Skill guide

Inspect, find, and review your installed Agent Skills across Codex and Claude Code.

Install

npx -y skills add gtskevin/skill-guide

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Use when the user wants to discover, inspect, compare, diagnose, or choose installed Agent Skills across Codex, Claude Code, cc-switch, or plugin directories.

SKILL.md

2.0 KB, as published. Nobody here has run it

Skill Guide

Overview

Use the bundled zero-dependency CLI to scan local skill metadata and generate a browser-ready HTML dashboard. Treat health scores and recommendations as local review prompts, not usage metrics or deletion decisions.

Default: Dashboard

Run the default dashboard:

node <skill-dir>/skill-guide.js --open

Add --lang zh for a Chinese dashboard. Add --refresh to force re-scan. Add --all to see skills from all platforms. Add --platform claude or --platform codex to force a specific platform view.

Sub-commands

For other modes, use sub-commands: /skill-guide: review, /skill-guide: find, /skill-guide: doctor, /skill-guide: recommend, /skill-guide: share, /skill-guide: lint. Or run node <skill-dir>/skill-guide.js --overlap to find semantically overlapping skills.

Guardrails

The scanner reads local metadata; it does not measure actual usage frequency.
Same-category suggestions and directory mentions require human review before installing, editing, or deleting anything.
Never delete skills, install packages, or publish results based only on a generated score.
The CLI only prepares evidence and questions — semantic judgment comes from the agent. Always wait for agent assessment before acting on any finding.
Built-in dashboard labels support English and Chinese. For other languages, summarize the result in the user's language without rewriting generated HTML unless explicitly requested.
If the CLI is unavailable, report the missing file instead of silently replacing its behavior.
All modes default to the current platform (auto-detected from env vars or install path). Cross-agent duplicates are normal — each agent needs its own skill copies. Use --all to see the full inventory across all agents.