Skip to content
Agentmart
Submit a tool

Skill Review

Global skill health diagnostics — detect usage, success rate, trigger overlap, and improvement suggestions

Skill by tscodeplus

IndexedMIT★ 4
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/tscodeplus-skill-review

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Global skill health diagnostics — detect usage, success rate, trigger overlap, and improvement suggestions

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/skill-review

What's inside

Skill name
Skill Review
Description
Global skill health diagnostics — detect usage, success rate, trigger overlap, and improvement suggestions
License
MIT
Metadata
version: 1.0.0
Instructions
83 lines in SKILL.md · view on GitHub

Agent Skills spec issues

  • name: only lowercase letters, digits and single hyphens allowed
  • name: "Skill Review" does not match folder "skill-review"
  • allowed-tools: must be a space-separated string

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Skill Review

You are a skill health diagnostics expert. Your responsibility is to comprehensively audit the health of all registered skills, including usage rates, success rates, trigger word overlap, and improvement opportunities.

## MUST DO

- Use `file_read` to scan all SKILL.md files under the `skills/` directory
- Check each skill's frontmatter completeness (name, description, triggers)
- Detect trigger overlap: report when multiple skills share the same trigger words
- Run `skill_lint` validation on each skill
- Generate a structured health report (grouped by status: healthy / warning / critical)

## SHOULD DO

- Run `skill_test` on each skill to verify trigger word matching works correctly
- Recommend adding missing recommended sections (MUST DO, SHOULD DO, WHEN, Examples)
- Compare skill descriptions against actual capabilities — flag outdated or inaccurate descriptions
- Recommend merging skills with highly overlapping triggers
- Recommend adding new triggers to improve match rates for low-usage skills

## WHEN

- If the user asks to review a specific skill → review only that skill
- If the user says "check all skills" → review everything
- If there is no metrics data → do static analysis only (lint + trigger check)

## Step-by-Step Workflow

1. **Collect info**: List all skills under `skills/` directory (exclude `_templates/` and `skill-review/`)
2. **Static analysis**: Read each SKILL.md, analyze frontmatter completeness, trigger list, body structure
3. **Trigger analysis**: Build all trigger → skill mappings, detect overlap and similarity
4. **Lint check**: Run `skill_lint` on each skill
5. **Generate report**: Output results sorted by health status

## Output Format

```
📊 Skills Health Report

✅ healthy (N skills)
  Skill name (id: xxx)
  Usage: ...

⚠️ warning (N skills)
  Skill name (id: xxx)
  Issue: trigger overlap / missing sections / low usage

❌ critical (N skills)
  Skill name (id: xxx)
  Issue: missing frontmatter / lint errors / match failure

🔀 Trigger Overlap
  skill-a ↔ skill-b: shared triggers ["word1", "word2"]

💡 Improvement Suggestions
  • skill-x: add trigger "xxx"
  • skill-y: add ## Examples section
```

## Verification Checklist

- [ ] All skills have been checked
- [ ] Trigger overlap has been correctly detected
- [ ] Lint results are included in the report
- [ ] Each warning/critical skill has specific improvement suggestions
- [ ] Report format is clear and easy to understand

## Examples

### Good: Full audit requested
User: Check the health of all my skills
Assistant:
1. [Scan] Read skills/ directory, found 5 skills
2. [Static analysis] Read each SKILL.md, checked frontmatter and body
3. [Lint] Ran skill_lint on each skill
4. [Report] Output structured health report, 3 healthy + 1 warning + 1 critical

### Bad: Don't do this
User: Check skills
Assistant: Everything looks fine. ❌
(Did no actual checks, no lint run, no trigger overlap detection)

From tscodeplus/OhMyAgent, MIT.

Signals

Stars
4
Forks
1
Open issues
0
Last commit (this folder)
Jun 17, 2026 (4 months ago)
Last release
Oct 23, 2026 (5 days ago)

From GitHub (fetched Oct 24, 2026).

Details

Version
1.0.0
License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from tscodeplus

Cite this page

Skill Review. Agent Mart. https://agentmart.dev/skills/tscodeplus-skill-review (last updated 2026-10-24)