agentleFS
nassaj2011nassaj2011/claude-skills-for-chatgpt/skills/react-artifacts-builder/SKILL.md

react-artifacts-builder

Skill0 starsChanged 23 days agoMITView on GitHub

Build multi-component interactive web interfaces using a compatible React stack, routing, state and UI primitives where appropriate.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are 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.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Keep API contracts typed where feasible.

    line 13
  2. Distinctive:

    Run formatting, typecheck, tests and build where available.

    line 14
  3. Distinctive:

    Prefer working features to ornamental complexity.

    line 18

≈ “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

Multi-component web app builder

  1. Confirm requested deliverable: mockup, reusable component, interactive local demo, or production feature. Never imply a demo is a deployed system.
  2. Inspect package versions, React framework (Next.js/Vite/etc.), existing routes, UI components and build/test commands.
  3. Choose a minimal component hierarchy, state ownership, data loading and routing model. Use actual project libraries; do not assume Tailwind or shadcn is installed.
  4. Separate view state, server state and derived state; validate form inputs and handle loading, empty, error, retry and offline states.
  5. Include accessible semantics and keyboard/focus behavior for overlays, menus and forms.
  6. Keep API contracts typed where feasible; never embed tokens/secrets in client bundles.
  7. Run formatting, typecheck, tests and build where available; if unable to execute, identify that explicitly.
  8. For complex interaction, verify through playwright-webapp-testing and capture reproducible evidence.

Output: files changed, architecture sketch, interaction states, test commands/results and remaining caveats. Prefer working features to ornamental complexity.

State-machine reference

Use examples/frontend-rtl/ui.mjs to inspect loading/success/error/reset transitions and safe text rendering, with node --test examples/frontend-rtl/ui.test.mjs. This example deliberately uses framework-free JavaScript, not React, so it can inform React state management but does not validate hooks, hydration or Next.js routing. Write framework-specific tests in the target project.

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.