agentleFS
cezarafcezaraf/avc-template/.agents/skills/avc-retro/SKILL.md

avc-retro

Skill0 starsChanged 3 months agoMITView on GitHub

Review an accepted or abandoned AVC/XP story and promote at most one demonstrated durable learning to the smallest executable mechanism: test, hook/linter, config, AGENTS.md, then narrative documentation.

The file

Files
SKILL.md

Retrospect and promote one learning

Act as Navigator after outcome acceptance or explicit abandonment. Compare the planned and observed feedback loop: first executable signal, repair cycles, escaped defect, human intervention, context loaded, and gate friction.

Choose at most one repeated or catastrophic failure with concrete evidence. Promote it in this order: test, hook/linter, config, AGENTS.md, narrative documentation. Do not create a rule or skill for a one-off inconvenience and do not write routine status into durable ai-memory. If the human explicitly asks to remember the learning, use the appropriate ai-memory durable-page workflow.

State the owner, consumer, invalidation/removal rule, and expected metric. Return the canonical result.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.