agentleFS
RaditteAnggoroRaditteAnggoro/skill-for-lazy-developer/.agents/skills/ui-implementation/SKILL.md

ui-implementation

Skill1 starsChanged 7 days agoMITView on GitHub

Implement an agreed UI design in the project's existing stack, including responsive behavior, keyboard access, and empty/loading/error states. Use when the intended interface is already clear; do not invent a new design direction.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 6 are distinctive, and 0 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.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read the affected components, styles, data flow, tests, and build commands.

    line 15
  2. Distinctive:

    Use semantic HTML and native controls where possible.

    line 25
  3. Distinctive:

    Keep destructive or financial actions explicit, reversible where possible, and clear about the affected record.

    line 30
  4. Distinctive:

    Avoid layout shift, horizontal overflow, and color-only status signals.

    line 32
  5. Distinctive:

    Use the project's existing test setup.

    line 40
  6. Distinctive:

    no console errors or failed required requests.

    line 47

≈ “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

UI Implementation

Turn an agreed design into working interface code using the project's existing components, tokens, and conventions. If the design direction is unresolved, route to ui-design-intelligence; if the interface is visibly broken and the cause is unknown, route to browser-diagnostics.

Inspect the implementation context

Read the affected components, styles, data flow, tests, and build commands. Identify the design tokens and primitives already in use. Reuse them before adding a wrapper or dependency. Check the API states the UI must render: loading, empty, partial, error, success, disabled, and permission-limited.

Preserve explicit user and design decisions. Do not silently redesign spacing, copy, navigation, or interaction patterns while implementing a local change.

Build the interface

  • Use semantic HTML and native controls where possible.
  • Implement keyboard order, visible focus, labels, names, and error associations.
  • Make responsive behavior intentional: test narrow and wide viewports, not only the desktop screenshot.
  • Implement empty, loading, and error states as first-class states, not afterthoughts.
  • Keep destructive or financial actions explicit, reversible where possible, and clear about the affected record.
  • Avoid layout shift, horizontal overflow, and color-only status signals.

For enterprise tables, filters, approvals, long forms, reconciliation, and dense financial data, follow the selected profile in ui-design-intelligence/references/enterprise-data-ux.md.

Verify while building

Use the project's existing test setup. Add focused interaction tests for meaningful behavior, not snapshots of every static element. Check at minimum:

  • keyboard traversal and focus visibility;
  • narrow and wide viewport behavior;
  • empty, loading, and error states;
  • the primary success path;
  • no console errors or failed required requests.

Hand the result to ui-quality-verification when a visual/interaction audit is requested or when the change affects a critical enterprise workflow.

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.