[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79XE4SBPD7XFC4D3H81CSJS":3,"skill-same:01M79XE4SBPD7XFC4D3H81CSJS":62},{"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":31,"commitSha":32,"skillDirectory":33,"forksCount":34,"repositoryHtmlUrl":35,"repositoryHomepageUrl":6,"ownerHtmlUrl":36,"ownerBlogUrl":6,"ownerDescription":37,"updatedAt":38,"install":39,"resources":51},"01M79XE4SBPD7XFC4D3H81CSJS","postmortem",null,"Auto-generates a structured postmortem from a completed campaign. Reads the campaign file, telemetry logs, and feature ledger. Produces a documented analysis of what broke, what the safety systems caught, and what patterns emerged. Can also be invoked manually for any incident.","mayankjain1815-commits\u002FCITADEL","mayankjain1815-commits","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F234472344?v=4","01M79X9599EWEQTD62DMNTEG7X","Mayank jain","01M79X95AA0KDFTN1Z1A6DQTX1",4,"MIT","https:\u002F\u002Fgithub.com\u002Fmayankjain1815-commits\u002FCITADEL\u002Fblob\u002Fmain\u002Fskills\u002Fpostmortem\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: postmortem\nlicense: MIT\ndescription: >-\n  Auto-generates a structured postmortem from a completed campaign. Reads the\n  campaign file, telemetry logs, and feature ledger. Produces a documented\n  analysis of what broke, what the safety systems caught, and what patterns\n  emerged. Can also be invoked manually for any incident.\nuser-invocable: true\nauto-trigger: false\ntrigger_keywords:\n  - postmortem\n  - retro\n  - what broke\n  - what happened\n  - debrief\neffort: medium\n---\n\n# \u002Fpostmortem — Campaign Postmortem Generator\n\n## Orientation\n\n**Use when:** A campaign just completed and you want a structured analysis of what broke, what safety systems caught, and what patterns emerged. Also for ad-hoc incident analysis from recent git history.\n\n**Don't use when:** You want to preserve session context for the next conversation (use `\u002Fsession-handoff`), extract reusable patterns from findings into the knowledge base (use `\u002Flearn`), or score and improve quality iteratively (use `\u002Fimprove`).\n\n## When to Use\n\n- After any Archon campaign completes (Archon should suggest it)\n- After a difficult debugging session\n- When the user says \"what just happened\" or \"what broke\"\n- When \u002Fdo routes \"postmortem\", \"retro\", \"what broke\", \"what happened\"\n\n## Inputs\n\nOne of:\n1. A campaign file path (.planning\u002Fcampaigns\u002F*.md)\n2. A time range (\"last session\", \"today\", \"this week\")\n3. Nothing (reads the most recent completed campaign)\n\n## Protocol\n\n### Step 1: GATHER\n\nCollect data from all available sources:\n\n**From the campaign file (if it exists):**\n- Direction vs what was actually built (scope drift?)\n- Phase completion timeline (which phases needed rework?)\n- Decision log entries (what architectural choices were made?)\n- Review queue items (what needed human eyes?)\n- Circuit breaker activations (what hit the limit?)\n- Feature ledger (what shipped?)\n\n**From telemetry (.planning\u002Ftelemetry\u002F):**\n- hook-timing.jsonl: which hooks fired most, any patterns\n- hook-errors.log: what was blocked, what failed, what had parse errors\n- Circuit breaker trips\n- Quality gate violations\n\n**From git history:**\n- Commits during the campaign period\n- Files changed (which areas got the most churn?)\n- Any reverts (what was undone?)\n- Commit message patterns (fix: commits indicate bugs found)\n\n**From the session itself (if no campaign):**\n- Recent tool calls and their outcomes\n- Files edited and errors encountered\n\n### Step 2: ANALYZE\n\nIdentify patterns across the data:\n\n1. **What broke:** List every failure, error, or unexpected outcome.\n   For each: what happened, what caught it (hook\u002Fgate\u002Fhuman\u002Fnothing),\n   what it cost (time, rework, tokens).\n\n2. **What the safety systems caught:** Circuit breaker activations,\n   quality gate blocks, anti-pattern warnings, typecheck failures.\n   This is the \"invisible value\" section — problems prevented.\n\n3. **What drifted:** Compare the campaign direction to what was built.\n   Did scope expand? Did phases get skipped or reordered? Did the\n   architecture change mid-build?\n\n4. **What patterns emerged:** Recurring error types, files that kept\n   needing fixes, phases that took longest, common anti-patterns.\n\n### Step 3: PRODUCE\n\nWrite to `.planning\u002Fpostmortems\u002Fpostmortem-{slug}-{date}.md`:\n\n```markdown\n# Postmortem: {Campaign Name or Session Description}\n\n> Date: {ISO date}\n> Campaign: {path to campaign file, or \"ad-hoc session\"}\n> Duration: {time from first to last commit}\n> Outcome: {completed | partial | parked}\n\n## Summary\n{2-3 sentences: what was attempted, what happened, what the result was}\n\n## What Broke\n{Numbered list. For each:}\n### {N}. {Short description}\n- **What happened:** {the failure}\n- **Caught by:** {hook name \u002F quality gate \u002F human \u002F nothing}\n- **Cost:** {rework time, files affected, phases repeated}\n- **Fix:** {what resolved it}\n- **Infrastructure created:** {new hook rule, new anti-pattern, new end condition — or \"none needed\"}\n\n## What Safety Systems Caught\n{Things that WOULD have been problems without the hooks\u002Fgates}\n| System | What It Caught | Times | Impact Prevented |\n|--------|---------------|-------|-----------------|\n| {hook\u002Fgate name} | {description} | {count} | {what would have happened} |\n\n## Scope Analysis\n- **Planned:** {what the campaign direction said}\n- **Built:** {what the feature ledger shows}\n- **Drift:** {none | minor | significant — with specifics}\n\n## Patterns\n{Recurring themes worth watching:}\n- {pattern 1}\n- {pattern 2}\n\n## Recommendations\n{Concrete next actions:}\n1. {recommendation — e.g., \"Add anti-pattern rule for X\"}\n2. {recommendation — e.g., \"Phase Y needs tighter end conditions\"}\n\n## Numbers\n| Metric | Value |\n|--------|-------|\n| Phases planned | {N} |\n| Phases completed | {N} |\n| Commits | {N} |\n| Files changed | {N} |\n| Circuit breaker trips | {N} |\n| Quality gate blocks | {N} |\n| Anti-pattern warnings | {N} |\n| Rework cycles | {N} |\n```\n\n### Step 4: HANDOFF\n\nOutput the HANDOFF block from the Exit Protocol, then suggest: `Run \u002Flearn {campaign-slug} to extract patterns into the knowledge base.`\n\n## What \u002Fpostmortem Does NOT Do\n\n- Invent failures that didn't happen (real data only)\n- Blame the user or the model (document what happened, not whose fault)\n- Recommend changes to skill files (that's for the user to decide)\n- Run during a campaign (only after completion or on demand)\n\n## Quality Gates\n\n- Every \"What Broke\" entry has all 5 fields filled\n- Numbers section has real data (not estimates)\n- Recommendations are concrete actions (not \"be more careful\")\n- If no failures occurred, say so honestly (don't manufacture drama)\n\n## Fringe Cases\n\n**Campaign not found**: If the specified campaign file doesn't exist, check `.planning\u002Fcampaigns\u002F` for the most recently modified campaign. If no campaigns exist, run in ad-hoc mode using recent git history and session context.\n\n**No telemetry data**: Proceed without telemetry. Mark the \"What Safety Systems Caught\" table as \"No telemetry available\" and the Numbers section fields as \"N\u002FA\". Don't manufacture data.\n\n**Partial campaign** (parked or in-progress): Generate the postmortem with `Outcome: partial`. Document what was completed and what was parked. Include a \"Remaining Work\" section listing incomplete phases.\n\n**If .planning\u002Fpostmortems\u002F does not exist**: Create it before writing. If `.planning\u002F` itself doesn't exist, output the postmortem inline and note: \"Run \u002Fdo setup to initialize .planning\u002F for future storage.\"\n\n## Exit Protocol\n\n```\n---HANDOFF---\n- Postmortem: {name}\n- Document: .planning\u002Fpostmortems\u002Fpostmortem-{slug}-{date}.md\n- Failures documented: {count}\n- Safety catches: {count}\n- Recommendations: {count}\n- Reversibility: green — one file written to .planning\u002Fpostmortems\u002F; git rm to undo\n---\n```\n\nAfter displaying the HANDOFF block, suggest: `Run \u002Flearn {campaign-slug} to extract patterns into the knowledge base.`\n","# \u002Fpostmortem — Campaign Postmortem Generator\n\n## Orientation\n\n**Use when:** A campaign just completed and you want a structured analysis of what broke, what safety systems caught, and what patterns emerged. Also for ad-hoc incident analysis from recent git history.\n\n**Don't use when:** You want to preserve session context for the next conversation (use `\u002Fsession-handoff`), extract reusable patterns from findings into the knowledge base (use `\u002Flearn`), or score and improve quality iteratively (use `\u002Fimprove`).\n\n## When to Use\n\n- After any Archon campaign completes (Archon should suggest it)\n- After a difficult debugging session\n- When the user says \"what just happened\" or \"what broke\"\n- When \u002Fdo routes \"postmortem\", \"retro\", \"what broke\", \"what happened\"\n\n## Inputs\n\nOne of:\n1. A campaign file path (.planning\u002Fcampaigns\u002F*.md)\n2. A time range (\"last session\", \"today\", \"this week\")\n3. Nothing (reads the most recent completed campaign)\n\n## Protocol\n\n### Step 1: GATHER\n\nCollect data from all available sources:\n\n**From the campaign file (if it exists):**\n- Direction vs what was actually built (scope drift?)\n- Phase completion timeline (which phases needed rework?)\n- Decision log entries (what architectural choices were made?)\n- Review queue items (what needed human eyes?)\n- Circuit breaker activations (what hit the limit?)\n- Feature ledger (what shipped?)\n\n**From telemetry (.planning\u002Ftelemetry\u002F):**\n- hook-timing.jsonl: which hooks fired most, any patterns\n- hook-errors.log: what was blocked, what failed, what had parse errors\n- Circuit breaker trips\n- Quality gate violations\n\n**From git history:**\n- Commits during the campaign period\n- Files changed (which areas got the most churn?)\n- Any reverts (what was undone?)\n- Commit message patterns (fix: commits indicate bugs found)\n\n**From the session itself (if no campaign):**\n- Recent tool calls and their outcomes\n- Files edited and errors encountered\n\n### Step 2: ANALYZE\n\nIdentify patterns across the data:\n\n1. **What broke:** List every failure, error, or unexpected outcome.\n   For each: what happened, what caught it (hook\u002Fgate\u002Fhuman\u002Fnothing),\n   what it cost (time, rework, tokens).\n\n2. **What the safety systems caught:** Circuit breaker activations,\n   quality gate blocks, anti-pattern warnings, typecheck failures.\n   This is the \"invisible value\" section — problems prevented.\n\n3. **What drifted:** Compare the campaign direction to what was built.\n   Did scope expand? Did phases get skipped or reordered? Did the\n   architecture change mid-build?\n\n4. **What patterns emerged:** Recurring error types, files that kept\n   needing fixes, phases that took longest, common anti-patterns.\n\n### Step 3: PRODUCE\n\nWrite to `.planning\u002Fpostmortems\u002Fpostmortem-{slug}-{date}.md`:\n\n```markdown\n# Postmortem: {Campaign Name or Session Description}\n\n> Date: {ISO date}\n> Campaign: {path to campaign file, or \"ad-hoc session\"}\n> Duration: {time from first to last commit}\n> Outcome: {completed | partial | parked}\n\n## Summary\n{2-3 sentences: what was attempted, what happened, what the result was}\n\n## What Broke\n{Numbered list. For each:}\n### {N}. {Short description}\n- **What happened:** {the failure}\n- **Caught by:** {hook name \u002F quality gate \u002F human \u002F nothing}\n- **Cost:** {rework time, files affected, phases repeated}\n- **Fix:** {what resolved it}\n- **Infrastructure created:** {new hook rule, new anti-pattern, new end condition — or \"none needed\"}\n\n## What Safety Systems Caught\n{Things that WOULD have been problems without the hooks\u002Fgates}\n| System | What It Caught | Times | Impact Prevented |\n|--------|---------------|-------|-----------------|\n| {hook\u002Fgate name} | {description} | {count} | {what would have happened} |\n\n## Scope Analysis\n- **Planned:** {what the campaign direction said}\n- **Built:** {what the feature ledger shows}\n- **Drift:** {none | minor | significant — with specifics}\n\n## Patterns\n{Recurring themes worth watching:}\n- {pattern 1}\n- {pattern 2}\n\n## Recommendations\n{Concrete next actions:}\n1. {recommendation — e.g., \"Add anti-pattern rule for X\"}\n2. {recommendation — e.g., \"Phase Y needs tighter end conditions\"}\n\n## Numbers\n| Metric | Value |\n|--------|-------|\n| Phases planned | {N} |\n| Phases completed | {N} |\n| Commits | {N} |\n| Files changed | {N} |\n| Circuit breaker trips | {N} |\n| Quality gate blocks | {N} |\n| Anti-pattern warnings | {N} |\n| Rework cycles | {N} |\n```\n\n### Step 4: HANDOFF\n\nOutput the HANDOFF block from the Exit Protocol, then suggest: `Run \u002Flearn {campaign-slug} to extract patterns into the knowledge base.`\n\n## What \u002Fpostmortem Does NOT Do\n\n- Invent failures that didn't happen (real data only)\n- Blame the user or the model (document what happened, not whose fault)\n- Recommend changes to skill files (that's for the user to decide)\n- Run during a campaign (only after completion or on demand)\n\n## Quality Gates\n\n- Every \"What Broke\" entry has all 5 fields filled\n- Numbers section has real data (not estimates)\n- Recommendations are concrete actions (not \"be more careful\")\n- If no failures occurred, say so honestly (don't manufacture drama)\n\n## Fringe Cases\n\n**Campaign not found**: If the specified campaign file doesn't exist, check `.planning\u002Fcampaigns\u002F` for the most recently modified campaign. If no campaigns exist, run in ad-hoc mode using recent git history and session context.\n\n**No telemetry data**: Proceed without telemetry. Mark the \"What Safety Systems Caught\" table as \"No telemetry available\" and the Numbers section fields as \"N\u002FA\". Don't manufacture data.\n\n**Partial campaign** (parked or in-progress): Generate the postmortem with `Outcome: partial`. Document what was completed and what was parked. Include a \"Remaining Work\" section listing incomplete phases.\n\n**If .planning\u002Fpostmortems\u002F does not exist**: Create it before writing. If `.planning\u002F` itself doesn't exist, output the postmortem inline and note: \"Run \u002Fdo setup to initialize .planning\u002F for future storage.\"\n\n## Exit Protocol\n\n```\n---HANDOFF---\n- Postmortem: {name}\n- Document: .planning\u002Fpostmortems\u002Fpostmortem-{slug}-{date}.md\n- Failures documented: {count}\n- Safety catches: {count}\n- Recommendations: {count}\n- Reversibility: green — one file written to .planning\u002Fpostmortems\u002F; git rm to undo\n---\n```\n\nAfter displaying the HANDOFF block, suggest: `Run \u002Flearn {campaign-slug} to extract patterns into the knowledge base.`\n",{"name":5,"effort":24,"license":15,"description":7,"auto-trigger":20,"user-invocable":25,"trigger_keywords":26},"medium",true,[5,27,28,29,30],"retro","what broke","what happened","debrief","main","49119fa06efc769f502bede04ad99746ac20f021","skills\u002Fpostmortem",0,"https:\u002F\u002Fgithub.com\u002Fmayankjain1815-commits\u002FCITADEL","https:\u002F\u002Fgithub.com\u002Fmayankjain1815-commits","2nd-yr EEE 📍 Bangalore | Python, C, Java, C# | ML, NLP & Flask backends | Building AI tools that ship 🚀 | Open to hackathons & collabs","2026-11-14 14:46:28",{"source":8,"skillName":5,"commands":40,"prompt":50,"zipAvailable":25},[41,44,47],{"tool":42,"command":43},"npx","npx skills add mayankjain1815-commits\u002FCITADEL --skill postmortem",{"tool":45,"command":46},"bunx","bunx skills add mayankjain1815-commits\u002FCITADEL --skill postmortem",{"tool":48,"command":49},"pnpm","pnpm dlx skills add mayankjain1815-commits\u002FCITADEL --skill postmortem","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmayankjain1815-commits\u002FCITADEL\u002Fblob\u002Fmain\u002Fskills\u002Fpostmortem\u002FSKILL.md",[52,58],{"path":53,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":56,"sourceHtmlUrl":57},"__benchmarks__\u002Fno-campaign.md","REFERENCE","参考文档",783,"https:\u002F\u002Fgithub.com\u002Fmayankjain1815-commits\u002FCITADEL\u002Fblob\u002Fmain\u002Fskills\u002Fpostmortem\u002F__benchmarks__\u002Fno-campaign.md",{"path":59,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":60,"sourceHtmlUrl":61},"__benchmarks__\u002Fwith-completed.md",854,"https:\u002F\u002Fgithub.com\u002Fmayankjain1815-commits\u002FCITADEL\u002Fblob\u002Fmain\u002Fskills\u002Fpostmortem\u002F__benchmarks__\u002Fwith-completed.md",[63,70,77,84,91,98],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":19},"01M79XH1DBMXQEF9N0Q6NW7Q5P","workspace","Multi-repo campaign coordinator. Same lifecycle as fleet -- scope claims, discovery relay, wave-based execution -- but the unit of work is a repo, not a file. Coordinates campaigns across repositories with shared context.","https:\u002F\u002Fgithub.com\u002Fmayankjain1815-commits\u002FCITADEL\u002Fblob\u002Fmain\u002Fskills\u002Fworkspace\u002FSKILL.md",[],[],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"01M79XGWJJHSKNTH78TNVX09VK","wiki","Markdown-first knowledge base where the LLM acts as librarian. Ingests raw sources, compiles and interlinks topic files, self-maintains an index. No vector DB or embeddings required -- uses LLM-native navigation over structured markdown up to ~400K words.","https:\u002F\u002Fgithub.com\u002Fmayankjain1815-commits\u002FCITADEL\u002Fblob\u002Fmain\u002Fskills\u002Fwiki\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M79XGNW2YTFHVMEZGZDEDN43","watch","File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through \u002Fdo. Use for automatic reactions to file changes; do NOT use for one-off inspection or tasks needing human judgment per file.","https:\u002F\u002Fgithub.com\u002Fmayankjain1815-commits\u002FCITADEL\u002Fblob\u002Fmain\u002Fskills\u002Fwatch\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"01M79XGHZ0028HDW7SDT186D6Q","verify","Self-test the Citadel hook pipeline from within a live session. Exercises real tool calls (Write, Edit, Bash, Read) and checks that hooks fired, telemetry accumulated, and no errors occurred. Reports HOOK HEALTH: PASS or HOOK HEALTH: FAIL with a per-hook breakdown.","https:\u002F\u002Fgithub.com\u002Fmayankjain1815-commits\u002FCITADEL\u002Fblob\u002Fmain\u002Fskills\u002Fverify\u002FSKILL.md",[],[],{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":19},"01M79XGDKHMADJXC27T0FMQAN3","unharness","Remove Citadel from a project. Exports valuable state (campaigns, postmortems, research, backlog, discoveries) to docs\u002Fcitadel\u002F as human-readable markdown, then removes all harness files and hooks. The archive is detected by \u002Fdo setup on re-install and offered for restore.","https:\u002F\u002Fgithub.com\u002Fmayankjain1815-commits\u002FCITADEL\u002Fblob\u002Fmain\u002Fskills\u002Funharness\u002FSKILL.md",[],[],{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":104,"publishedAt":19},"01M79XG81A3RHP2TKKBT5WYEY2","triage","GitHub issue and PR investigator. Pulls open issues\u002FPRs, classifies them, searches the codebase for root cause or reviews contributed code, proposes fixes with file:line references, and optionally implements fixes. Use for investigating GitHub issues and reviewing PRs; do NOT use for general code review unrelated to GitHub issues.","https:\u002F\u002Fgithub.com\u002Fmayankjain1815-commits\u002FCITADEL\u002Fblob\u002Fmain\u002Fskills\u002Ftriage\u002FSKILL.md",[],[]]