agentleFS
tanitaka-techtanitaka-tech/todome/.agents/skills/todome-type-lint-runner/SKILL.md

todome-type-lint-runner

Skill1 starsChanged 7 months agoMITView on GitHub

Run todome frontend typecheck and lint, then return only a compact structured summary. Use when the task is to confirm `cd client && npx tsc -b` and `cd client && npm run lint`, or when noisy TypeScript/ESLint output should be condensed into file-focused results.

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 6 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Run the frontend checks and compress the result so the main thread does not get flooded with raw logs.

    line 8
  2. Distinctive:

    Prefer running them in parallel when possible.

    line 15
  3. Distinctive:

    If both pass, reply with exactly:

    line 19
  4. Very specific:

    If either fails, group findings by file and summarize each item as L<line> <code>: <short message>.

    line 22
  5. Distinctive:

    Put the likely root cause first when one upstream type error is obviously creating many downstream errors.

    line 23
  6. Very specific:

    Do not paste full raw tsc or ESLint output.

    line 25
  7. Distinctive:

    Do not suggest fixes unless explicitly asked.

    line 26
  8. Distinctive:

    If sandbox or dependency issues block the commands, report that clearly instead of guessing.

    line 31

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Todome Type/Lint Runner

Run the frontend checks and compress the result so the main thread does not get flooded with raw logs.

Commands

  • cd client && npx tsc -b
  • cd client && npm run lint

Prefer running them in parallel when possible.

Output Rules

  • If both pass, reply with exactly:
    • ✅ tsc: clean
    • ✅ lint: clean
  • If either fails, group findings by file and summarize each item as L<line> <code>: <short message>.
  • Put the likely root cause first when one upstream type error is obviously creating many downstream errors.
  • Count warnings separately from errors. Detail errors first; warnings can stay summarized.
  • Do not paste full raw tsc or ESLint output.
  • Do not suggest fixes unless explicitly asked. This skill is for execution and summarization.

Notes

  • This skill is frontend-only. Server checks and unit tests belong elsewhere.
  • If sandbox or dependency issues block the commands, report that clearly instead of guessing.

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.