agentleFS
ManojDevHub1ManojDevHub1/visual-engineering-suite/skills/frontend-implementation/SKILL.md

frontend-implementation

Skill1 starsChanged 26 days agoMITView on GitHub

Inspect existing codebase conventions, framework, routing, and styling, and implement accessible, reusable UI components handling loading, empty, error, and success states without architectural rewrites.

3 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

7 rules. 0 are common, 4 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill when implementing UI components from visual reconstruction specs and design token maps, ensuring alignment with the host …

    line 9
  2. Distinctive:

    State Completeness: Follow the Component State Matrix to implement default, loading, empty, error, and hover/focus states.

    line 15
  3. Distinctive:

    Run the inspection script to identify active frameworks, TypeScript usage, and component paths:

    line 23
  4. Very specific:

    Use semantic HTML tags (<nav>, <header>, <main>, <article>, <button>).

    line 29
  5. Very specific:

    Focus Rings: Ensure interactive elements have visible high-contrast focus rings (focus-visible:ring-2).

    line 38
  6. Very specific:

    Run existing linter or build commands (npm run lint, npm run build, npm test).

    line 41
  7. Distinctive:

    Ensure no console syntax errors or hydration mismatches are introduced.

    line 42

“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “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

Frontend Implementation Skill

Use this skill when implementing UI components from visual reconstruction specs and design token maps, ensuring alignment with the host codebase architecture.

Core Responsibilities

  1. Codebase Discovery: Inspect target frameworks and styling setup using inspect-codebase.js.
  2. Semantic & Accessible Markup: Implement semantic HTML with proper ARIA attributes, keyboard focus states, and color contrast.
  3. State Completeness: Follow the Component State Matrix to implement default, loading, empty, error, and hover/focus states.
  4. Architectural Respect: Adhere to the Framework Adaptation Guide to preserve existing project patterns.

Step-by-Step Procedure

1. Audit Existing Codebase Conventions

Run the inspection script to identify active frameworks, TypeScript usage, and component paths:

node skills/frontend-implementation/scripts/inspect-codebase.js [path-to-workspace]

2. Implement Component Structure

  • Use semantic HTML tags (<nav>, <header>, <main>, <article>, <button>).
  • Apply design tokens or Tailwind utility classes extracted in design-system-extraction.
  • Support responsive viewport constraints (mobile-first layout).

3. Handle Lifecycle States

Implement each state defined in state-matrix-template.md:

  • Loading State: Provide skeleton placeholders or spinner indicators.
  • Empty State: Show friendly fallback text and clear call-to-action when data arrays are empty.
  • Error State: Render accessible error alert messages with retry actions.
  • Focus Rings: Ensure interactive elements have visible high-contrast focus rings (focus-visible:ring-2).

4. Verify Local Implementation

  • Run existing linter or build commands (npm run lint, npm run build, npm test).
  • Ensure no console syntax errors or hydration mismatches are introduced.
  • Hand off to browser-visual-qa for rendering verification.

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.