agentleFS
Sign inStart free
8starlabs8starlabs/ui/skills/8sl-pattern-review/SKILL.md

8sl-pattern-review

Skill143 starsChanged 4 months agoMITView on GitHub

Use when reviewing, debugging, or cleaning up existing 8StarLabs UI usage. Focus on import correctness, component composition, docs drift, unnecessary rewrites, and mismatches between intended registry usage and actual implementation.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 5 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill when 8StarLabs UI is already present and the task is to review, debug, or tighten that usage.

    line 8
  2. Distinctive:

    Start by identifying bugs or risks with exact references when possible.

    line 25
  3. Distinctive:

    Read the current code and identify the actual user-visible or developer workflow problem.

    line 34
  4. Distinctive:

    Check imports and aliases first: wrong generated path, wrong alias assumptions, or missing supporting files often explain the bug faster …

    line 36
  5. Distinctive:

    If the user asked for a review only, do not jump straight to a rewrite unless the request includes that scope.

    line 45
  6. Very specific:

    Read references/review-checks.md for a compact anti-pattern checklist.

    line 78

≈ “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

8StarLabs Pattern Review

Use this skill when 8StarLabs UI is already present and the task is to review, debug, or tighten that usage. This is not the primary skill for fresh installs or for publishing new components to this repo.

Apply this skill when

  • the user says "review", "what's wrong", "debug", or "clean this up"
  • a component was installed but behaves incorrectly
  • code drifted away from documented examples
  • a custom rewrite may have replaced a better registry-based solution

Review priorities

  1. Correctness first. Broken imports, wrong props, invalid composition, or behavior regressions matter more than style cleanup.
  2. Findings before rewrite. Start by identifying bugs or risks with exact references when possible.
  3. Smallest fix wins. Recommend the minimal change that restores correct library usage.
  4. Stay library-aware. Judge the code against actual 8StarLabs and shadcn-style patterns, not abstract React preferences.

Workflow

  1. Read the current code and identify the actual user-visible or developer workflow problem.
  2. Check imports and aliases first: wrong generated path, wrong alias assumptions, or missing supporting files often explain the bug faster than deeper styling analysis.
  3. Compare usage against the intended installation/documentation pattern.
  4. Separate: correctness bugs, integration mistakes, and optional cleanup opportunities.
  5. Recommend the smallest fix that restores aligned usage.
  6. If the user asked for a review only, do not jump straight to a rewrite unless the request includes that scope.

Output format

For review requests, prefer:

  1. Findings
  2. Open questions or assumptions
  3. Optional cleanup suggestions

Each finding should answer:

  • what is wrong
  • why it is wrong
  • what specific change would fix it

Common focus areas

  • wrong import path or alias assumptions after registry install
  • component used without matching supporting structure from docs/examples
  • stale docs-derived usage after API drift
  • unnecessary local fork of a component that should stay close to registry form
  • app-side code blaming the library when the issue is integration shape

Avoid

  • generic React lint-style advice with no library context
  • leading with style opinions before user-facing bugs
  • telling consumers to edit this repo's internal registry authoring files
  • recommending a rewrite when a small import, prop, or composition fix is enough

References

  • Read references/review-checks.md for a compact anti-pattern checklist.

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