[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79BS3PR92A4QNEJAFNDKB2G":3,"skill-same:01M79BS3PR92A4QNEJAFNDKB2G":46},{"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":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":14,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":29,"ownerDescription":30,"updatedAt":31,"install":32,"resources":45},"01M79BS3PR92A4QNEJAFNDKB2G","team-coordination",null,"Agent Teams orchestration patterns for multi-agent SAFe workflows. Use when spawning agent teams, coordinating teammates, enforcing quality gates via task dependencies, or orchestrating the 11-agent SAFe pipeline. Covers team creation, messaging, shared task lists, and SAFe gate enforcement. Do NOT use for single-agent or simple subagent workflows.","sahil-kaushik1\u002FAuditing-Workflow","sahil-kaushik1","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F143880923?v=4","01M79BEEK3947RQYD3WC00K9W3","Sahil Kaushik","01M79BEEKVHPFPTNBDB0GFXBHE",0,"MIT","https:\u002F\u002Fgithub.com\u002Fsahil-kaushik1\u002FAuditing-Workflow\u002Fblob\u002Fmain\u002F.gemini\u002Fskills\u002Fteam-coordination\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: team-coordination\ndescription: >\n  Agent Teams orchestration patterns for multi-agent SAFe workflows. Use when\n  spawning agent teams, coordinating teammates, enforcing quality gates via task\n  dependencies, or orchestrating the 11-agent SAFe pipeline. Covers team\n  creation, messaging, shared task lists, and SAFe gate enforcement.\n  Do NOT use for single-agent or simple subagent workflows.\n---\n\n# Team Coordination Skill\n\n> **TEMPLATE**: This skill uses `{{PLACEHOLDER}}` tokens. Replace with your project values before use.\n\n## Purpose\n\nOrchestrate multi-agent teams for SAFe workflows. This skill provides patterns for spawning teams, assigning work by role, enforcing quality gates via task dependencies, and managing the full delivery pipeline.\n\n## Prerequisites\n\nAgent Teams may be **experimental** depending on provider. Enable as required:\n\n```json\n\u002F\u002F Provider-specific settings\n{\n  \"env\": {\n    \"AGENT_TEAMS_ENABLED\": \"1\"\n  }\n}\n```\n\n## When This Skill Applies\n\n- Orchestrating work across multiple agent roles (FE, BE, QAS, etc.)\n- Spawning a team for a Feature or Epic-level deliverable\n- Coordinating parallel implementation with quality gate enforcement\n- Running competing hypothesis debugging with multiple agents\n- Performing parallel code review across security, performance, and test coverage\n\n## Agent Teams vs Subagents vs Background Agents\n\n| Approach | Communication | Coordination | Best For |\n|----------|--------------|--------------|----------|\n| **Agent Teams** | DMs, broadcasts | Shared TaskList with dependencies | Complex multi-role SAFe workflows |\n| **Subagents** | Report back only | Main agent manages | Focused tasks, results only |\n| **Background Agents** | None | None | Fire-and-forget parallel work |\n\n**Use Agent Teams when**: teammates need to share findings, challenge each other, and coordinate via SAFe gates.\n**Use Subagents when**: you need quick, focused workers that report back.\n**Use Background Agents when**: tasks are independent and do not need coordination.\n\n## SAFe Team Patterns\n\n### Pattern 1: TDM as Team Lead\n\nThe TDM (Technical Delivery Manager) is the natural team lead in the 11-agent model:\n\n```text\nCreate an agent team for {{TICKET_PREFIX}}-XXX implementation.\n\nTeam lead (TDM) responsibilities:\n- Spawn teammates by role (BE, FE, QAS, etc.)\n- Create tasks with SAFe gate dependencies\n- Monitor progress and steer teammates\n- Synthesize results and escalate blockers\n\nSpawn these teammates:\n- BE Developer: Implement API endpoints per spec\n- FE Developer: Implement UI components per spec\n- QAS: Validate acceptance criteria after implementation\n```\n\n### Pattern 2: Task Dependencies for Quality Gates\n\nUse task dependencies to enforce the SAFe pipeline:\n\n```text\nTask structure for {{TICKET_PREFIX}}-XXX:\n\n1. \"Implement API endpoint\" (owner: be-developer)\n2. \"Implement UI components\" (owner: fe-developer)\n3. \"QAS validation\" (owner: qas, blockedBy: [1, 2])\n4. \"Create PR\" (owner: rte, blockedBy: [3])\n5. \"Stage 1 review\" (owner: system-architect, blockedBy: [4])\n\nThis enforces: Implementation -> QAS -> RTE -> Architect Review\n```\n\n### Pattern 3: Spawning Teammates by Role\n\nMap harness agent roles to teammate configurations:\n\n```text\nSpawn teammates with role-specific prompts:\n\nBE Developer teammate:\n- Load: api-patterns, rls-patterns skills\n- Task: Implement endpoints per spec at specs\u002F{{TICKET_PREFIX}}-XXX-spec.md\n- Constraint: All DB operations must use RLS context helpers\n\nFE Developer teammate:\n- Load: frontend-patterns skill\n- Task: Implement UI per spec\n- Constraint: Follow component patterns in patterns_library\u002Fui\u002F\n\nQAS teammate:\n- Load: testing-patterns skill\n- Task: Execute testing strategy from spec\n- Constraint: Must verify all acceptance criteria before approving\n```\n\n### Pattern 4: Parallel Code Review\n\n```text\nCreate an agent team to review PR #XXX. Spawn three reviewers:\n- Security reviewer: Focus on RLS enforcement, input validation, auth checks\n- Architecture reviewer: Focus on pattern compliance, separation of concerns\n- Test reviewer: Focus on test coverage, edge cases, acceptance criteria\n\nHave them each review independently, then share and challenge findings.\n```\n\n### Pattern 5: Competing Hypothesis Debugging\n\n```text\nUsers report [issue description]. Spawn 3-4 teammates to investigate:\n- Teammate 1: Investigate [hypothesis A]\n- Teammate 2: Investigate [hypothesis B]\n- Teammate 3: Investigate [hypothesis C]\n\nHave them talk to each other to challenge and disprove theories.\nUpdate findings as consensus emerges.\n```\n\n## Communication Patterns\n\n### Direct Messages (Most Common)\n\n```text\nSend a message to the BE developer:\n\"The API endpoint needs to handle pagination. Check patterns_library\u002Fapi\u002F\nfor the standard pagination pattern before implementing.\"\n```\n\n### Broadcast (Use Sparingly -- Expensive)\n\n```text\nBroadcast to all teammates:\n\"STOP: Architecture decision changed. The auth middleware now uses\n{{AUTH_PROVIDER}} session tokens instead of JWT. Check the updated\nspec before continuing.\"\n```\n\nOnly broadcast for:\n- Critical blocking issues\n- Architecture changes affecting everyone\n- Stop-the-line announcements\n\n### Shutdown Coordination\n\n```text\nWhen all tasks are complete:\n1. Send shutdown request to each teammate\n2. Wait for approval from each\n3. Clean up team resources\n```\n\n## Quality Gate Hooks\n\n### TeammateIdle Hook\n\nValidates teammates completed their work before going idle. Configure hook to return exit code 2 to send feedback and keep the teammate working.\n\n### TaskCompleted Hook\n\nValidates task output meets criteria before allowing completion. Configure hook to return exit code 2 to prevent completion and send feedback.\n\n## Team Sizing Guidelines\n\n| Work Scope | Recommended Size | Tasks per Teammate |\n|-----------|-----------------|-------------------|\n| Single Story | 2-3 teammates | 3-4 tasks each |\n| Feature (multi-story) | 3-5 teammates | 5-6 tasks each |\n| Epic (parallel features) | 5-8 teammates | 5-6 tasks each |\n\n**Rules of thumb**:\n- Start with fewer teammates; scale up if needed\n- Each teammate should own different files (avoid conflicts)\n- 5-6 tasks per teammate keeps everyone productive\n- More than 8 teammates rarely helps (coordination overhead)\n\n## Known Limitations\n\n- **Experimental**: May require feature flag to enable\n- **No session resumption**: Resuming may not restore in-process teammates\n- **One team per session**: Clean up before starting a new team\n- **No nested teams**: Teammates cannot spawn their own teams\n- **Permissions inherit**: All teammates start with lead's permission mode\n- **Token cost**: Significantly higher than single session\n\n## Authoritative References\n\n- **Harness Agents**: `AGENTS.md`\n- **Team Config**: `.claude\u002Fteam-config.json` (if applicable)\n- **Agent Workflow SOP**: `docs\u002Fsop\u002FAGENT_WORKFLOW_SOP.md`\n","# Team Coordination Skill\n\n> **TEMPLATE**: This skill uses `{{PLACEHOLDER}}` tokens. Replace with your project values before use.\n\n## Purpose\n\nOrchestrate multi-agent teams for SAFe workflows. This skill provides patterns for spawning teams, assigning work by role, enforcing quality gates via task dependencies, and managing the full delivery pipeline.\n\n## Prerequisites\n\nAgent Teams may be **experimental** depending on provider. Enable as required:\n\n```json\n\u002F\u002F Provider-specific settings\n{\n  \"env\": {\n    \"AGENT_TEAMS_ENABLED\": \"1\"\n  }\n}\n```\n\n## When This Skill Applies\n\n- Orchestrating work across multiple agent roles (FE, BE, QAS, etc.)\n- Spawning a team for a Feature or Epic-level deliverable\n- Coordinating parallel implementation with quality gate enforcement\n- Running competing hypothesis debugging with multiple agents\n- Performing parallel code review across security, performance, and test coverage\n\n## Agent Teams vs Subagents vs Background Agents\n\n| Approach | Communication | Coordination | Best For |\n|----------|--------------|--------------|----------|\n| **Agent Teams** | DMs, broadcasts | Shared TaskList with dependencies | Complex multi-role SAFe workflows |\n| **Subagents** | Report back only | Main agent manages | Focused tasks, results only |\n| **Background Agents** | None | None | Fire-and-forget parallel work |\n\n**Use Agent Teams when**: teammates need to share findings, challenge each other, and coordinate via SAFe gates.\n**Use Subagents when**: you need quick, focused workers that report back.\n**Use Background Agents when**: tasks are independent and do not need coordination.\n\n## SAFe Team Patterns\n\n### Pattern 1: TDM as Team Lead\n\nThe TDM (Technical Delivery Manager) is the natural team lead in the 11-agent model:\n\n```text\nCreate an agent team for {{TICKET_PREFIX}}-XXX implementation.\n\nTeam lead (TDM) responsibilities:\n- Spawn teammates by role (BE, FE, QAS, etc.)\n- Create tasks with SAFe gate dependencies\n- Monitor progress and steer teammates\n- Synthesize results and escalate blockers\n\nSpawn these teammates:\n- BE Developer: Implement API endpoints per spec\n- FE Developer: Implement UI components per spec\n- QAS: Validate acceptance criteria after implementation\n```\n\n### Pattern 2: Task Dependencies for Quality Gates\n\nUse task dependencies to enforce the SAFe pipeline:\n\n```text\nTask structure for {{TICKET_PREFIX}}-XXX:\n\n1. \"Implement API endpoint\" (owner: be-developer)\n2. \"Implement UI components\" (owner: fe-developer)\n3. \"QAS validation\" (owner: qas, blockedBy: [1, 2])\n4. \"Create PR\" (owner: rte, blockedBy: [3])\n5. \"Stage 1 review\" (owner: system-architect, blockedBy: [4])\n\nThis enforces: Implementation -> QAS -> RTE -> Architect Review\n```\n\n### Pattern 3: Spawning Teammates by Role\n\nMap harness agent roles to teammate configurations:\n\n```text\nSpawn teammates with role-specific prompts:\n\nBE Developer teammate:\n- Load: api-patterns, rls-patterns skills\n- Task: Implement endpoints per spec at specs\u002F{{TICKET_PREFIX}}-XXX-spec.md\n- Constraint: All DB operations must use RLS context helpers\n\nFE Developer teammate:\n- Load: frontend-patterns skill\n- Task: Implement UI per spec\n- Constraint: Follow component patterns in patterns_library\u002Fui\u002F\n\nQAS teammate:\n- Load: testing-patterns skill\n- Task: Execute testing strategy from spec\n- Constraint: Must verify all acceptance criteria before approving\n```\n\n### Pattern 4: Parallel Code Review\n\n```text\nCreate an agent team to review PR #XXX. Spawn three reviewers:\n- Security reviewer: Focus on RLS enforcement, input validation, auth checks\n- Architecture reviewer: Focus on pattern compliance, separation of concerns\n- Test reviewer: Focus on test coverage, edge cases, acceptance criteria\n\nHave them each review independently, then share and challenge findings.\n```\n\n### Pattern 5: Competing Hypothesis Debugging\n\n```text\nUsers report [issue description]. Spawn 3-4 teammates to investigate:\n- Teammate 1: Investigate [hypothesis A]\n- Teammate 2: Investigate [hypothesis B]\n- Teammate 3: Investigate [hypothesis C]\n\nHave them talk to each other to challenge and disprove theories.\nUpdate findings as consensus emerges.\n```\n\n## Communication Patterns\n\n### Direct Messages (Most Common)\n\n```text\nSend a message to the BE developer:\n\"The API endpoint needs to handle pagination. Check patterns_library\u002Fapi\u002F\nfor the standard pagination pattern before implementing.\"\n```\n\n### Broadcast (Use Sparingly -- Expensive)\n\n```text\nBroadcast to all teammates:\n\"STOP: Architecture decision changed. The auth middleware now uses\n{{AUTH_PROVIDER}} session tokens instead of JWT. Check the updated\nspec before continuing.\"\n```\n\nOnly broadcast for:\n- Critical blocking issues\n- Architecture changes affecting everyone\n- Stop-the-line announcements\n\n### Shutdown Coordination\n\n```text\nWhen all tasks are complete:\n1. Send shutdown request to each teammate\n2. Wait for approval from each\n3. Clean up team resources\n```\n\n## Quality Gate Hooks\n\n### TeammateIdle Hook\n\nValidates teammates completed their work before going idle. Configure hook to return exit code 2 to send feedback and keep the teammate working.\n\n### TaskCompleted Hook\n\nValidates task output meets criteria before allowing completion. Configure hook to return exit code 2 to prevent completion and send feedback.\n\n## Team Sizing Guidelines\n\n| Work Scope | Recommended Size | Tasks per Teammate |\n|-----------|-----------------|-------------------|\n| Single Story | 2-3 teammates | 3-4 tasks each |\n| Feature (multi-story) | 3-5 teammates | 5-6 tasks each |\n| Epic (parallel features) | 5-8 teammates | 5-6 tasks each |\n\n**Rules of thumb**:\n- Start with fewer teammates; scale up if needed\n- Each teammate should own different files (avoid conflicts)\n- 5-6 tasks per teammate keeps everyone productive\n- More than 8 teammates rarely helps (coordination overhead)\n\n## Known Limitations\n\n- **Experimental**: May require feature flag to enable\n- **No session resumption**: Resuming may not restore in-process teammates\n- **One team per session**: Clean up before starting a new team\n- **No nested teams**: Teammates cannot spawn their own teams\n- **Permissions inherit**: All teammates start with lead's permission mode\n- **Token cost**: Significantly higher than single session\n\n## Authoritative References\n\n- **Harness Agents**: `AGENTS.md`\n- **Team Config**: `.claude\u002Fteam-config.json` (if applicable)\n- **Agent Workflow SOP**: `docs\u002Fsop\u002FAGENT_WORKFLOW_SOP.md`\n",{"name":5,"description":7},"main","39a25d63191d67efe43cdce5b7507069e2307f0f",".gemini\u002Fskills\u002Fteam-coordination","https:\u002F\u002Fgithub.com\u002Fsahil-kaushik1\u002FAuditing-Workflow","https:\u002F\u002Fgithub.com\u002Fsahil-kaushik1","https:\u002F\u002Fdrive.google.com\u002Ffile\u002Fd\u002F1Te4TcrpgcN4j8DsYqVdjPl4QXVbs5XXo\u002Fview?usp=drive_link","Web3 security researcher \u002F developer","2026-10-18 15:17:21",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add sahil-kaushik1\u002FAuditing-Workflow --skill team-coordination",{"tool":38,"command":39},"bunx","bunx skills add sahil-kaushik1\u002FAuditing-Workflow --skill team-coordination",{"tool":41,"command":42},"pnpm","pnpm dlx skills add sahil-kaushik1\u002FAuditing-Workflow --skill team-coordination","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fsahil-kaushik1\u002FAuditing-Workflow\u002Fblob\u002Fmain\u002F.gemini\u002Fskills\u002Fteam-coordination\u002FSKILL.md",true,[],[47,53,59,66,73,80],{"skillNo":48,"name":49,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":50,"categories":51,"keywords":52,"publishedAt":19},"01M79BSEAG0SS9CC2EN1S51K2X","stripe-patterns","https:\u002F\u002Fgithub.com\u002Fsahil-kaushik1\u002FAuditing-Workflow\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fsync\u002Frendertrust\u002F.claude\u002Fskills\u002Fstripe-patterns\u002FSKILL.md",[],[],{"skillNo":54,"name":55,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":58,"publishedAt":19},"01M79BSBAZXQBWCPKYJP38A35B","payment-patterns","https:\u002F\u002Fgithub.com\u002Fsahil-kaushik1\u002FAuditing-Workflow\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fsync\u002Fkeryk-ai\u002F.claude\u002Fskills\u002Fpayment-patterns\u002FSKILL.md",[],[],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":19},"01M79BS8PKZXFGBNQBS2GHNXZW","testing-patterns","Testing patterns for Jest and Playwright. Use when writing tests, setting up test fixtures, or validating RLS enforcement. Routes to existing test conventions.","https:\u002F\u002Fgithub.com\u002Fsahil-kaushik1\u002FAuditing-Workflow\u002Fblob\u002Fmain\u002F.gemini\u002Fskills\u002Ftesting-patterns\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":19},"01M79BRZ422QD8D5QHQMXAVPWZ","task-compilation","Compile broad audit goals into structured proof obligations with 9 mandatory fields. Used after decomposition by the Threat Modeler agent.","https:\u002F\u002Fgithub.com\u002Fsahil-kaushik1\u002FAuditing-Workflow\u002Fblob\u002Fmain\u002F.gemini\u002Fskills\u002Ftask-compilation\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":19},"01M79BRV2MK2AJZBNSE2BETP28","storage-layout-analysis","Proxy patterns, slot collisions, upgrade safety. Used during decomposition to identify storage-related vulnerabilities in upgradeable contracts.","https:\u002F\u002Fgithub.com\u002Fsahil-kaushik1\u002FAuditing-Workflow\u002Fblob\u002Fmain\u002F.gemini\u002Fskills\u002Fstorage-layout-analysis\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":19},"01M79BRQSR9Z3YEEKFRWKHETP3","state-machine-analysis","Map legal\u002Fillegal state transitions, stuck states, impossible states. Used during decomposition to feed the Threat Modeler with transition tables.","https:\u002F\u002Fgithub.com\u002Fsahil-kaushik1\u002FAuditing-Workflow\u002Fblob\u002Fmain\u002F.gemini\u002Fskills\u002Fstate-machine-analysis\u002FSKILL.md",[],[]]