agentleFS
rikeda71rikeda71/cxbridge/.claude/skills/validate-mappings/SKILL.md

validate-mappings

Skill1 starsChanged 6 months agoMITView on GitHub

Validates the invariants of the conversion table (id uniqueness, direction/loss value domains, degrade⇒lossy, no transform on dropped) when mappings/*.yaml has been edited or before committing. Always use this after modifying mappings. Use when asked to "check mappings", "validate mappings", or "validate mappings".

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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:

    Run the validation script.

    line 14
  2. Distinctive:

    If all results are OK, report completion.

    line 20
  3. Very specific:

    If any NG results appear, fix the errors according to the vocabulary definitions in mappings/SCHEMA.md.

    line 22
  4. Distinctive:

    After fixing, run the script again to confirm all results are OK.

    line 29

≈ “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

Steps

  1. Run the validation script.

    uv run "$CLAUDE_PROJECT_DIR/scripts/validate-mappings.py"
  2. If all results are OK, report completion.
  3. If any NG results appear, fix the errors according to the vocabulary definitions in mappings/SCHEMA.md.
    • id uniqueness violation → Find entries with duplicate ids and change one to a different id.
    • direction domain violation → Fix to one of both / claude_to_codex / codex_to_claude.
    • loss domain violation → Fix to one of lossless / lossy / dropped.
    • degrade⇒lossy violation → Entries with degrade set must have loss: lossy.
    • transform on dropped violation → Entries with loss: dropped must not have transform (set it back to null).
  4. After fixing, run the script again to confirm all results are OK.

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.