[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MKFXH3B7MTSN4ABGYJVX8C":3,"skill-same:01M6MKFXH3B7MTSN4ABGYJVX8C":91},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":27,"publishedAt":48,"linkOnly":49,"markdownContent":50,"markdownBody":51,"frontMatter":52,"refName":71,"commitSha":72,"skillDirectory":73,"forksCount":13,"repositoryHtmlUrl":74,"repositoryHomepageUrl":6,"ownerHtmlUrl":75,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":76,"install":77,"resources":90},"01M6MKFXH3B7MTSN4ABGYJVX8C","pm-skills",null,"Use when coordinating project-delivery work across the 8 project-management sub-skills — sprint\u002Fvelocity analytics, portfolio health, Jira\u002FJQL, Confluence, Atlassian admin, templates, meeting analysis, team comms. Triggers on 'our sprints feel off', 'project health report', 'audit our Jira permissions', 'when will it be done', 'run the delivery loop'. Forks context to route to one sub-skill via a deterministic signal router and returns a digest; can also drive a full goal→plan→execute→verify→close delivery loop through the repo-wide agent-harness with Jira MCP data bridged into the domain's analytics tools. Distinct from product-team (what to build vs how to deliver it), business-operations (internal ops), and engineering\u002Fagent-harness (the generic loop engine this orchestrator plugs into).","JiayiV\u002Fquestion_mixing","JiayiV","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F54466889?v=4","01M6JFJYYMRZ3QRGP9339JNQ2K","01M6JFJZ35KB0QVT50NAHPJA7G",0,"MIT","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Fpublic-02-claude-skills-main-project-management-skills-pm-skills-skill-ee21305f\u002FSKILL.md",[17,22],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",{"categoryNo":23,"categoryName":24,"taxonomyType":25,"taxonomyTypeDesc":26},"01JBSEEDCAT000000000000033","数据分析师","PROFESSION","适用职业",[28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47],"pm","pm skills","comms","MCP","close","jql","full","project","digest","portfolio","router","project-management","plan","loop","how","team","permissions","run","jira","analytics","2026-11-10 10:12:30",false,"---\nname: \"pm-skills\"\ndescription: \"Use when coordinating project-delivery work across the 8 project-management sub-skills — sprint\u002Fvelocity analytics, portfolio health, Jira\u002FJQL, Confluence, Atlassian admin, templates, meeting analysis, team comms. Triggers on 'our sprints feel off', 'project health report', 'audit our Jira permissions', 'when will it be done', 'run the delivery loop'. Forks context to route to one sub-skill via a deterministic signal router and returns a digest; can also drive a full goal→plan→execute→verify→close delivery loop through the repo-wide agent-harness with Jira MCP data bridged into the domain's analytics tools. Distinct from product-team (what to build vs how to deliver it), business-operations (internal ops), and engineering\u002Fagent-harness (the generic loop engine this orchestrator plugs into).\"\ncontext: fork\nversion: 2.11.1\nauthor: Alireza Rezvani\nlicense: MIT\ntags: [project-management, orchestrator, jira, confluence, atlassian, scrum, agile, flow-metrics, agent-harness]\ncompatible_tools: [claude-code, codex-cli, cursor, antigravity, opencode, gemini-cli]\n---\n\n# Project Management — Domain Orchestrator & Delivery Loop\n\nThis orchestrator does two jobs. **Routing:** fork context, classify a PM inquiry with\n`scripts\u002Fpm_goal_router.py`, run exactly one of the 8 sub-skills, return a digest.\n**Looping:** turn a delivery goal into a bounded agentic loop — pull live Jira data via the\nbundled Atlassian MCP, bridge it into the domain's deterministic analytics tools, verify\nevery step with machine-run gates, and refuse to close until everything is verified or a\nhuman waives it. The bundled `.mcp.json` wires the Atlassian Remote MCP\n(`https:\u002F\u002Fmcp.atlassian.com\u002Fv1\u002Fsse`, OAuth handled by Claude Code).\n\n## When to invoke\n\n| Symptom | Sub-skill |\n|---|---|\n| \"Project\u002Fportfolio health, risk EMV, capacity\" | `senior-pm` |\n| \"Sprint velocity, retro follow-through, ceremony health, when-will-it-be-done\" | `scrum-master` |\n| \"JQL, Jira workflows, boards, automation\" | `jira-expert` |\n| \"Confluence spaces, page trees, content audits\" | `confluence-expert` |\n| \"Users, groups, permissions, SSO\" | `atlassian-admin` |\n| \"Reusable Jira\u002FConfluence templates\" | `atlassian-templates` |\n| \"Meeting transcripts, talk time, action items\" | `meeting-analyzer` |\n| \"Status updates, 3P updates, stakeholder comms\" | `team-communications` |\n\n## Routing logic (deterministic)\n\nRun the router — do not eyeball the table when a script can decide:\n\n```bash\npython3 scripts\u002Fpm_goal_router.py --text \"\u003Cthe goal>\" --output json\n```\n\nExit 0 → `route_to` names the sub-skill: load its SKILL.md and follow its workflow.\nExit 2 → ask ONE clarifying question naming the listed candidates, with a recommended\nanswer. Exit 3 → no signal: ask the user to restate the goal with the deliverable named.\nNever guess silently; never silently chain a second sub-skill — digest first, confirm, then\nchain.\n\n## The delivery loop (agentic)\n\nFor goals (not questions) — \"get sprint 14 to a verified close\", \"produce a portfolio\nhealth report from live Jira\", \"make our flow metrics visible weekly\" — run the\nloop-library contract (Observe → Choose → Act → Verify → Record → Repeat-or-stop):\n\n1. **Observe** — pull fresh state: `mcp__atlassian__searchJiraIssuesUsingJql` (get\n   `cloudId` via `getAccessibleAtlassianResources` first), save the result JSON, then\n   bridge it:\n   ```bash\n   python3 scripts\u002Fjira_snapshot_bridge.py --input snapshot.json --to flow            # WIP, throughput, cycle time p50\u002F85\u002F95, work-item age, SLE, aging alerts\n   python3 scripts\u002Fjira_snapshot_bridge.py --input snapshot.json --to sprint > s.json # scrum-master schema\n   python3 ..\u002Fscrum-master\u002Fscripts\u002Fvelocity_analyzer.py s.json                        # velocity + volatility + forecast\n   ```\n   Add `--forecast N` for a seeded Monte Carlo \"when will N items be done\" answer\n   (refuses on \u003C 10 completed items — thin history forecasts are lies).\n2. **Choose** — route the next task with `pm_goal_router.py`; one task at a time.\n3. **Act** — execute with the routed sub-skill's own tools per its SKILL.md.\n4. **Verify** — gate the plan and every close with:\n   ```bash\n   python3 scripts\u002Fdelivery_loop_gate.py --plan plan.json --mode plan    # exit 2 = blocked\n   python3 scripts\u002Fdelivery_loop_gate.py --plan plan.json --mode close   # exit 4 = close refused\n   ```\n   Plus each sub-skill's own gates (scrum-master's ≥ 3-sprints rule, atlassian-admin's\n   VERIFY steps). Never adjudicate your own verification.\n5. **Record \u002F Repeat-or-stop** — for multi-task goals, run the state through the repo-wide\n   harness (it enforces attempt caps, iteration budgets, and evidence logging):\n   ```bash\n   python3 engineering\u002Fagent-harness\u002Fskills\u002Fagent-harness\u002Fscripts\u002Fgoal_compiler.py \\\n     --goal \"\u003Cgoal>\" --manifest engineering\u002Fagent-harness\u002Fskills\u002Fagent-harness\u002Fassets\u002Fharnesses\u002Fproject-management.json \\\n     --out .agent-harness\u002Fplan.json\n   python3 engineering\u002Fagent-harness\u002Fskills\u002Fagent-harness\u002Fscripts\u002Floop_controller.py init|next|record|verify|close ...\n   ```\n   Terminal states: success, clean no-op, blocked, approval-required, exhausted,\n   stagnated. An exhausted budget is an escalation — never a success report.\n\n## Hard rules (agentic delegation governance)\n\n1. **Agents are contributors, never owners** (Linear model): every loop task carries a\n   named human owner; agent-executed tasks also carry a named human reviewer.\n   `delivery_loop_gate.py` enforces this (G1\u002FG2).\n2. **Acceptance must be machine-checkable** — a command, or a criterion with a threshold.\n   \"Looks good\" is not a gate (G3).\n3. **Every Jira\u002FConfluence write is auditable and reversible-first** (Rovo discipline):\n   never `transitionJiraIssue` to Done without verify evidence; destructive\u002Firreversible\n   actions (deletes, permission changes, org-wide admin) are approval-required terminal\n   states, not loop steps.\n4. **Never modify a gate you are judged by** — same locked-evaluator invariant as\n   autoresearch-agent.\n5. **Forecasts are ranges with confidence, never dates** — Monte Carlo percentiles\n   (p50\u002Fp70\u002Fp85\u002Fp95), per Vacanti. Single-date promises are the anti-pattern.\n6. **Max 3 attempts per task, 12 loop iterations per goal** — then escalate to the named\n   human with the evidence log.\n\n## Forcing-question library (grill-with-docs pattern)\n\nOne per turn, recommended answer, canon citation. Never run a sub-skill or start a loop\nuntil the lane-defining decision is locked:\n\n- **SPRINT lane**: \"Do you want to *measure* flow (cycle time, WIP, throughput, age) or\n  *forecast* delivery? Recommended: measure first — a forecast off unmeasured flow is\n  noise. Canon: Kanban Guide (May 2025) four mandatory flow measures; Vacanti,\n  *Actionable Agile Metrics*.\"\n- **HEALTH lane**: \"Is your project status self-reported RAG or derived from signals?\n  Recommended: derive it (schedule variance, aging WIP, scope churn) and diff against the\n  self-report — that diff finds watermelon projects. Canon: Kanban Guide 2025;\n  DORA 2025 (AI amplifies, doesn't fix, weak signals).\"\n- **JIRA lane**: \"Is this configuration change deployable to a test project first?\n  Recommended: always stage in a test project; jira-expert's workflow validator must exit\n  0 before production. Canon: jira-expert validation workflow.\"\n- **ADMIN lane**: \"Is this action reversible, and who approves it? Recommended: name the\n  approver before touching permissions — admin actions are approval-required terminal\n  states in any loop. Canon: atlassian-admin VERIFY discipline; loop-library stop states.\"\n- **LOOP intake**: \"What single observable outcome means DONE, and which command proves\n  it? Recommended: a named artifact + a command that exits 0 against it. Canon:\n  agent-harness verifier's law; Anthropic, *Building Effective Agents* (evaluator needs\n  clear criteria).\"\n- **MEETINGS\u002FCOMMS lanes**: \"Could this meeting be an async written update? Recommended:\n  status-broadcast meetings convert to async 3P updates; decision meetings keep sync.\n  Canon: GitLab async-first handbook.\"\n\n## Assumptions\n\n1. The user has (or is preparing analysis for someone with) delivery authority.\n2. Jira\u002FConfluence access goes through the bundled MCP; capabilities NOT in\n   `project-management\u002Freferences\u002Fatlassian-mcp-tools.md` (project\u002Fsprint\u002Fboard\u002Fspace\n   creation, admin config) are done in the web UI — never invent tool names.\n3. Inputs may be partial — every tool ships `--sample` so the shape is visible first.\n\n## Non-goals\n\n- Not a replacement for the sub-skills — the orchestrator routes and loops; the\n  sub-skills do the work.\n- Not the generic loop engine — that is `engineering\u002Fagent-harness`; this orchestrator is\n  the PM-domain adapter (data bridge + governance gate + lane router).\n- Does not decide *what* to build — that's `product-team`.\n\n## Output artifacts\n\n| Mode | Artifact |\n|---|---|\n| Route | Sub-skill's own artifact + ≤ 200-word digest with one canon-cited challenge |\n| Flow report | `flow_metrics.json` (bridge output) with SLE conformance + aging alerts |\n| Delivery loop | `.agent-harness\u002Fplan.json` + `state.json` + gate verdicts + close handoff |\n\n## Anti-patterns (do not)\n\n- ❌ Run all 8 sub-skills \"to be thorough\" — route to one, digest, chain on confirmation\n- ❌ Report sprint health or forecasts from hand-typed numbers when a Jira snapshot is one\n  MCP call away — bridge real data\n- ❌ Close a loop with unverified tasks, or report an exhausted budget as success\n- ❌ Let an agent be the assignee of record — humans own, agents contribute\n- ❌ Auto-transition Jira issues or touch permissions inside a loop without the named\n  approver\n\n## References\n\n- [references\u002Fflow_forecasting_canon.md](references\u002Fflow_forecasting_canon.md) — Kanban\n  Guide 2025, Vacanti Monte Carlo, DORA 2025, EBM, SPACE\n- [references\u002Fagentic_delivery_governance.md](references\u002Fagentic_delivery_governance.md) —\n  Linear\u002FRovo delegation models, Anthropic agent patterns, audit discipline\n- [references\u002Fpm_loop_playbook.md](references\u002Fpm_loop_playbook.md) — the five reusable PM\n  loops (sprint, health, retro-action, RAID-hygiene, comms) mapped to the loop contract\n- Canonical MCP tool list: `project-management\u002Freferences\u002Fatlassian-mcp-tools.md`\n- Loop engine: `engineering\u002Fagent-harness` · Loop vocabulary: `loop-library`\n","# Project Management — Domain Orchestrator & Delivery Loop\n\nThis orchestrator does two jobs. **Routing:** fork context, classify a PM inquiry with\n`scripts\u002Fpm_goal_router.py`, run exactly one of the 8 sub-skills, return a digest.\n**Looping:** turn a delivery goal into a bounded agentic loop — pull live Jira data via the\nbundled Atlassian MCP, bridge it into the domain's deterministic analytics tools, verify\nevery step with machine-run gates, and refuse to close until everything is verified or a\nhuman waives it. The bundled `.mcp.json` wires the Atlassian Remote MCP\n(`https:\u002F\u002Fmcp.atlassian.com\u002Fv1\u002Fsse`, OAuth handled by Claude Code).\n\n## When to invoke\n\n| Symptom | Sub-skill |\n|---|---|\n| \"Project\u002Fportfolio health, risk EMV, capacity\" | `senior-pm` |\n| \"Sprint velocity, retro follow-through, ceremony health, when-will-it-be-done\" | `scrum-master` |\n| \"JQL, Jira workflows, boards, automation\" | `jira-expert` |\n| \"Confluence spaces, page trees, content audits\" | `confluence-expert` |\n| \"Users, groups, permissions, SSO\" | `atlassian-admin` |\n| \"Reusable Jira\u002FConfluence templates\" | `atlassian-templates` |\n| \"Meeting transcripts, talk time, action items\" | `meeting-analyzer` |\n| \"Status updates, 3P updates, stakeholder comms\" | `team-communications` |\n\n## Routing logic (deterministic)\n\nRun the router — do not eyeball the table when a script can decide:\n\n```bash\npython3 scripts\u002Fpm_goal_router.py --text \"\u003Cthe goal>\" --output json\n```\n\nExit 0 → `route_to` names the sub-skill: load its SKILL.md and follow its workflow.\nExit 2 → ask ONE clarifying question naming the listed candidates, with a recommended\nanswer. Exit 3 → no signal: ask the user to restate the goal with the deliverable named.\nNever guess silently; never silently chain a second sub-skill — digest first, confirm, then\nchain.\n\n## The delivery loop (agentic)\n\nFor goals (not questions) — \"get sprint 14 to a verified close\", \"produce a portfolio\nhealth report from live Jira\", \"make our flow metrics visible weekly\" — run the\nloop-library contract (Observe → Choose → Act → Verify → Record → Repeat-or-stop):\n\n1. **Observe** — pull fresh state: `mcp__atlassian__searchJiraIssuesUsingJql` (get\n   `cloudId` via `getAccessibleAtlassianResources` first), save the result JSON, then\n   bridge it:\n   ```bash\n   python3 scripts\u002Fjira_snapshot_bridge.py --input snapshot.json --to flow            # WIP, throughput, cycle time p50\u002F85\u002F95, work-item age, SLE, aging alerts\n   python3 scripts\u002Fjira_snapshot_bridge.py --input snapshot.json --to sprint > s.json # scrum-master schema\n   python3 ..\u002Fscrum-master\u002Fscripts\u002Fvelocity_analyzer.py s.json                        # velocity + volatility + forecast\n   ```\n   Add `--forecast N` for a seeded Monte Carlo \"when will N items be done\" answer\n   (refuses on \u003C 10 completed items — thin history forecasts are lies).\n2. **Choose** — route the next task with `pm_goal_router.py`; one task at a time.\n3. **Act** — execute with the routed sub-skill's own tools per its SKILL.md.\n4. **Verify** — gate the plan and every close with:\n   ```bash\n   python3 scripts\u002Fdelivery_loop_gate.py --plan plan.json --mode plan    # exit 2 = blocked\n   python3 scripts\u002Fdelivery_loop_gate.py --plan plan.json --mode close   # exit 4 = close refused\n   ```\n   Plus each sub-skill's own gates (scrum-master's ≥ 3-sprints rule, atlassian-admin's\n   VERIFY steps). Never adjudicate your own verification.\n5. **Record \u002F Repeat-or-stop** — for multi-task goals, run the state through the repo-wide\n   harness (it enforces attempt caps, iteration budgets, and evidence logging):\n   ```bash\n   python3 engineering\u002Fagent-harness\u002Fskills\u002Fagent-harness\u002Fscripts\u002Fgoal_compiler.py \\\n     --goal \"\u003Cgoal>\" --manifest engineering\u002Fagent-harness\u002Fskills\u002Fagent-harness\u002Fassets\u002Fharnesses\u002Fproject-management.json \\\n     --out .agent-harness\u002Fplan.json\n   python3 engineering\u002Fagent-harness\u002Fskills\u002Fagent-harness\u002Fscripts\u002Floop_controller.py init|next|record|verify|close ...\n   ```\n   Terminal states: success, clean no-op, blocked, approval-required, exhausted,\n   stagnated. An exhausted budget is an escalation — never a success report.\n\n## Hard rules (agentic delegation governance)\n\n1. **Agents are contributors, never owners** (Linear model): every loop task carries a\n   named human owner; agent-executed tasks also carry a named human reviewer.\n   `delivery_loop_gate.py` enforces this (G1\u002FG2).\n2. **Acceptance must be machine-checkable** — a command, or a criterion with a threshold.\n   \"Looks good\" is not a gate (G3).\n3. **Every Jira\u002FConfluence write is auditable and reversible-first** (Rovo discipline):\n   never `transitionJiraIssue` to Done without verify evidence; destructive\u002Firreversible\n   actions (deletes, permission changes, org-wide admin) are approval-required terminal\n   states, not loop steps.\n4. **Never modify a gate you are judged by** — same locked-evaluator invariant as\n   autoresearch-agent.\n5. **Forecasts are ranges with confidence, never dates** — Monte Carlo percentiles\n   (p50\u002Fp70\u002Fp85\u002Fp95), per Vacanti. Single-date promises are the anti-pattern.\n6. **Max 3 attempts per task, 12 loop iterations per goal** — then escalate to the named\n   human with the evidence log.\n\n## Forcing-question library (grill-with-docs pattern)\n\nOne per turn, recommended answer, canon citation. Never run a sub-skill or start a loop\nuntil the lane-defining decision is locked:\n\n- **SPRINT lane**: \"Do you want to *measure* flow (cycle time, WIP, throughput, age) or\n  *forecast* delivery? Recommended: measure first — a forecast off unmeasured flow is\n  noise. Canon: Kanban Guide (May 2025) four mandatory flow measures; Vacanti,\n  *Actionable Agile Metrics*.\"\n- **HEALTH lane**: \"Is your project status self-reported RAG or derived from signals?\n  Recommended: derive it (schedule variance, aging WIP, scope churn) and diff against the\n  self-report — that diff finds watermelon projects. Canon: Kanban Guide 2025;\n  DORA 2025 (AI amplifies, doesn't fix, weak signals).\"\n- **JIRA lane**: \"Is this configuration change deployable to a test project first?\n  Recommended: always stage in a test project; jira-expert's workflow validator must exit\n  0 before production. Canon: jira-expert validation workflow.\"\n- **ADMIN lane**: \"Is this action reversible, and who approves it? Recommended: name the\n  approver before touching permissions — admin actions are approval-required terminal\n  states in any loop. Canon: atlassian-admin VERIFY discipline; loop-library stop states.\"\n- **LOOP intake**: \"What single observable outcome means DONE, and which command proves\n  it? Recommended: a named artifact + a command that exits 0 against it. Canon:\n  agent-harness verifier's law; Anthropic, *Building Effective Agents* (evaluator needs\n  clear criteria).\"\n- **MEETINGS\u002FCOMMS lanes**: \"Could this meeting be an async written update? Recommended:\n  status-broadcast meetings convert to async 3P updates; decision meetings keep sync.\n  Canon: GitLab async-first handbook.\"\n\n## Assumptions\n\n1. The user has (or is preparing analysis for someone with) delivery authority.\n2. Jira\u002FConfluence access goes through the bundled MCP; capabilities NOT in\n   `project-management\u002Freferences\u002Fatlassian-mcp-tools.md` (project\u002Fsprint\u002Fboard\u002Fspace\n   creation, admin config) are done in the web UI — never invent tool names.\n3. Inputs may be partial — every tool ships `--sample` so the shape is visible first.\n\n## Non-goals\n\n- Not a replacement for the sub-skills — the orchestrator routes and loops; the\n  sub-skills do the work.\n- Not the generic loop engine — that is `engineering\u002Fagent-harness`; this orchestrator is\n  the PM-domain adapter (data bridge + governance gate + lane router).\n- Does not decide *what* to build — that's `product-team`.\n\n## Output artifacts\n\n| Mode | Artifact |\n|---|---|\n| Route | Sub-skill's own artifact + ≤ 200-word digest with one canon-cited challenge |\n| Flow report | `flow_metrics.json` (bridge output) with SLE conformance + aging alerts |\n| Delivery loop | `.agent-harness\u002Fplan.json` + `state.json` + gate verdicts + close handoff |\n\n## Anti-patterns (do not)\n\n- ❌ Run all 8 sub-skills \"to be thorough\" — route to one, digest, chain on confirmation\n- ❌ Report sprint health or forecasts from hand-typed numbers when a Jira snapshot is one\n  MCP call away — bridge real data\n- ❌ Close a loop with unverified tasks, or report an exhausted budget as success\n- ❌ Let an agent be the assignee of record — humans own, agents contribute\n- ❌ Auto-transition Jira issues or touch permissions inside a loop without the named\n  approver\n\n## References\n\n- [references\u002Fflow_forecasting_canon.md](references\u002Fflow_forecasting_canon.md) — Kanban\n  Guide 2025, Vacanti Monte Carlo, DORA 2025, EBM, SPACE\n- [references\u002Fagentic_delivery_governance.md](references\u002Fagentic_delivery_governance.md) —\n  Linear\u002FRovo delegation models, Anthropic agent patterns, audit discipline\n- [references\u002Fpm_loop_playbook.md](references\u002Fpm_loop_playbook.md) — the five reusable PM\n  loops (sprint, health, retro-action, RAID-hygiene, comms) mapped to the loop contract\n- Canonical MCP tool list: `project-management\u002Freferences\u002Fatlassian-mcp-tools.md`\n- Loop engine: `engineering\u002Fagent-harness` · Loop vocabulary: `loop-library`\n",{"name":5,"tags":53,"author":61,"context":62,"license":14,"version":63,"description":7,"compatible_tools":64},[39,54,46,55,56,57,58,59,60],"orchestrator","confluence","atlassian","scrum","agile","flow-metrics","agent-harness","Alireza Rezvani","fork","2.11.1",[65,66,67,68,69,70],"claude-code","codex-cli","cursor","antigravity","opencode","gemini-cli","main","068c2486ccc0f8d200a3db4d21ec137064eda3b4","skills\u002Fpublic-02-claude-skills-main-project-management-skills-pm-skills-skill-ee21305f","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing","https:\u002F\u002Fgithub.com\u002FJiayiV","2026-08-25 16:30:52",{"source":8,"skillName":5,"commands":78,"prompt":88,"zipAvailable":89},[79,82,85],{"tool":80,"command":81},"npx","npx skills add JiayiV\u002Fquestion_mixing --skill pm-skills",{"tool":83,"command":84},"bunx","bunx skills add JiayiV\u002Fquestion_mixing --skill pm-skills",{"tool":86,"command":87},"pnpm","pnpm dlx skills add JiayiV\u002Fquestion_mixing --skill pm-skills","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Fpublic-02-claude-skills-main-project-management-skills-pm-skills-skill-ee21305f\u002FSKILL.md",true,[],[92,118,145,173,201,234],{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":48},"01M6NN9PJS9NHWPDG4QP93BP8F","webmcpify","Make a web app agent-ready — propose a WebMCP tool manifest, integrate, verify in a real browser, heal; unrelated code stays untouched. Use for \"webmcpify\", \"add WebMCP\", or \"expose app actions to AI agents\".","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Fwebmcpify\u002FSKILL.md",[],[94,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117],"github","ai agents","web","notes","code","browser","https","actions","manifest","inventory","verify","tool","use","ready","unrelated","app","scope","for","webmcp",{"skillNo":119,"name":120,"nameZh":6,"description":121,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":122,"licenseFileUrl":6,"sourceHtmlUrl":123,"categories":124,"keywords":125,"publishedAt":48},"01M6NN6KZE5RBN6NGHN2WXV1RE","vardoger-analyze","Use when the user asks to personalize the GitHub Copilot CLI assistant, adapt Copilot to their style, use vardoger, or analyze their Copilot CLI conversation history. Reads the local session directory at `~\u002F.copilot\u002Fsession-state\u002F`, extracts recurring preferences and conventions, and writes a fenced personalization block into `~\u002F.copilot\u002Fcopilot-instructions.md`. Runs entirely on the user's machine via the local `vardoger` CLI (`pipx install vardoger`); no network calls and no uploads. Triggers: 'personalize my copilot', 'analyze my copilot history', 'tailor copilot to me', 'run vardoger', 'update my copilot instructions from history', 'make copilot learn my style'.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Fvardoger-analyze\u002FSKILL.md",[],[126,127,128,129,130,131,45,132,133,134,135,136,137,138,139,140,141,142,143,144],"vardoger analyze","analyze","directory","cli","github copilot","copilot","update","learn","network","my style","install","conversation","me","local","github copilot cli","pipx","my","at","copilot instructions",{"skillNo":146,"name":147,"nameZh":6,"description":148,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":149,"categories":150,"keywords":155,"publishedAt":48},"01M6NN3CZGQP3XAJ04BM1NNYGT","transloadit-media-processing","Process media files (video, audio, images, documents) using Transloadit. Use when asked to encode video to HLS\u002FMP4, generate thumbnails, resize or watermark images, extract audio, concatenate clips, add subtitles, OCR documents, or run any media processing pipeline. Covers 86+ processing robots for file transformation at scale.","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Ftransloadit-media-processing\u002FSKILL.md",[151,154],{"categoryNo":152,"categoryName":153,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000016","图像与多媒体",{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},[156,157,158,159,31,160,161,162,163,164,165,166,167,111,168,169,170,171,116,172],"transloadit media processing","Media","media processing","processing","mcp server","documents","subtitles","pipeline","ocr","Video","Audio","mp4","images","files","transformation","free","hls",{"skillNo":174,"name":175,"nameZh":6,"description":176,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":177,"categories":178,"keywords":182,"publishedAt":48},"01M6NN28E92F9GH4WFYQ2H1Y15","terraform-azurerm-set-diff-analyzer","Analyze Terraform plan JSON output for AzureRM Provider to distinguish between false-positive diffs (order-only changes in Set-type attributes) and actual resource changes. Use when reviewing terraform plan output for Azure resources like Application Gateway, Load Balancer, Firewall, Front Door, NSG, and other resources with Set-type attributes that cause spurious diffs due to internal ordering changes.","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Fterraform-azurerm-set-diff-analyzer\u002FSKILL.md",[179],{"categoryNo":180,"categoryName":181,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000011","运维与部署",[183,184,185,186,187,188,189,190,191,111,192,193,194,195,196,197,198,199,200,116],"terraform","SET","terraform azurerm set diff analyzer","diff","analyzer","diffs","azure","gateway","firewall","only","resource changes","provider","resources","load balancer","attributes","front","load","balancer",{"skillNo":202,"name":203,"nameZh":6,"description":204,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":205,"categories":206,"keywords":216,"publishedAt":48},"01M6NN1QMH2TDYWTH3XY3N5XPV","technical-job-search","Use this skill when a software engineer asks for help with job search tasks: parsing or analyzing a job description, tailoring a CV\u002Fresume, writing a cover letter, evaluating a job offer, or drafting a post-interview follow-up email. Do not activate for general career advice unrelated to an active job search action.","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Ftechnical-job-search\u002FSKILL.md",[207,210,213],{"categoryNo":208,"categoryName":209,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":211,"categoryName":212,"taxonomyType":25,"taxonomyTypeDesc":26},"01JBSEEDCAT000000000000036","内容创作者",{"categoryNo":214,"categoryName":215,"taxonomyType":25,"taxonomyTypeDesc":26},"01JBSEEDCAT000000000000038","人力资源",[217,218,219,220,221,222,223,224,127,225,111,226,227,228,229,230,231,232,116,233],"search","Job Search","technical job search","technical","writing","tasks","email","parsing","interview","up","engineer","general","activate","do","task","cv","letter",{"skillNo":235,"name":236,"nameZh":6,"description":237,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":238,"categories":239,"keywords":240,"publishedAt":48},"01M6NMZFA67XYS1GS09WT42235","steno-mode","Shorthand-first response compression that cuts ~40% of response tokens while preserving technical precision and exact literals. Use when the user says \"steno mode\", \"shorthand mode\", \"compressed responses\", \"token reduction\", \"brief structured output\", or invokes \u002Fsteno. Supports four compression levels: lite, brief, court, machine. Do not trigger for requests needing polished prose such as onboarding\u002Ftutorial content, stakeholder or customer-facing copy, or teaching-focused explanations.","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Fsteno-mode\u002FSKILL.md",[],[241,242,243,244,245,220,246,111,230,247,248,249,250,251,252,253,254,255,116,256],"steno mode","mode","customer","brief","first","tutorial","teaching","tokens","as","trigger","structured output","machine","output","court","requests","response compression"]