agentleFS
Sign inStart free
loganware05loganware05/captains-compass-cursor/.cursor/skills/react-engineering/SKILL.md

react-engineering

Skill2 starsChanged 31 days agoMITView on GitHub

Implements React and TypeScript UI changes with accessible components, state, and client tests

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 7 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Prefer small, focused components with clear props.

    line 21
  2. Distinctive:

    Keep client state minimal.

    line 23
  3. Distinctive:

    Add or update unit/component tests for behavior changes.

    line 24
  4. Distinctive:

    Run the project's lint and unit test commands before handoff.

    line 26
  5. Distinctive:

    Do not introduce a new UI framework without plan approval.

    line 34
  6. Distinctive:

    Do not disable accessibility attributes to silence warnings.

    line 35
  7. Distinctive:

    Do not expand into backend/auth refactors unless the approved plan includes them.

    line 36

≈ “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

React Engineering

Use this Skill when

Working on React components, hooks, client routing, forms, browser behavior, responsive layout, or UI tests in a React/Vite/Next-style repository.

Inputs

  • Approved IMPLEMENTATION_PLAN.md
  • Existing component and styling conventions
  • Accessibility expectations from PROJECT_CONTEXT.md

Procedure

  1. Match existing project patterns (file layout, styling, state library).
  2. Prefer small, focused components with clear props.
  3. Label form controls; associate errors with fields (aria-invalid, aria-describedby).
  4. Keep client state minimal; avoid unrelated refactors.
  5. Add or update unit/component tests for behavior changes.
  6. For user-visible UI, capture screenshot evidence under .agent/evidence/.
  7. Run the project's lint and unit test commands before handoff.

Output

Changed React/TS files, tests, and evidence paths reported to the First Mate.

Prohibited actions

  • Do not introduce a new UI framework without plan approval.
  • Do not disable accessibility attributes to silence warnings.
  • Do not expand into backend/auth refactors unless the approved plan includes them.

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