agentleFS
Sign inStart free
loganware05loganware05/captains-compass-cursor/.cursor/skills/experience-skill-training/SKILL.md

experience-skill-training

Skill2 starsChanged 32 days agoMITView on GitHub

Imports a product-repo Experience and drafts a Skill for control-repo testing

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    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. Very specific:

    If validation passes, open a Captain-approved PR to promote the draft into .cursor/skills/<slug>/ (use candidate-promotion guidance).

    line 42

≈ “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

Experience Skill Training

Use this Skill when

A production/product repository has an Experience sample the Captain wants Compass to learn from. By default Experiences stay in control-repo test fixtures; this Skill is the second instance that imports a product Experience into the control repo for draft Skill training and local validation.

Inputs

  • Path to Experience JSON (often from a product repo .agent/experience/)
  • Control repository root (this Compass repo)
  • Optional Skill slug

Procedure

  1. Confirm the Experience validates against experience.schema.json.

  2. Train a draft Skill in control-repo staging (not live Skills):

    ./scripts/train-skill-from-experience.sh \
  --experience /path/to/product/.agent/experience/<id>.json \
  --control-root /path/to/captains-compass-cursor \
  [--skill-slug my-new-skill]
  3. Review drafts under .agent/capabilities/candidates/skill-drafts/<slug>/.

  4. Run control-repo validation:

    ./scripts/doctor.sh
PYTHONPATH=. python3 -m unittest discover -s tests/orchestrator -p 'test_*.py' -q
  5. If validation passes, open a Captain-approved PR to promote the draft into .cursor/skills/<slug>/ (use candidate-promotion guidance). Stop for approval.

Output

Draft SKILL.md + capability.yaml + copied source Experience in staging.

Prohibited actions

  • Writing drafts directly into .cursor/skills/ without Captain approval
  • Skipping control-repo tests
  • Treating product Experiences as live Compass Skills automatically

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.

Check your setup, free