agentleFS
netanelavrnetanelavr/dotcursor/skills/kit-capture-lesson/SKILL.md

kit-capture-lesson

Skill6 starsChanged 27 days agoMITView on GitHub

Turn a correction into a short written rule so it does not repeat. Use after steering, a repeated bug class, or “remember this”.

The file

We split this skill into the rules it gives an agent

10 rules. About 0 are common, 4 are distinctive, and 6 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 6

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Write the smallest rule that would have blocked this mistake.

    line 9
  2. Very specific:

    Not domain terms or hard-to-reverse architecture (kit-challenge-design → CONTEXT / ADR)

    line 13
  3. Very specific:

    Not a feature decision log (kit-decisions)

    line 14
  4. Very specific:

    Not choosing a thinner implementation (kit-minimize)

    line 15
  5. Very specific:

    Not a kit catalog audit (kit-audit-skills)

    line 16
  6. Distinctive:

    Not a dump into CLAUDE.md / AGENTS.md / a new mega-skill

    line 17
  7. Distinctive:

    Prefer patching an existing skill or rule over adding a name.

    line 32
  8. Very specific:

    After yes: smallest edit. If you add or rename a skill/rule, update README.md catalogs and run kit-audit-skills.

    line 35
  9. Very specific:

    Do not duplicate kit-plan, kit-prove, kit-minimize, kit-strip-diff, or kit-delegate

    line 41
  10. Distinctive:

    Do not auto-apply. A proposed lesson that they reject is done.

    line 42

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Capture Lesson

Write the smallest rule that would have blocked this mistake. Apply only after explicit approval.

What this is NOT

  • Not domain terms or hard-to-reverse architecture (kit-challenge-design → CONTEXT / ADR)
  • Not a feature decision log (kit-decisions)
  • Not choosing a thinner implementation (kit-minimize)
  • Not a kit catalog audit (kit-audit-skills)
  • Not a dump into CLAUDE.md / AGENTS.md / a new mega-skill

Flow

  1. Failure - one sentence: what the agent did or missed.
  2. Rule - 1-5 lines that would have blocked it. Concrete trigger + action. No essays.
  3. Surface - pick one:
Put it hereWhen
Existing skillThe miss belongs to a paced workflow already in the catalog
Project rules/It must fire without a slash (style, git, safety, loop gates)
New skillRare: a full opt-in flow that is not an always-on habit
User-global memoryOnly if they ask for a personal habit across repos

Prefer patching an existing skill or rule over adding a name.

  1. Show the exact patch. Stop. Wait for yes.
  2. After yes: smallest edit. If you add or rename a skill/rule, update README.md catalogs and run kit-audit-skills.
  3. Approved or not: if .kit-evolve/lessons.md exists and this correction has no line yet, append one in its header's format.

Constraints

  • Generic: no employer names, private hosts, or work-only tools (AGENTS.md)
  • Do not duplicate kit-plan, kit-prove, kit-minimize, kit-strip-diff, or kit-delegate
  • Do not auto-apply. A proposed lesson that they reject is done.

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.