retrospective
Skill4 starsChanged 3 months agoMITView on GitHub
Produce a short 3-5 sentence post-mortem when an AI agent's output was wrong or based on faulty verification. Plain English, technical, no headers. Trigger phrases: "retro", "retrospective", "what went wrong", "post-mortem", "reflect on this error", "why did this fail", "the fix didn't work", "what should the agent have done", "analyze this failure".
- Reads credentials
69 other projects use a version of this.
Adopted by
Most recently taken up by
- Adelie-Squad/solosquadtheir own version, first seen Nov 8, 2026
- sbfnk/skillstheir own version, first seen Nov 8, 2026
- AndyB840506/skillstheir own version, first seen Nov 8, 2026
- paureis/pau-skillstheir own version, first seen Nov 8, 2026
- AsiaOstrich/EngramGraphtheir own version, first seen Nov 8, 2026
- simonasrazm/skillstheir own version, first seen Nov 8, 2026
Used with
Projects with it also use dev-story, team-level and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
lilangMaxSkilldev-story
Read a story file and implement it. Loads the full context (story, GDD requirement, ADR guidelines, control manifest), routes to the right programmer agent for the system and engine, implements the code and test, and confirms each acceptance criterion. The core implementation skill — run after /story-readiness, before /code-review and /story-done.
Also in 12 projects that use this
CoralGameSkillteam-level
Orchestrate level design team: level-designer + narrative-director + world-builder + art-director + systems-designer + qa-tester for complete area/level creation.
Also in 12 projects that use this
- CoralGameSkill
team-narrative
Orchestrate the narrative team: coordinates narrative-director, writer, world-builder, and level-designer to create cohesive story content, world lore, and narrative-driven level design.
Also in 12 projects that use this
- lilangMaxSkill
create-stories
Break a single epic into implementable story files. Reads the epic, its GDD, governing ADRs, and control manifest. Each story embeds its GDD requirement TR-ID, ADR guidance, acceptance criteria, story type, and test evidence path. Run after /create-epics for each epic.
Also in 11 projects that use this
- +7 more from lilangMax
- +1 more from CoralGame
Other versions69 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 69
- Donchitos/Claude-Code-Game-Studios★ 27ksame name
- alibaba/MNN★ 16ksame name
- glebis/claude-skills★ 410same name
- pixel-cellar/Claude-Code-Game-Studios★ 324same name
- blacklanternsecurity/red-run★ 296same name
- striderZA/OpenCodeGameStudios★ 118same name
- The01Geek/prflow★ 99same name
- PAIR-code/deliberate-lab★ 97same name
- AsiaOstrich/universal-dev-standards★ 84same name
- tranhieutt/software_development_department★ 71same name
59 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository38 other files it gives its agents.
- skills/take-ownership/AGENTS.mdAGENTS.md
- bitwarden-cliSkill
- blogpostSkill
- build-in-public-reelSkill
- chrome-devtools-remoteSkill
- chrome-useSkill
- claude-maxSkill
- claude-sessionsSkill
- dev-stackSkill
- dev-workflowSkill
- dev-workflow-supervisorSkill
- duckdns-domainSkill
- flutter-android-releaseSkill
- github-copilot-sessionsSkill
- git-worktreeSkill
- google-workspace-cliSkill
- hyperagent-eval-skillSkill
- macro-panelSkill
- mermaid2excalidrawSkill
- naste-slaste-styleSkill
- no-github-backlogSkill
- no-pr-backlogSkill
- opencode-apiSkill
- opencodeSkill
- overflowSkill
- prompt-hermes-aiSkill
- reportSkill
- secretsmctlSkill
- solo-founder-meta-agentSkill
- solo-founderSkill
- spaceship-dnsSkill
- take-ownership-meta-agentSkill
- take-ownershipSkill
- telegram-cliSkill
- vercel-lfsSkill
- write-agents-mdSkill
- write-skillSkill
- yc-pitch-deckSkill
The file
We split this skill into the rules it gives an agent
9 rules. 0 are common, 8 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 58 edited versions we read keep these.
8
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 13
Use "AI Agent" for all self-references.
- Distinctive: line 17
Write 3-5 sentences in plain English that explain what went wrong, why, and what the exact correct action would have been.
- Distinctive: line 24
Every sentence must be technical and specific: name files, commands, tools, line numbers.
- Distinctive: line 26
No qualitative language ("could have been better").
- Distinctive: line 27
Use "AI Agent" not "I" or "we".
- Distinctive: line 46
No headers. No bullet points.
- Very specific: line 64
Stop after appending to .retrospective.md.
- Distinctive: line 65
If evidence is insufficient for a specific claim, write "Insufficient evidence to name [X]" inline.
- Distinctive: line 76
Use today's date. Create the file if it does not exist.
“Common” is measured: kept by at least 6 in 10 of the 58 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
<role>
Failure analyst for AI agent work. Produce a precise, unsentimental post-mortem.
Use "AI Agent" for all self-references. No apologies, no fluff.
</role><goal>
Write 3-5 sentences in plain English that explain what went wrong, why,
and what the exact correct action would have been. Specific enough that
another agent reading it would not repeat the mistake.
</goal><constraints>
- 3-5 sentences total. No headers, no bullet lists, no sections.
- Every sentence must be technical and specific: name files, commands, tools, line numbers.
- Root cause: one word from the taxonomy (`wrong-validator`, `evidence-gap`, `assumption`, `missing-test`, `no-visual-check`, `head-drift`, `scope-violation`).
- No qualitative language ("could have been better"). Use concrete bars.
- Use "AI Agent" not "I" or "we".
</constraints><root_cause_taxonomy>
| Category | Definition |
evidence-gap | Claimed outcome without verifying it (exit code ≠ correctness) |
wrong-validator | Used wrong tool to verify (build for visual bug, compiler for behavior) |
assumption | Stated fact about code/state without reading or running it |
missing-test | Changed behavior without running or writing a covering test |
no-visual-check | Fixed UI/rendering bug without screenshot or DOM verification |
head-drift | Tested one commit, pushed a different one |
scope-violation | Changed more than requested or skipped a required step |
| </root_cause_taxonomy> |
<output_format> One prose block. 3-5 sentences. Pattern: [What AI Agent did wrong, specific.] [Root cause category in backticks, one-line why.] [What should have happened — exact command or verification step.] [Optional: correction rule as imperative.]
No headers. No bullet points. No sections. </output_format>
<examples>
<example>
Task: Fix provider dropdown clipping — bottom items not visible.AI Agent changed overflow-hidden to max-h-[280px] overflow-y-auto at line 1656 of SettingsPage.tsx, ran npm run build:extension:dev, and declared the bug fixed. wrong-validator — build success proves compilation, not rendering; the dropdown still clipped after merge. AI Agent should have run tests/extension.mock.test.js, taken a screenshot via CDP Page.captureScreenshot, and confirmed all 7 provider names visible before pushing. For any visual bug, screenshot evidence is required — build exit code is not.
</example>
<example>
Task: Confirm Stripe webhook wired for dev environment.AI Agent ran stripe webhook_endpoints list, saw the correct URL, and declared the webhook configured. wrong-validator — endpoint existence does not confirm event delivery; the endpoint was using the wrong API key mode. AI Agent should have run stripe trigger customer.subscription.updated --api-key "$STRIPE_SECRET_KEY" and checked kubectl logs -n vibe-dev deployment/stripe-service for a successful processing log line. For any integration config, trigger a real event and verify it lands in service logs.
</example>
</examples>
<stop_rules>
- Stop after appending to
.retrospective.md. Do not add headers, summaries, or lessons-learned sections. - If evidence is insufficient for a specific claim, write "Insufficient evidence to name [X]" inline. </stop_rules>
After producing the retrospective
Append one line to .retrospective.md in the project root:
YYYY-MM-DD: <3-5 sentence retrospective text on one line>Use today's date. Create the file if it does not exist. Never overwrite existing entries.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.