skill-usage-stats

84 / 100 · Low risk

Fine to try. Some of what it can do is expected: a coding skill usually runs build and test commands.

By majiayu000/spellbook (GitHub) · coding · 290 stars · scanned at commit 238e076

只读统计 Claude/Codex 的 Skill 使用证据并检查 agent 配置健康。仅用于明确的健康检查、配置诊断、使用排行或低使用候选请求；会识别 enabled 插件并单列批量审计读取。哪些 skill 坏了、互相抢触发、点名却没触发、占用列表预算，或要用历史请求检验改写后的描述，改用 skill-checkup。不要用于规范源、全局/项目/profile/冷存储、投影或退役治理，改用 skill-ecosystem-doctor。忽略引用日志和相邻任务。

Works with any agent that supports SKILL.md skills.

What this skill can do

Runs commands on your computer

This is disclosed by the author in the skill's SKILL.md or README. Expected for a coding skill.

Found in 8 places.

skills/skill-usage-stats/SKILL.md, line 39python3 scripts/agent_health.py --lang en
skills/skill-usage-stats/SKILL.md, line 117mv ~/.claude/local ~/.claude/local.quarantine-YYYYMMDD-HHMMSS
skills/skill-usage-stats/SKILL.md, line 138python3 scripts/skill_usage_report.py --lang en

Show 5 more

skills/skill-usage-stats/scripts/agent_health_claude.py, line 47result = subprocess.run(
skills/skill-usage-stats/scripts/agent_health_claude.py, line 59except (OSError, subprocess.SubprocessError) as exc:
skills/skill-usage-stats/scripts/agent_health_codex.py, line 40result = subprocess.run(
skills/skill-usage-stats/scripts/agent_health_codex.py, line 43except (OSError, subprocess.SubprocessError) as exc:
skills/skill-usage-stats/scripts/skill_usage_report.py, line 333proc = subprocess.run(cmd, capture_output=True, text=True, check=False)

Changes files outside its own folder

The author does not mention this.

Found in 2 places.

skills/skill-usage-stats/SKILL.md, line 117mv ~/.claude/local ~/.claude/local.quarantine-YYYYMMDD-HHMMSS
skills/skill-usage-stats/scripts/agent_health_claude.py, line 108"Evidence supports quarantining the legacy install: move `~/.claude/local` to "

Sends data to these websites: downloads.claude.ai

This is disclosed by the author in the skill's SKILL.md or README.

Found in 3 places.

skills/skill-usage-stats/scripts/agent_health.py, line 17import urllib.request
skills/skill-usage-stats/scripts/agent_health.py, line 162request = urllib.request.Request("https://downloads.claude.ai/claude-code-releases/latest")
skills/skill-usage-stats/scripts/agent_health.py, line 163with urllib.request.urlopen(request, timeout=10) as response:

Install

Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.

if [ -e ~/.agents/skills/'skill-usage-stats' ] || [ -L ~/.agents/skills/'skill-usage-stats' ]; then echo 'A skill folder named skill-usage-stats already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/majiayu000/spellbook' "$d" && git -C "$d" checkout --quiet '238e07625aeca5bcf0d6f7cb3e2d07f94c717194' -- 'skills/skill-usage-stats' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/skill-usage-stats' ~/.agents/skills/'skill-usage-stats' && rm -rf "$d"; fi

Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'skill-usage-stats' ~/.claude/skills/'skill-usage-stats' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.

Badge for your README

The badge for majiayu000/spellbook shows the score of its lowest-scoring skill.

SkillTrust badge for majiayu000/spellbook

[![SkillTrust](https://zalavijaysinh.github.io/skilltrust/badges/majiayu000/spellbook.svg)](https://zalavijaysinh.github.io/skilltrust/repos/majiayu000/spellbook/)

Score history

Date	Version	Score
2026-11-07	`238e076`	100