agentleFS
hmj1026hmj1026/dhpk/skills/js-static-checks/SKILL.md

js-static-checks

Skill2 starsChanged 6 days agoMITView on GitHub

JavaScript/TypeScript static-check status, ESLint tier setup, legacy-global synchronization, and progressive checkJs rollout. Use for lint/typecheck configuration or rollout tasks and check, setup, rollout actions. Not for everyday JS business logic. Output: read-only status, scoped configuration, or leaf migration evidence.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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. Very specific:

    Use $js-static-checks <task>.

    line 12
  2. Very specific:

    Read-only status/check: read rollout's status contract and run this skill's scripts/status.js [--path <directory>] with Node from the …

    line 30
  3. Distinctive:

    Check/status and review requests are read-only.

    line 51

≈ “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

JS static checks

Use $js-static-checks <task>; optional check, setup, and rollout actions select the same task procedures. status remains an internal synonym for the read-only status contract.

Resolve scope and compatibility

Identify the consumer package/frontend directory and its package.json, lock/configuration evidence first. An intentional explicit target override wins; record it separately. For version-sensitive configuration, retain exact versus range precision for ESLint and TypeScript. Missing, broad incompatible, or conflicting evidence and unspecified monorepo scope require asking and waiting before versioned reference loads or dependent changes. Runtime Node/npm versions describe the environment. Migration requires an explicit destination; group multi-version results by target. A simple directive-count check needs a scan path, not a fabricated lint version.

Select the local procedure

  • Read-only status/check: read rollout's status contract and run this skill's scripts/status.js [--path <directory>] with Node from the consumer working directory. Omit --path to use CLAUDE_PLUGIN_OPTION_JS_CHECK_PATH, otherwise js/. Report deterministic JSON buckets and total=N strict=N nocheck=N unmarked=N. Scan immediate regular .js files only; nocheck takes precedence and comment mentions do not count. Missing/unreadable/symlink paths are UNAVAILABLE without counts. A completed UNAVAILABLE scan can exit0; its verdict is still not PASS.
  • ESLint tier/configuration or shaped globals (setup): read setup; use static checks and review patterns only as needed.
  • Per-leaf type-check adoption (rollout): read rollout; use setup detail only for tier/global changes.

The local references contain all required guidance. Hook/module integration is an optional consumer installation input, not a prerequisite or a resource recovery path. Preserve shared tools in the consumer; this skill does not install hooks. Missing bundled procedures/scripts are BLOCKED.

Authority and completion

Check/status and review requests are read-only. Setup/rollout implementation requests authorize the corresponding scoped configuration/leaf edits; a plan alone authorizes no writes. Keep vendor/minified files outside owned source work. Preserve explicit tier exemptions and the canonical AJAX facade. Update ESLint globals, ambient declarations, and shaped JSDoc typedefs together when a new shaped global is introduced. Classify typedef-widening fixes separately from permanent exclusions; retain one-leaf verification and the project-wide checkJs exit decision.

Report target scope/version, selected procedure, status/configuration or leaf classification, lint/type/behavior checks actually run, and residual exclusions. Tool absence is NOT_RUN/UNAVAILABLE; directive counts alone do not prove runtime correctness. Commit, push, and publication need separate authorization.

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.