skill-link-check - Skill123

⚡

skill-link-check Checked

Audit project and global .agents/skills and .claude/skills layouts. Verify that .agents/skills co…

⚡ Productivity By yan-labs Version v1.0.0 Updated 2026-09-11

9.1Overall rating

Installation

🤖 Install via AI

Copy the prompt below and send it to your AI assistant (e.g. Claude Code) — it will follow the instructions and install automatically.

Install the "skill-link-check" skill by following the instructions at https://skill123.me/install/skill-link-check.

⌨️ Command line install

Run in your terminal — downloads and installs to ~/.claude/skills/.

curl -fsSL https://skill123.me/install/skill-link-check.sh | bash

📦 Download ZIP

Download the zip and extract it into your skills directory (e.g. ~/.claude/skills/), then restart your session.

⬇ Download v1.0.0 · 7 KB

About this skill

Overview

Audit project and global .agents/skills and .claude/skills layouts. Verify that .agents/skills contains the real source and .claude/skills mirrors it through a parent or per-skill symlink. Use whenever a skill or slash command is missing, not loading, duplicated, inconsistent, or described as "skill 没生效", "skill 不一致", "为什么 skill 没识别到", "检查 skill 链接", ghost skill, broken skill link, or missing skill. Also use when a skill exists in one directory but not the other.

Source

Repo: https://github.com/yan-labs/yan-skills
Path: skill-link-check

Score breakdown

Trigger

7.0

Clear What and bilingual trigger phrases for missing or inconsistent skills, but no When-Not and keyword breadth is inherently narrow.

Structure

8.7

Tight 99-line SKILL.md with one script and tests; check.py lives at skill root instead of scripts/.

Workflow

10.0

Excellent reviewer design: goal contract with gate and done-when, five-class issue taxonomy, no-auto-fix guard, JSON evidence mode, unittest self-check.

Content

10.0

Crisp imperative instructions with concrete runnable commands and precise exit-code semantics.

Engineering

9.0

Valid frontmatter, shebang and tests present; run snippet relies on resolving skill dir via $0 which agents must adapt.

Security

10.0

Strictly read-only script, no network, no secrets; suggested rm -rf fixes are quoted, flagged for review, and never executed.

Exemplary small reviewer skill: read-only symlink audit with clear issue taxonomy, honest exit-code contract, suggested-fix-only commands and unit tests; only blemishes are the script sitting at skill root and a description without exclusions.

Installation

About this skill

Overview

Source

Score breakdown

Related skills