agentleFS
SaehwanParkSaehwanPark/agent-skills-archive/skills/lesson-documenter/SKILL.md

lesson-documenter

Skill1 starsChanged 5 months agoMITView on GitHub

Use when setup, implementation, testing, debugging, deployment, or tooling reveals a non-obvious recurring trap whose cause, verified resolution, and prevention should be preserved for future contributors.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 5 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    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
  1. Distinctive:

    Do not document routine mistakes, blame, speculation, or facts already obvious from code, tests, and standard tooling.

    line 9
  2. Very specific:

    Document a lesson when it is likely to recur and involves an unexpected prerequisite, version or environment mismatch, misleading failure, …

    line 14
  3. Distinctive:

    Check for an existing lesson and update it instead of duplicating it.

    line 26
  4. Distinctive:

    Add the smallest useful entry with context, symptom, cause, resolution, and prevention.

    line 27
  5. Distinctive:

    Verify the prevention step from a clean or representative state when practical.

    line 30
  6. Distinctive:

    Do not publish the lesson when the cause remains speculative, the content contains secrets or personal paths, the guidance is temporary …

    line 49

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

Lesson Documenter

Record durable, verified knowledge that would save future contributors meaningful time. Do not document routine mistakes, blame, speculation, or facts already obvious from code, tests, and standard tooling.

Selection criteria

Document a lesson when it is likely to recur and involves an unexpected prerequisite, version or environment mismatch, misleading failure, dead-end diagnosis, integration constraint, generated/cache/migration behavior, or newly discovered domain assumption.

First search existing contributor docs, LESSONS.md, docs/lessons.md, development guides, and nearby troubleshooting material. Update the established location. If none exists and the lesson justifies a new file, prefer root LESSONS.md for a small project or the existing docs hierarchy for a larger one.

Workflow

  1. Investigate until the cause and successful resolution are supported by evidence.
  2. Check for an existing lesson and update it instead of duplicating it.
  3. Add the smallest useful entry with context, symptom, cause, resolution, and prevention.
  4. Include exact commands, versions, paths, or links only when they materially reduce ambiguity and do not expose secrets or machine-specific data.
  5. Verify the prevention step from a clean or representative state when practical.
  6. Link to the durable source of truth rather than copying large instructions.

Suggested form:

## Short lesson title

- Context:
- Symptom:
- Cause:
- Resolution:
- Prevention:

Collapse small lessons into a paragraph when the fields would add noise.

Stop conditions

Do not publish the lesson when the cause remains speculative, the content contains secrets or personal paths, the guidance is temporary without a clear expiry/version, or an existing canonical document should be fixed instead.

Expected output

Report the lesson location, verified cause and prevention, evidence used, and any remaining uncertainty.

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.