agentleFS
Sign inStart free
vibe-cokitvibe-cokit/claude-code/skills/vk-fix-ui/SKILL.md

vk-fix-ui

Skill1 starsChanged 4 months agoApache-2.0View on GitHub

⚡⚡ Analyze and fix UI issues

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 2 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use ui-ux-designer subagent to read and analyze ./docs/design-guidelines.md then fix the following issues: <issue>$ARGUMENTS</issue>

    line 9
  2. Very specific:

    Use chrome-devtools or playwright skill to take screenshots of the implemented fix (at the exact parent container, not the whole page), …

    line 31
  3. Distinctive:

    If the issues are not addressed, repeat the process until all issues are addressed.

    line 32
  4. Very specific:

    Use chrome-devtools skill to analyze the implemented fix and make sure it matches the design guideline.

    line 39
  5. Very specific:

    Use tester agent to test the fix and compile the code to make sure it works, then report back to main agent.

    line 40
  6. Distinctive:

    If there are issues or failed tests, ask main agent to fix all of them and repeat the process until all tests pass.

    line 41

≈ “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

Fix UI

Use ui-ux-designer subagent to read and analyze ./docs/design-guidelines.md then fix the following issues: <issue>$ARGUMENTS</issue>

Triage (before delegating)

Is <issue> a shared design-token/global-CSS problem (affects many components via one root cause) or N independent component-local problems? This is a Taste decision — decide per YAGNI/KISS, state the reasoning in the final report.

  • Shared/global → single ui-ux-designer instance fixes the shared file, serial (unchanged from today's workflow).
  • N independent components → fan out per component (see Workflow step 1 below).

Workflow

For video/screenshot input handling, see workflows/visual-input.md.

  1. Shared/global path: one ui-ux-designer instance implements the fix, serial. N-independent-components path: spawn one ui-ux-designer instance per component (≤3-4/wave per workflows/parallel-execution.md), each owning only its component's files (no shared token/CSS edits in this path — if a worker discovers the fix actually needs a shared change, STOP that instance and re-triage to the shared/global path). Print the Parallel Execution Matrix before spawning.
  2. Use chrome-devtools or playwright skill to take screenshots of the implemented fix (at the exact parent container, not the whole page), then use the Read tool and ui-ux-pro-max skill to analyze those outputs so the result matches the design guideline and addresses all issues.
    • If the issues are not addressed, repeat the process until all issues are addressed.
    • In the N-components path, parallelize only the fix edits (wave 0). Run this screenshot+verify step serially by default (one browser session at a time, wave 1, scoped per component so one component's retry loop doesn't block or re-run others') — browser-automation concurrency is untested. A project MAY opt into parallel screenshot capture only after confirming its browser tooling is stable under concurrent sessions.
  3. Use chrome-devtools skill to analyze the implemented fix and make sure it matches the design guideline.
  4. Use tester agent to test the fix and compile the code to make sure it works, then report back to main agent.
    • If there are issues or failed tests, ask main agent to fix all of them and repeat the process until all tests pass.
  5. Closing: follow workflows/fix-report-contract.md — post-approval project-manager + docs-manager parallel wave, rejection path, Final Report, asset rules. Do not restate it here.

IMPORTANT: Analyze the skills catalog and activate the skills that are needed for the task during the process.

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