focuses)\n- Modify monitoring depth (lightweight vs comprehensive based on complexity)\n- Influence priority ordering (stability vs. adoption focus)\n\n### --interactive Parameter\n\n**Purpose**: You ask 5-8 strategic questions to understand project context\n\n**Questions to Ask** (if --interactive):\n\n```\nI'll ask 8 strategic questions to tailor hypercare to your needs:\n\nQ1: What are your top priorities for hypercare?\n    (e.g., stability validation, user adoption, performance monitoring)\n\nQ2: What's the deployment risk level?\n    (Helps determine monitoring intensity and duration)\n\nQ3: What are your critical SLOs?\n    (Availability, response time, error rate targets)\n\nQ4: What's your expected user volume?\n    (Helps set alert thresholds and capacity monitoring)\n\nQ5: What's your support team's experience level?\n    (Influences runbook detail and escalation paths)\n\nQ6: What are your biggest concerns about this deployment?\n    (These become focus areas for monitoring and validation)\n\nQ7: Are there regulatory or compliance requirements?\n    (e.g., HIPAA, SOC2, PCI-DSS - affects audit logging and security monitoring)\n\nQ8: What's your incident response capability?\n    (24\u002F7 on-call? Business hours? Helps plan escalation and response)\n\nBased on your answers, I'll adjust:\n- Monitoring intensity (alert thresholds, dashboard focus)\n- Agent assignments (add specialized monitoring agents)\n- Exit criteria strictness (standard vs. elevated)\n- Support team guidance level (detailed runbooks vs. minimal)\n```\n\n**Synthesize Guidance**: Combine answers into structured guidance string for execution\n\n## Artifacts to Generate\n\n**Primary Deliverables**:\n- **Hypercare Team Roster**: Roles, on-call rotation, contacts → `.aiwg\u002Fdeployment\u002Fhypercare-team-roster.md`\n- **Production Health Dashboard**: Real-time monitoring config → `.aiwg\u002Fdeployment\u002Fproduction-dashboard-config.md`\n- **Alert Escalation Matrix**: Severity definitions and response SLAs → `.aiwg\u002Fdeployment\u002Falert-escalation-matrix.md`\n- **Daily Hypercare Standups**: Status reports (daily) → `.aiwg\u002Fdeployment\u002Fhypercare-standup-{YYYY-MM-DD}.md`\n- **Incident Response Logs**: All P0\u002FP1 incidents → `.aiwg\u002Fdeployment\u002Fincidents\u002Fincident-{ID}.md`\n- **Risk Retirement Report**: Validation evidence → `.aiwg\u002Frisks\u002Fhypercare-risk-validation.md`\n- **Hypercare Exit Report**: Final status and transition plan → `.aiwg\u002Freports\u002Fhypercare-exit-report.md`\n\n**Supporting Artifacts**:\n- SLO tracking logs (hourly updates)\n- User adoption metrics (daily updates)\n- Support ticket analysis (daily summary)\n- Post-incident reviews (PIRs) for all P0\u002FP1\n- Corrective action tracker\n\n## Multi-Agent Orchestration Workflow\n\n### Step 1: Establish Hypercare Team and Schedule\n\n**Purpose**: Create dedicated support structure with clear ownership and 24\u002F7 coverage\n\n**Your Actions**:\n\n1. **Read Deployment Context**:\n   ```\n   Read:\n   - .aiwg\u002Fdeployment\u002Foperational-readiness-review.md (team assignments, contacts)\n   - .aiwg\u002Fdeployment\u002Fslo-sli-definition.md (SLO targets, monitoring approach)\n   - .aiwg\u002Fdeployment\u002Fincident-response-runbook.md (escalation paths)\n   ```\n\n2. **Launch Hypercare Planning Agents** (parallel):\n   ```\n   # Agent 1: Operations Manager\n   Task(\n       subagent_type=\"operations-manager\",\n       description=\"Create hypercare team roster and on-call rotation\",\n       prompt=\"\"\"\n       Read ORR team assignments and contacts\n\n       Create Hypercare Team Roster:\n\n       ## Core Team\n       - Hypercare Lead: {name} (overall coordination, daily standups)\n       - On-Call Engineers: {rotation-schedule} (24\u002F7 coverage)\n       - Reliability Engineer: {name} (SLO monitoring, performance analysis)\n       - Support Lead: {name} (user-facing issues, ticket triage)\n       - DevOps Engineer: {name} (rapid deployment, rollback authority)\n\n       ## Extended Team\n       - Product Owner: {name} (prioritization, user impact)\n       - Security Gatekeeper: {name} (security incidents)\n       - Component Owners: {list by component}\n\n       Create 24\u002F7 On-Call Rotation ({duration} days):\n       - Primary on-call schedule (8-hour shifts or daily rotation)\n       - Backup on-call contacts\n       - Escalation path (P0\u002FP1\u002FP2\u002FP3 response procedures)\n\n       Schedule Daily Standups:\n       - Time: {suggest optimal time}\n       - Duration: 30 minutes\n       - Attendees: Core team (mandatory), Extended team (optional)\n\n       Save to: .aiwg\u002Fdeployment\u002Fhypercare-team-roster.md\n       \"\"\"\n   )\n\n   # Agent 2: Reliability Engineer\n   Task(\n       subagent_type=\"reliability-engineer\",\n       description=\"Configure production monitoring and alerting\",\n       prompt=\"\"\"\n       Read SLO\u002FSLI definitions\n\n       Configure Production Health Dashboard:\n\n       ## Key Metrics (Auto-Refresh: 30s)\n\n       **Availability**\n       - Current Uptime: {percentage}% (Target: ≥99.9%)\n       - Service Health: {GREEN | YELLOW | RED}\n       - Failed Health Checks: {count}\n\n       **Performance (Last 5 min)**\n       - Response Time (p50\u002Fp95\u002Fp99): {value}ms\n       - Throughput: {requests-per-second} req\u002Fs\n       - Target: p95 \u003C {SLA}ms\n\n       **Errors (Last 5 min)**\n       - Error Rate: {percentage}% (Target: \u003C0.1%)\n       - 4xx\u002F5xx Errors: {count}\n       - Database Errors: {count}\n\n       **Business Metrics**\n       - Active Users (Current): {count}\n       - Successful Transactions: {count}\n       - Transaction Success Rate: {percentage}%\n\n       **Infrastructure**\n       - CPU\u002FMemory Utilization: {percentage}%\n       - Disk I\u002FO, Network Traffic\n\n       Define alert thresholds for P0\u002FP1\u002FP2\u002FP3 severity levels\n\n       Save to: .aiwg\u002Fdeployment\u002Fproduction-dashboard-config.md\n       \"\"\"\n   )\n\n   # Agent 3: Support Lead\n   Task(\n       subagent_type=\"support-lead\",\n       description=\"Define alert escalation and incident response\",\n       prompt=\"\"\"\n       Read incident response runbook\n\n       Create Alert Escalation Matrix:\n\n       ## P0 (Critical) - Page Immediately\n       - Availability \u003C99%\n       - Error rate >1%\n       - All instances down\n       - Security breach detected\n\n       Action: Page on-call engineer + Hypercare Lead\n       Response SLA: Immediate acknowledgment, 15 min time-to-engage\n\n       ## P1 (High) - Alert Within 5 Minutes\n       - Availability \u003C99.5%\n       - Error rate >0.5%\n       - Response time p95 >2x SLA\n\n       Action: Alert on-call engineer via Slack + SMS\n       Response SLA: 30 min acknowledgment, 1 hour time-to-mitigation\n\n       ## P2 (Medium) - Alert Within 30 Minutes\n       - Availability \u003C99.9%\n       - Error rate >0.1%\n       - Resource utilization >80%\n\n       Action: Alert on-call engineer via Slack\n       Response SLA: 4 hours\n\n       ## P3 (Low) - Log and Review\n       - Minor performance degradation\n       - Non-critical errors\n\n       Action: Create ticket for review\n       Response SLA: 1 business day\n\n       Document incident response workflow (5 phases):\n       1. Detection (Target: \u003C5 min)\n       2. Triage (Target: \u003C15 min)\n       3. Investigation (P0=30min, P1=1h)\n       4. Mitigation (P0=1h, P1=4h)\n       5. Resolution (P0=2h, P1=8h)\n       6. Post-Incident Review (Within 48h)\n\n       Save to: .aiwg\u002Fdeployment\u002Falert-escalation-matrix.md\n       \"\"\"\n   )\n   ```\n\n3. **Synthesize Hypercare Setup Plan**:\n   ```\n   # You do this directly (no agent needed)\n\n   Read all hypercare planning artifacts\n\n   Validate completeness:\n   - Team roster: All roles assigned?\n   - On-call rotation: 24\u002F7 coverage confirmed?\n   - Monitoring: All SLOs tracked?\n   - Escalation: Response SLAs defined?\n\n   Create dedicated communication channel: #hypercare-{project-name}-{YYYY-MM}\n   ```\n\n**Communicate Progress**:\n```\n✓ Initialized hypercare setup\n⏳ Establishing hypercare team and monitoring...\n  ✓ Hypercare team roster created (Core + Extended teams)\n  ✓ 24\u002F7 on-call rotation scheduled ({duration} days)\n  ✓ Production dashboard configured (5 metric categories)\n  ✓ Alert escalation matrix defined (P0\u002FP1\u002FP2\u002FP3)\n✓ Hypercare infrastructure ready: .aiwg\u002Fdeployment\u002F\n```\n\n### Step 2: Monitor Production Stability and SLOs (Daily)\n\n**Purpose**: Continuously validate production system meets SLO targets and stability expectations\n\n**Your Actions**:\n\n1. **Launch SLO Monitoring Agents** (automated, repeat daily):\n   ```\n   # Agent 1: Reliability Engineer (Daily SLO Report)\n   Task(\n       subagent_type=\"reliability-engineer\",\n       description=\"Generate daily SLO compliance report\",\n       prompt=\"\"\"\n       Read production metrics from monitoring dashboard\n       Read SLO definitions: .aiwg\u002Fdeployment\u002Fslo-sli-definition.md\n\n       Generate Daily SLO Report:\n\n       ## SLO Tracking (Updated Hourly)\n\n       ### Availability SLO\n       - Target: ≥99.9% uptime\n       - Current (24h): {percentage}%\n       - Current (7d): {percentage}%\n       - Error Budget Remaining: {percentage}%\n       - Status: {ON TARGET | AT RISK | EXCEEDED}\n\n       ### Performance SLO\n       - Target: p95 response time \u003C{value}ms\n       - Current p95 (24h): {value}ms\n       - Current p95 (7d): {value}ms\n       - Status: {ON TARGET | AT RISK | EXCEEDED}\n\n       ### Error Rate SLO\n       - Target: \u003C0.1% error rate\n       - Current (24h): {percentage}%\n       - Current (7d): {percentage}%\n       - Status: {ON TARGET | AT RISK | EXCEEDED}\n\n       ### Throughput SLO\n       - Target: Handle {value} req\u002Fs\n       - Current Peak: {value} req\u002Fs\n       - Current Average: {value} req\u002Fs\n       - Status: {ON TARGET | AT RISK | EXCEEDED}\n\n       Calculate Error Budget Burn Rate:\n       - Monthly error budget: {value} minutes downtime allowed\n       - Hypercare period budget: {value} minutes\n       - Current burn rate: {value} minutes consumed\n       - Budget remaining: {percentage}%\n       - Assessment: {HEALTHY | MONITOR | CRITICAL}\n\n       If CRITICAL: Recommend incident freeze, focus on stability\n       If MONITOR: Recommend increased monitoring, defer risky changes\n\n       Save to: .aiwg\u002Fdeployment\u002Fslo-report-{YYYY-MM-DD}.md\n       \"\"\"\n   )\n\n   # Agent 2: Support Lead (Daily Support Analysis)\n   Task(\n       subagent_type=\"support-lead\",\n       description=\"Analyze user adoption and support tickets\",\n       prompt=\"\"\"\n       Read support ticket system\n       Read user analytics\n\n       Generate User Adoption Dashboard:\n\n       ### Active Users\n       - DAU (Daily Active Users): {count} (Target: >{target})\n       - WAU\u002FMAU: {count}\n       - User Growth Rate: {+\u002F-percentage}%\n\n       ### Feature Adoption (New Features)\n       For each new feature:\n       - Total Users: {count}\n       - Users Engaged: {count} ({percentage}%)\n       - Adoption Rate: {percentage}% (Target: >{target}%)\n       - Trend: {INCREASING | STABLE | DECREASING}\n\n       ### Support Ticket Analysis\n       - Total Tickets (24h): {count}\n       - By Category: Bug Reports, How-To, Performance, etc.\n       - Critical Issues: {count} (blockers)\n       - Average Response Time: {value}h (Target: \u003C{SLA}h)\n\n       ### User Feedback Summary\n       - Sentiment: {POSITIVE | NEUTRAL | NEGATIVE} ({percentage}%)\n       - Top Issues: {list top 3}\n       - Top Praises: {list top 3}\n\n       Flag Critical User Blockers (if any)\n\n       Save to: .aiwg\u002Fdeployment\u002Fuser-adoption-{YYYY-MM-DD}.md\n       \"\"\"\n   )\n   ```\n\n2. **Incident Tracking** (on-demand per incident):\n   ```\n   # When incident detected:\n   Task(\n       subagent_type=\"devops-engineer\",\n       description=\"Document and respond to incident {incident-ID}\",\n       prompt=\"\"\"\n       Incident detected: {incident-description}\n       Severity: {P0 | P1 | P2 | P3}\n\n       Follow Incident Response Workflow:\n\n       1. Detection (\u003C5 min):\n          - Alert acknowledged\n          - Initial severity assessment\n          - Create incident channel: #incident-{YYYY-MM-DD}-{ID}\n\n       2. Triage (\u003C15 min):\n          - Gather evidence (logs, metrics, user reports)\n          - Identify affected systems\u002Fusers\n          - Estimate business impact\n          - Engage Component Owners\n          - Update severity if needed\n\n       3. Investigation (P0=30min, P1=1h):\n          - Review logs\u002Fmetrics for root cause\n          - Check recent deployments\u002Fchanges\n          - Reproduce in non-prod if possible\n          - Identify probable root cause\n\n       4. Mitigation (P0=1h, P1=4h):\n          - Execute mitigation (rollback\u002Fhotfix\u002Fconfig change)\n          - Validate effectiveness\n          - Monitor for regression\n\n       5. Resolution (P0=2h, P1=8h):\n          - Confirm fully resolved\n          - Validate SLOs back to normal\n          - Close incident\n\n       Document incident timeline and actions\n\n       Save to: .aiwg\u002Fdeployment\u002Fincidents\u002Fincident-{ID}.md\n\n       If P0\u002FP1: Schedule post-incident review within 48h\n       \"\"\"\n   )\n   ```\n\n**Communicate Progress** (daily update):\n```\n✓ Hypercare Day {N} of {duration}\n⏳ Monitoring production stability...\n  ✓ SLO compliance: {percentage}% of SLOs met (target: 100%)\n  ✓ Incidents (24h): {count} total (P0: {count}, P1: {count}, P2: {count})\n  ✓ User adoption: {percentage}% ({trend})\n  ✓ Support tickets: {count} (Trend: {↑\u002F→\u002F↓})\n✓ Daily reports: .aiwg\u002Fdeployment\u002Fslo-report-{date}.md, user-adoption-{date}.md\n```\n\n### Step 3: Conduct Daily Hypercare Standups\n\n**Purpose**: Maintain team alignment, surface issues early, coordinate rapid response\n\n**Your Actions**:\n\n1. **Generate Daily Standup Report** (automated):\n   ```\n   Task(\n       subagent_type=\"operations-manager\",\n       description=\"Generate daily hypercare standup report\",\n       prompt=\"\"\"\n       Read daily reports:\n       - .aiwg\u002Fdeployment\u002Fslo-report-{YYYY-MM-DD}.md\n       - .aiwg\u002Fdeployment\u002Fuser-adoption-{YYYY-MM-DD}.md\n       - .aiwg\u002Fdeployment\u002Fincidents\u002F* (all open\u002Frecent incidents)\n\n       Create Daily Standup Agenda:\n\n       ## Hypercare Daily Standup - Day {N} of {duration}\n\n       **Date**: {YYYY-MM-DD}\n       **Facilitator**: {Hypercare Lead}\n\n       ### 1. Production Health Review (5 min)\n       **Presented by**: Reliability Engineer\n\n       - Availability: {percentage}% (Target: ≥99.9%) - {STATUS}\n       - Performance: p95 {value}ms (Target: \u003C{SLA}ms) - {STATUS}\n       - Error Rate: {percentage}% (Target: \u003C0.1%) - {STATUS}\n       - Error Budget: {percentage}% remaining - {STATUS}\n\n       Overall Health: {GREEN | YELLOW | RED}\n\n       ### 2. Incident Summary (Last 24h) (10 min)\n       **Presented by**: On-Call Engineer\n\n       Total Incidents: {count}\n       - P0 (Critical): {count} - {list titles if any}\n       - P1 (High): {count} - {list titles if any}\n       - P2 (Medium): {count}\n       - P3 (Low): {count}\n\n       Key Incidents:\n       For each P0\u002FP1:\n       - Incident-ID: {title}\n       - Status: {Open\u002FResolved\u002FClosed}\n       - Impact: {user-count} users, {duration} minutes\n       - Root Cause: {brief description}\n       - Action Items: {list}\n\n       Patterns\u002FTrends: {emerging issues or recurring problems}\n\n       ### 3. User Feedback Review (5 min)\n       **Presented by**: Support Lead\n\n       - Support Tickets (24h): {count} (Trend: {↑\u002F→\u002F↓})\n       - Critical User Issues: {count}\n       - Top Complaints: {list top 3}\n       - Top Praises: {list top 3}\n       - Sentiment: {POSITIVE | NEUTRAL | NEGATIVE}\n\n       Blockers for Users: {list critical issues}\n\n       ### 4. SLO\u002FSLI Status (5 min)\n       **Presented by**: Reliability Engineer\n\n       | SLO | Target | Current (24h) | Status |\n       |-----|--------|---------------|--------|\n       | Availability | ≥99.9% | {percentage}% | {✓\u002F⚠\u002F✗} |\n       | Response Time | p95\u003C{value}ms | {value}ms | {✓\u002F⚠\u002F✗} |\n       | Error Rate | \u003C0.1% | {percentage}% | {✓\u002F⚠\u002F✗} |\n       | Throughput | >{value} req\u002Fs | {value} req\u002Fs | {✓\u002F⚠\u002F✗} |\n\n       ### 5. Action Items and Blockers (5 min)\n\n       Open Action Items:\n       | Action | Owner | Due Date | Status |\n       |--------|-------|----------|--------|\n       {list open actions}\n\n       New Blockers:\n       {list blockers requiring escalation}\n\n       Tomorrow's On-Call: {name} (taking over at {HH:MM})\n\n       ---\n\n       Overall Status: {GREEN | YELLOW | RED}\n\n       Key Decisions Made:\n       {list decisions from standup}\n\n       New Action Items:\n       {list new actions assigned}\n\n       Save to: .aiwg\u002Fdeployment\u002Fhypercare-standup-{YYYY-MM-DD}.md\n       \"\"\"\n   )\n   ```\n\n2. **Weekly Summary** (if hypercare > 7 days):\n   ```\n   # On Day 7, 14, etc.:\n   Task(\n       subagent_type=\"operations-manager\",\n       description=\"Generate weekly hypercare summary\",\n       prompt=\"\"\"\n       Read all daily standups for week: .aiwg\u002Fdeployment\u002Fhypercare-standup-*.md\n\n       Create Weekly Summary:\n\n       ## Hypercare Week {N} Summary\n\n       **Week**: {date-range}\n       **Overall Status**: {GREEN | YELLOW | RED}\n\n       ### Production Stability\n       - Availability: {percentage}% (Target: ≥99.9%)\n       - Total Incidents: {count} (P0: {count}, P1: {count})\n       - MTTR: {value} min\n       - SLO Compliance: {percentage}%\n\n       ### User Adoption\n       - Active Users: {count} ({+\u002F-percentage}% vs. previous week)\n       - Feature Adoption: {percentage}%\n       - User Sentiment: {POSITIVE | NEUTRAL | NEGATIVE}\n\n       ### Support Health\n       - Support Tickets: {count} ({+\u002F-percentage}% vs. previous week)\n       - Critical Issues: {count}\n       - Response Time: {value}h (Target: \u003C{SLA}h)\n\n       ### Accomplishments\n       {list accomplishments}\n\n       ### Challenges\n       {list challenges}\n\n       ### Next Week Focus\n       {list focus areas}\n\n       Save to: .aiwg\u002Freports\u002Fhypercare-week-{N}-summary.md\n       \"\"\"\n   )\n   ```\n\n**Communicate Progress**:\n```\n⏳ Conducting daily standup...\n✓ Daily standup report generated: .aiwg\u002Fdeployment\u002Fhypercare-standup-{date}.md\n  - Overall Health: {GREEN | YELLOW | RED}\n  - Key Decisions: {count}\n  - New Action Items: {count}\n  - Escalations: {count}\n```\n\n### Step 4: Post-Incident Reviews (For P0\u002FP1 Incidents)\n\n**Purpose**: Document root cause and corrective actions for all critical incidents\n\n**Your Actions**:\n\n1. **For Each P0\u002FP1 Incident** (within 48h of resolution):\n   ```\n   Task(\n       subagent_type=\"reliability-engineer\",\n       description=\"Conduct post-incident review for {incident-ID}\",\n       prompt=\"\"\"\n       Read incident log: .aiwg\u002Fdeployment\u002Fincidents\u002Fincident-{ID}.md\n\n       Create Post-Incident Review (PIR):\n\n       ## Post-Incident Review: {Incident-ID}\n\n       **Date**: {YYYY-MM-DD}\n       **Severity**: {P0\u002FP1\u002FP2\u002FP3}\n       **Duration**: {detection-to-resolution}\n       **Impact**: {user-count} users, {downtime-minutes} minutes downtime\n\n       ### Incident Summary\n       {1-2 sentence description of what happened}\n\n       ### Timeline\n       | Time | Event | Actor |\n       |------|-------|-------|\n       {incident timeline from detection to resolution}\n\n       ### Root Cause\n       {Detailed technical root cause analysis}\n\n       ### Contributing Factors\n       1. {Factor 1 - e.g., insufficient testing}\n       2. {Factor 2 - e.g., monitoring gap}\n       3. {Factor 3 - e.g., unclear runbook}\n\n       ### Corrective Actions\n       | Action | Owner | Due Date | Status |\n       |--------|-------|----------|--------|\n       {list corrective actions to prevent recurrence}\n\n       ### Lessons Learned\n       - What went well: {list}\n       - What could improve: {list}\n       - Process changes needed: {list}\n\n       Save to: .aiwg\u002Fdeployment\u002Fincidents\u002Fpir-{ID}.md\n\n       Update incident log with PIR link\n       Track corrective actions in action tracker\n       \"\"\"\n   )\n   ```\n\n**Communicate Progress**:\n```\n⏳ Conducting post-incident reviews...\n✓ PIR complete: Incident-{ID} ({title})\n  - Root cause: {summary}\n  - Corrective actions: {count} assigned\n  - Status: Tracking to completion\n```\n\n### Step 5: Validate Exit Criteria and Generate Hypercare Report\n\n**Purpose**: Ensure production is stable and support team is ready before ending hypercare\n\n**Your Actions**:\n\n1. **Validate Exit Criteria** (on final day or when user requests):\n   ```\n   Task(\n       subagent_type=\"operations-manager\",\n       description=\"Validate hypercare exit criteria\",\n       prompt=\"\"\"\n       Read all hypercare artifacts\n\n       Validate Hypercare Exit Criteria:\n\n       ## Hypercare Exit Criteria Validation\n\n       **Hypercare Period**: Day {N} of {duration}\n       **Validation Date**: {YYYY-MM-DD}\n\n       ### Production Stability\n       - [ ] Zero P0 (Critical) incidents in last 48 hours\n       - [ ] Zero P1 (High) incidents in last 24 hours\n       - [ ] All SLOs met for 72 consecutive hours\n         - [ ] Availability ≥99.9%\n         - [ ] Response time p95 \u003C{SLA}ms\n         - [ ] Error rate \u003C0.1%\n         - [ ] Throughput >{target} req\u002Fs\n       - [ ] Error budget healthy: >{percentage}% remaining\n       - [ ] No open P0\u002FP1 incidents\n\n       ### User Adoption\n       - [ ] User adoption trending positive ({percentage}% growth)\n       - [ ] Feature adoption >{target}% for critical features\n       - [ ] User sentiment majority positive (≥70%)\n       - [ ] Support ticket volume stable or decreasing\n       - [ ] No critical user blockers unresolved\n\n       ### Support Readiness\n       - [ ] Support team trained and confident\n       - [ ] Runbooks validated (all common issues documented)\n       - [ ] Escalation paths tested and effective\n       - [ ] Knowledge base updated with hypercare learnings\n       - [ ] On-call rotation transitioned to standard support\n\n       ### Documentation Complete\n       - [ ] Hypercare report completed\n       - [ ] Post-incident reviews completed (all P0\u002FP1)\n       - [ ] Corrective actions tracked (assigned, due dates set)\n       - [ ] Lessons learned documented\n       - [ ] Runbooks updated\n\n       Overall Exit Criteria Status: {PASS | CONDITIONAL | FAIL}\n       Decision: {END HYPERCARE | EXTEND HYPERCARE | ESCALATE}\n\n       Save to: .aiwg\u002Freports\u002Fhypercare-exit-criteria.md\n       \"\"\"\n   )\n   ```\n\n2. **Generate Hypercare Exit Report** (comprehensive final report):\n   ```\n   Task(\n       subagent_type=\"operations-manager\",\n       description=\"Generate comprehensive hypercare exit report\",\n       prompt=\"\"\"\n       Read all hypercare artifacts:\n       - .aiwg\u002Fdeployment\u002Fhypercare-team-roster.md\n       - .aiwg\u002Fdeployment\u002Fslo-report-*.md (all days)\n       - .aiwg\u002Fdeployment\u002Fuser-adoption-*.md (all days)\n       - .aiwg\u002Fdeployment\u002Fhypercare-standup-*.md (all days)\n       - .aiwg\u002Fdeployment\u002Fincidents\u002F*.md (all incidents)\n       - .aiwg\u002Freports\u002Fhypercare-exit-criteria.md\n\n       Generate Hypercare Exit Report:\n\n       # Hypercare Report: {Project-Name}\n\n       **Hypercare Period**: {start-date} to {end-date} ({duration} days)\n       **Report Date**: {YYYY-MM-DD}\n       **Report Author**: {Hypercare Lead}\n\n       ## Executive Summary\n\n       {2-3 sentence summary of hypercare outcomes}\n\n       Overall Status: {SUCCESS | SUCCESS WITH CONDITIONS | CHALLENGES}\n\n       Key Metrics:\n       - Availability: {percentage}%\n       - Total Incidents: {count} (P0: {count}, P1: {count})\n       - User Adoption: {percentage}%\n       - Support Tickets: {count}\n\n       ## Production Stability Summary\n\n       ### SLO Performance\n       | SLO | Target | Achieved | Status |\n       |-----|--------|----------|--------|\n       {SLO compliance table}\n\n       SLO Compliance Rate: {percentage}%\n\n       ### Incident Summary\n       Total Incidents: {count}\n       - P0 (Critical): {count}\n       - P1 (High): {count}\n       - P2 (Medium): {count}\n       - P3 (Low): {count}\n\n       Key Metrics:\n       - MTTD (Mean Time to Detect): {value} min\n       - MTTA (Mean Time to Acknowledge): {value} min\n       - MTTR (Mean Time to Resolve): {value} min\n\n       Major Incidents:\n       For each P0\u002FP1:\n       - Incident-ID: {title}\n         - Date, Duration, Impact, Root Cause, Resolution\n         - Corrective Actions: {count} assigned\n\n       ### Performance Trends\n       - Response Time: {IMPROVED | STABLE | DEGRADED} ({+\u002F-percentage}% vs. pre-deployment)\n       - Error Rate: {IMPROVED | STABLE | DEGRADED}\n       - Resource Utilization: {HEALTHY | CONCERNING}\n\n       ## User Adoption Summary\n\n       ### Adoption Metrics\n       - Active Users: {count} ({+\u002F-percentage}% vs. pre-deployment)\n       - Feature Adoption: {percentage}% (Target: >{target}%)\n       - User Retention (Day 14): {percentage}%\n\n       ### User Feedback\n       - Total Feedback Items: {count}\n       - Sentiment: {percentage}% positive\n       - Net Promoter Score: {value}\n\n       Top Praises: {list top 3}\n       Top Complaints: {list top 3 with resolution status}\n\n       ## Support Summary\n\n       ### Ticket Volume\n       - Total Support Tickets: {count}\n       - Daily Average: {count} tickets\u002Fday\n       - Trend: {DECREASING | STABLE | INCREASING}\n\n       ### Support Performance\n       - Average Response Time: {value}h (Target: \u003C{SLA}h) - {✓\u002F⚠\u002F✗}\n       - First Contact Resolution: {percentage}%\n\n       ### Support Team Readiness\n       - Team Confidence Level: {HIGH | MEDIUM | LOW}\n       - Runbook Completeness: {percentage}%\n\n       ## Lessons Learned\n\n       ### What Went Well\n       {list successes}\n\n       ### What Could Improve\n       {list improvements}\n\n       ### Process Recommendations\n       {list recommendations for future deployments}\n\n       ## Corrective Actions\n\n       Total Actions Identified: {count}\n\n       | Action | Category | Owner | Due Date | Status |\n       |--------|----------|-------|----------|--------|\n       {corrective actions table}\n\n       ## Handover to Standard Support\n\n       ### Transition Plan\n       - [ ] Standard on-call rotation activated (starting {date})\n       - [ ] Support runbooks transferred\n       - [ ] Knowledge base published\n       - [ ] Support team training complete\n       - [ ] Escalation paths updated for BAU\n\n       ### Post-Hypercare Monitoring\n       - Duration: {duration} days continued close monitoring\n       - Responsible: {Support Lead}\n       - Review Cadence: Weekly check-ins for {duration} weeks\n\n       ## Conclusion\n\n       {2-3 sentence summary and readiness for standard support}\n\n       Recommendation: {END HYPERCARE | EXTEND HYPERCARE}\n\n       Signoff:\n       - Hypercare Lead: {name} - {date}\n       - Reliability Engineer: {name} - {date}\n       - Support Lead: {name} - {date}\n       - Product Owner: {name} - {date}\n       - Project Manager: {name} - {date}\n\n       Save to: .aiwg\u002Freports\u002Fhypercare-exit-report.md\n       \"\"\"\n   )\n   ```\n\n3. **Present Exit Summary to User**:\n   ```\n   # You present this directly (not via agent)\n\n   Read .aiwg\u002Freports\u002Fhypercare-exit-report.md\n\n   Present summary:\n   ─────────────────────────────────────────────\n   Hypercare Monitoring Period Complete\n   ─────────────────────────────────────────────\n\n   **Hypercare Period**: {start-date} to {end-date} ({duration} days)\n   **Overall Status**: {SUCCESS | SUCCESS WITH CONDITIONS | CHALLENGES}\n\n   **Key Metrics**:\n   ✓ Availability: {percentage}% (Target: ≥99.9%)\n   ✓ Total Incidents: {count} (P0: {count}, P1: {count})\n   ✓ User Adoption: {percentage}% of target\n   ✓ Support Readiness: Team confident and ready\n\n   **Exit Criteria Status**:\n   ✓ Production Stability: {PASS | CONDITIONAL | FAIL}\n   ✓ User Adoption: {PASS | CONDITIONAL | FAIL}\n   ✓ Support Readiness: {PASS | CONDITIONAL | FAIL}\n   ✓ Documentation: {PASS | CONDITIONAL | FAIL}\n\n   **Decision**: {END HYPERCARE | EXTEND HYPERCARE | ESCALATE}\n\n   **Artifacts Generated**:\n   - Hypercare Team Roster (.aiwg\u002Fdeployment\u002Fhypercare-team-roster.md)\n   - Production Dashboard Config (.aiwg\u002Fdeployment\u002Fproduction-dashboard-config.md)\n   - Alert Escalation Matrix (.aiwg\u002Fdeployment\u002Falert-escalation-matrix.md)\n   - Daily Standup Reports (.aiwg\u002Fdeployment\u002Fhypercare-standup-*.md, {count} files)\n   - SLO Reports (.aiwg\u002Fdeployment\u002Fslo-report-*.md, {count} files)\n   - User Adoption Reports (.aiwg\u002Fdeployment\u002Fuser-adoption-*.md, {count} files)\n   - Incident Logs (.aiwg\u002Fdeployment\u002Fincidents\u002F*.md, {count} files)\n   - Post-Incident Reviews (.aiwg\u002Fdeployment\u002Fincidents\u002Fpir-*.md, {count} files)\n   - Hypercare Exit Report (.aiwg\u002Freports\u002Fhypercare-exit-report.md)\n\n   **Next Steps**:\n   - Review hypercare exit report with stakeholders\n   - Obtain formal signoffs (5 required signatures)\n   - If END HYPERCARE: Transition to standard support (run handoff workflow)\n   - If EXTEND HYPERCARE: Address gaps, continue monitoring\n   - If ESCALATE: Executive decision required\n\n   **Transition to Standard Support**:\n   - Standard on-call rotation activated: {date}\n   - Continued monitoring period: {duration} days\n   - Weekly check-ins scheduled\n\n   ─────────────────────────────────────────────\n   ```\n\n**Communicate Progress**:\n```\n⏳ Validating hypercare exit criteria...\n✓ Exit criteria validated: {PASS | CONDITIONAL | FAIL}\n✓ Hypercare Exit Report generated: .aiwg\u002Freports\u002Fhypercare-exit-report.md\n✓ Transition plan documented\n```\n\n## Quality Gates\n\nBefore marking workflow complete, verify:\n- [ ] Hypercare team established with 24\u002F7 coverage\n- [ ] Production monitoring operational (dashboards, alerts)\n- [ ] Daily standups conducted and documented\n- [ ] All P0\u002FP1 incidents have post-incident reviews\n- [ ] SLO compliance tracked daily\n- [ ] User adoption monitored and reported\n- [ ] Exit criteria validated\n- [ ] Hypercare exit report complete and approved\n- [ ] Transition to standard support planned\n\n## User Communication\n\n**At start**: Confirm understanding and list activities\n\n```\nUnderstood. I'll orchestrate the hypercare monitoring period.\n\nHypercare Duration: {duration} days\nHypercare Period: {start-date} to {estimated-end-date}\n\nThis will establish:\n- Hypercare team roster and 24\u002F7 on-call rotation\n- Production health monitoring dashboards\n- Alert escalation and incident response procedures\n- Daily standup coordination\n- SLO tracking and user adoption monitoring\n- Post-incident review process\n- Hypercare exit criteria validation\n\nI'll coordinate multiple agents for comprehensive monitoring and support.\nExpected setup: 20-30 minutes.\n\nStarting orchestration...\n```\n\n**During**: Update progress with clear indicators\n\n```\n✓ = Complete\n⏳ = In progress\n❌ = Error\u002Fblocked\n⚠️ = Warning\u002Fattention needed\n```\n\n**Daily**: Provide daily status summary\n\n```\nHypercare Day {N} of {duration}: {GREEN | YELLOW | RED}\n\nProduction Health:\n✓ Availability: {percentage}% (Target: ≥99.9%)\n✓ Performance: p95 {value}ms (Target: \u003C{SLA}ms)\n{⚠️ | ✓} Error Rate: {percentage}% (Target: \u003C0.1%)\n\nIncidents (24h):\n- P0: {count}\n- P1: {count}\n- P2: {count}\n\nUser Adoption: {percentage}% ({trend})\n\nDaily reports: .aiwg\u002Fdeployment\u002Fhypercare-standup-{date}.md\n```\n\n**At end**: Summary report (see Step 5.3 above)\n\n## Error Handling\n\n**If P0 Incident During Hypercare**:\n```\n❌ Critical incident detected - immediate response initiated\n\nIncident: {incident-ID} - {title}\nSeverity: P0 (Complete outage \u002F Data loss \u002F Security breach)\nImpact: {user-count} users affected\n\nActions:\n1. On-call engineer + Hypercare Lead paged\n2. Incident war room created: #incident-{date}-{ID}\n3. Executive Sponsor notified\n4. Status page updated\n\nResponse Timeline:\n- Detection: {timestamp}\n- Acknowledgment: {timestamp} (Target: Immediate)\n- Time-to-engage: {minutes} min (Target: \u003C15 min)\n\nCurrent Status: {INVESTIGATING | MITIGATING | RESOLVED}\n\nImpact on Exit Criteria: P0 incident resets 48h \"zero critical incidents\" requirement\n\nMonitoring incident response...\n```\n\n**If SLO Breach**:\n```\n⚠️ SLO breach detected - immediate investigation required\n\nSLO Breached: {SLO-name}\n- Target: {target-value}\n- Current: {actual-value}\n- Duration: {duration} (continuous breach)\n\nImpact:\n- Error budget consumed: {percentage}%\n- User impact: {description}\n\nActions:\n1. Reliability Engineer investigating root cause\n2. Metrics and logs under review\n3. Mitigation plan in progress\n\nIf breach persists >24h: Recommend extending hypercare period\nIf error budget critically low: Recommend incident freeze\n\nMonitoring for improvement...\n```\n\n**If User Adoption Low**:\n```\n⚠️ User adoption below target\n\nCurrent Adoption: {percentage}% (Target: >{target}%)\nGap: {percentage} points\n\nAnalysis:\n- Top User Issues: {list issues}\n- Support Ticket Themes: {list themes}\n- Potential Blockers: {list blockers}\n\nActions:\n1. Product Owner engaged for adoption analysis\n2. Support team reviewing common user issues\n3. Documentation and training gaps identified\n\nDecision Point:\n- If blockers identified: Prioritize fixes, may extend hypercare\n- If education needed: Launch awareness campaign\n- If feature not valuable: Escalate to stakeholders\n\nImpact on Exit Criteria: User adoption trend must improve before exit approval\n```\n\n**If Support Team Overwhelmed**:\n```\n⚠️ Support team capacity exceeded\n\nSupport Volume: {count} tickets\u002Fday (Capacity: {capacity})\nTeam Status: {STRESSED | OVERWHELMED}\n\nRoot Cause Analysis:\n- Top Issue Categories: {list categories with counts}\n- Product Bugs vs User Education: {ratio}\n\nImmediate Relief Actions:\n1. Additional support staff brought in (temp)\n2. Engineering team handling overflow tickets\n3. Workarounds created for top issues\n4. FAQ and self-service guides published\n\nMitigation:\n- Deploy hotfixes for high-frequency bugs\n- Update documentation for common questions\n- Additional training sessions scheduled\n\nImpact on Exit Criteria: Support team must be confident and staffed before exit\n```\n\n**If Exit Criteria Not Met**:\n```\n⚠️ Hypercare exit criteria not met - extension recommended\n\nExit Criteria Status: {FAIL | CONDITIONAL}\n\nGaps Identified:\n{list unmet criteria with details}\n\nRecommendation: {EXTEND HYPERCARE | CONDITIONAL EXIT | ESCALATE}\n\nExtension Plan:\n- Additional Duration: {days} days\n- Focus Areas: {list areas needing improvement}\n- Re-validation Date: {date}\n\nEscalating to user for decision...\n```\n\n## Success Criteria\n\nThis orchestration succeeds when:\n- [ ] Hypercare team established with 24\u002F7 coverage\n- [ ] Production monitoring operational (dashboards, alerts, SLO tracking)\n- [ ] Daily standups conducted for entire hypercare period\n- [ ] All incidents documented and P0\u002FP1 incidents have PIRs\n- [ ] SLO compliance ≥95% (all SLOs met for 72+ consecutive hours)\n- [ ] Zero P0\u002FP1 incidents in final 48\u002F24 hours\n- [ ] User adoption trending positive (≥target%)\n- [ ] Support team ready and confident\n- [ ] Exit criteria validated: PASS or CONDITIONAL PASS\n- [ ] Hypercare exit report complete and approved\n- [ ] Transition to standard support planned and executed\n\n## Metrics to Track\n\n**During orchestration, track**:\n- SLO compliance rate: % of SLOs met (target: 100% for 72h before exit)\n- Incident frequency: # of P0\u002FP1\u002FP2\u002FP3 incidents (target: P0\u002FP1 = 0 in final 48\u002F24h)\n- Mean time to detect (MTTD): Minutes from incident to detection (target: \u003C5 min)\n- Mean time to resolve (MTTR): Minutes from detection to resolution (target: P0 \u003C120 min, P1 \u003C480 min)\n- Error budget burn rate: % of monthly budget consumed (target: \u003C50% during hypercare)\n- User adoption rate: % of target users actively engaged (target: ≥70%)\n- Support ticket volume: # of tickets\u002Fday (target: decreasing trend)\n- Support response time: Hours to first response (target: \u003CSLA)\n\n## References\n\n**Templates** (via $AIWG_ROOT):\n- Operational Readiness Review: `agentic\u002Fcode\u002Fframeworks\u002Fsdlc-complete\u002Ftemplates\u002Freliability\u002Foperational-readiness-review-template.md`\n- SLO\u002FSLI Definition: `agentic\u002Fcode\u002Fframeworks\u002Fsdlc-complete\u002Ftemplates\u002Freliability\u002Fslo-sli-template.md`\n- Incident Response Runbook: `agentic\u002Fcode\u002Fframeworks\u002Fsdlc-complete\u002Ftemplates\u002Fdeployment\u002Fsupport-runbook-template.md`\n- Support Plan: `agentic\u002Fcode\u002Fframeworks\u002Fsdlc-complete\u002Ftemplates\u002Fdeployment\u002Fsupport-runbook-template.md`\n\n**Related Flows**:\n- Gate Check: `commands\u002Fflow-gate-check.md`\n- Handoff Checklist: `commands\u002Fflow-handoff-checklist.md`\n- Deployment Workflow: `commands\u002Fflow-deployment-workflow.md`\n\n**SDLC Phase Context**:\n- Phase: Transition (Deployment → Operations)\n- Milestone: Hypercare Complete (transition to BAU support)\n",{"name":5,"namespace":49,"platforms":50,"commandHint":52,"description":7},"aiwg",[51],"all",{"model":31,"category":53,"modelRole":34,"modelTier":29,"allowedTools":54,"argumentHint":55,"orchestration":56},"sdlc-orchestration","Task, Read, Write, Glob, TodoWrite","[hypercare-duration-days] [project-directory] [--guidance \"text\"] [--interactive]",true,"main","a602706fc62ff1cfcb18001358ac39647b08acf5","agentic\u002Fcode\u002Fplugins\u002Fsdlc\u002Fskills\u002Fflow-hypercare-monitoring",36,"https:\u002F\u002Fgithub.com\u002Fjmagly\u002Faiwg","https:\u002F\u002Faiwg.io","https:\u002F\u002Fgithub.com\u002Fjmagly","https:\u002F\u002Fintegrolabs.io","ml\u002Fai, industrial automation, safety\u002Fsecurity, ssi\r\n\r\nmagly.net\r\nintegrolabs.io\r\naiwg.io\r\nfortemi.com\r\npagenary.com\r\nbytecask.com","2026-11-12 00:33:10",{"source":8,"skillName":5,"commands":68,"prompt":78,"zipAvailable":56},[69,72,75],{"tool":70,"command":71},"npx","npx skills add jmagly\u002Faiwg --skill flow-hypercare-monitoring",{"tool":73,"command":74},"bunx","bunx skills add jmagly\u002Faiwg --skill flow-hypercare-monitoring",{"tool":76,"command":77},"pnpm","pnpm dlx skills add jmagly\u002Faiwg --skill flow-hypercare-monitoring","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjmagly\u002Faiwg\u002Fblob\u002Fmain\u002Fagentic\u002Fcode\u002Fplugins\u002Fsdlc\u002Fskills\u002Fflow-hypercare-monitoring\u002FSKILL.md",[],[81,108,131,137,144,157],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":88,"publishedAt":44},"01M70QA0BSYJ49EES9V4RE8QH1","host-hardening","Read-only system hardening baseline and plan-first host hardening recommendations for SSH, Docker bind addresses, firewall persistence, datastores, exporters and audit retention.","https:\u002F\u002Fgithub.com\u002Fjmagly\u002Faiwg\u002Fblob\u002Fmain\u002Fagentic\u002Fcode\u002Fplugins\u002Fsecurity-engineering\u002Fskills\u002Fhost-hardening\u002FSKILL.md",[87],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[89,90,91,37,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107],"host","host hardening","hardening","re","recommendations","remediation","plan","port","verification","Bash","access","only","retention","audit","never","firewall","bind","secrets","request",{"skillNo":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":112,"categories":113,"keywords":118,"publishedAt":44},"01M70PNT2Z4HMZPRBTAF6073NN","exposure-analysis","Read-only firewall analysis and effective host exposure reconstruction for Docker published ports, UFW bypass, stale rules, CDN scope, IPv6 asymmetry and external probe allowlists.","https:\u002F\u002Fgithub.com\u002Fjmagly\u002Faiwg\u002Fblob\u002Fmain\u002Fagentic\u002Fcode\u002Fplugins\u002Fforensics\u002Fskills\u002Fexposure-analysis\u002FSKILL.md",[114,117],{"categoryNo":115,"categoryName":116,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000011","运维与部署",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[119,120,121,37,122,96,123,124,98,125,89,126,100,127,128,103,104,129,130,36],"exposure analysis","analysis","unknown","credentials","collection","ufw","ports","internet","local","scope","reconstruction","operator",{"skillNo":132,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":133,"categories":134,"keywords":136,"publishedAt":44},"01M70P8QATMPKA78E4FT5D2TNA","https:\u002F\u002Fgithub.com\u002Fjmagly\u002Faiwg\u002Fblob\u002Fmain\u002Fagentic\u002Fcode\u002Fframeworks\u002Fsecurity-engineering\u002Fskills\u002Fhost-hardening\u002FSKILL.md",[135],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[91,89,90,99,37,107,94,93,102,95,96,97,98,106,100,101,92,103,104,105],{"skillNo":138,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":139,"categories":140,"keywords":143,"publishedAt":44},"01M70NMPVJ5H0JH131P60FW4R8","https:\u002F\u002Fgithub.com\u002Fjmagly\u002Faiwg\u002Fblob\u002Fmain\u002Fagentic\u002Fcode\u002Fframeworks\u002Fforensics-complete\u002Fskills\u002Fexposure-analysis\u002FSKILL.md",[141,142],{"categoryNo":115,"categoryName":116,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[120,119,103,122,96,123,98,121,89,126,100,127,128,37,104,125,124,129,130,36],{"skillNo":145,"name":146,"nameZh":6,"description":147,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":148,"categories":149,"keywords":151,"publishedAt":44},"01M6CB4DDR0B4NNCFK7ZK7449H","fixture-skill","Exercise rule delivery.","https:\u002F\u002Fgithub.com\u002Fjmagly\u002Faiwg\u002Fblob\u002Fmain\u002Ftest\u002Ffixtures\u002Frule-delivery\u002Fskills\u002Ffixture-skill\u002FSKILL.md",[150],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[152,153,154,155,30,156],"fixture skill","fixture","rule","delivery","exercise",{"skillNo":158,"name":159,"nameZh":6,"description":160,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":161,"categories":162,"keywords":164,"publishedAt":44},"01M6CB4AVK1W76MFMPP0JP32CJ","pi-local","Pi-local duplicate-precedence fixture.","https:\u002F\u002Fgithub.com\u002Fjmagly\u002Faiwg\u002Fblob\u002Fmain\u002Ftest\u002Ffixtures\u002Fproviders\u002Fpi\u002Fproject\u002F.pi\u002Fskills\u002Fpi-local\u002FSKILL.md",[163],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[165,166,127,167,153],"pi","pi local","duplicate"]