Local Skill Directory & Usage Auditor
Audits local Claude Code and Codex skill directories to verify usage history, detect trigger failures, and resolve multi-layer runtime…
- Context cost
- 39.3k tokensestimated from the bundle, loaded when it triggers
- Bundle
- 20 of 21 fileshanded out here; the rest is at its source
- Licence
- not declarednone named by its author
- Last change
- —no release on file
- Servers it uses
- Noneruns standalone
What it does
承接明确的上游参考发现、技能市场搜索和候选内容比较；普通业务请求不自动搜索技能。检查本地技能目录和历史使用证据，确认 Claude/Codex 实际读取或调用过哪些技能，发现长期未见使用、疑似漏用、可能冗余、目录结构问题、重复或可合并技能、插件与本地技能重叠、名字不一致、链接失效、空技能或源码与运行时未同步。Use when 用户要监测本地技能触发情况、查哪些 skill 一直没触发或可能该触发却没触发、区分 Claude 真正的 Skill 调用与启动时候选加载、确认当前加载了哪些 skill、查同名冲突、判断技能是否该合并、判断应停用整个插件还是只停用其中的重复技能、检查目录名和 `name:` 是否一致、分清源码、lark 实体层、cc-switch 与 Claude/Codex 运行时、排查 `Skill 不存在于 SSOT` 或“已经改了为什么没生效”；prefer this over `agent-rules` when 目标是执行一次具体审计。
Installed, it changes the agent in these ways.
What this skill changes about the agent has not been set out here as a list. Its SKILL.md, shown below, says it in the author’s own words.
And these are the jobs people reach for it for.
The skill itself
A skill is instructions the model reads, so you can see what you are getting: below is the start of its SKILL.md. The front matter loads with every session, the body loads when the skill triggers, and the whole file comes with the install.
Nothing in a skill executes. The client loads the text and the model follows it, so a skill can be audited the way a runbook is — by reading it.
What it costs in context
Skills are not billed by the call. They are paid for in context: every token the instructions occupy is a token your code, your diff and your conversation cannot use. Here is what this one takes and when it takes it.
39.3k tokens, estimated from the bundle at four bytes to the token, held for the rest of the session once it triggers. Heavy. Teams tend to install this one per project rather than globally, and load it only when the job comes up.
A server charges by the month. A skill charges once per session, in context, and then keeps charging it for as long as the session lives.
Before and after
The same question, put to the same model twice: once as it comes, and once with these instructions loaded.
No worked example has been published for this skill yet.
The procedure it runs
The procedure has not been set out here step by step. It is in the body of its SKILL.md: the start of it is shown above, and the whole file comes with the install.
These steps are written for a model to follow, not executed by a runtime. It can still be told to skip one, and it will say so when it does.
Servers it uses
None. This skill calls no MCP servers at all.
Everything it needs is in the instructions, so it works in a project with nothing connected — the model reads the file and changes how it works with what it can already reach.
Its SKILL.md does not declare which tools it asks the agent for, so what it touches is whatever the instructions themselves ask for — read them before you install it.
This SKILL.md carries no allowed-tools line, so neither is declared. A skill grants no permissions of its own — it can only ask for tools your client already has.
What it will not do
Every skill is narrow, and the useful ones say where they stop. These are the jobs this one is the wrong tool for.
What this skill is not for has not been published here. Nothing is implied by that: it is a section the author has not filled in.
What is in the bundle
The download carries 20 of the 21 files in its source folder; the list here names 20 files, 491.4 kB on disk. Mostly text — the instructions the model reads — with 6 scripts in it that your client would run only if the instructions tell it to. The other one is not in the download — listed after these, with why.
- SKILL.md25.6 kB
- assets/skill-usage-dashboard.html26.3 kB
- evals/evals.json41.2 kB
- evals/integration-cases.md6.1 kB
- evals/trigger-evals.json3.7 kB
- references/finding-severity.md0.6 kB
- references/report-template.md1.6 kB
- references/skill-hygiene.md23.3 kB
- references/upstream-sources.md0.6 kB
- references/usage-audit.md9.2 kB
- references/weekly-review.md16.0 kB
- scripts/audit_skill_tree.py26.6 kB
- scripts/audit_skill_usage.py67.9 kB
- scripts/run_codex_skill_ecosystem_audit.py10.7 kB
- scripts/run_weekly_skill_review.py148.0 kB
- tests/test_audit_skill_usage.py30.1 kB
- tests/test_run_weekly_skill_review.py50.9 kB
- evals/fixtures/claude-session-sample.jsonl1.7 kB
- evals/fixtures/claude-telemetry-sample.jsonl0.3 kB
- evals/fixtures/codex-session-sample.jsonl1.0 kB
Not in the download
Not carried is a type a skill download does not hold. Marked read: its SKILL.md or scripts name the file, so without it the skill works only in part. Take it from its source.
- scripts/manage_market_skills.ps1read · not carried
A skill installs nothing and depends on nothing: it is a folder your client reads. This one carries 6 scripts beside the text, so the download is 20 files — not the whole of its source: 1 file is left out, and the skill reads it. It is listed under the files, with why.
Install
Installing copies the bundle into your project. Nothing runs at install time — the files sit on disk until the model reads them.
# Local Skill Directory & Usage Auditor · 39.3k tokens when loaded · macOS, Linux
mkdir -p .claude/skills && t=$(mktemp -d) &&
curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/local-skill-directory-usage-auditor/bundle.tar.gz &&
tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/local-skill-directory-usage-auditor" ] &&
{ [ ! -e .claude/skills/local-skill-directory-usage-auditor ] || { mv .claude/skills/local-skill-directory-usage-auditor "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } &&
mv "$t/local-skill-directory-usage-auditor" .claude/skills/ && echo "Installed .claude/skills/local-skill-directory-usage-auditor"npx mcprush@latest skill add sanantonio021/local-skill-directory-usage-auditorWindows PowerShell says 'running scripts is disabled on this system'? Run Set-ExecutionPolicy -Scope CurrentUser RemoteSigned once, or type npx.cmd instead of npx (codex.cmd, gemini.cmd, grok.cmd likewise). PowerShell 7 needs neither. Writes to .claude/skills/local-skill-directory-usage-auditor/ in the current project. For every project instead, run mkdir -p ~/.claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/local-skill-directory-usage-auditor/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/local-skill-directory-usage-auditor" ] && { [ ! -e ~/.claude/skills/local-skill-directory-usage-auditor ] || { mv ~/.claude/skills/local-skill-directory-usage-auditor "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/local-skill-directory-usage-auditor" ~/.claude/skills/ && echo "Installed ~/.claude/skills/local-skill-directory-usage-auditor" (macOS, Linux) — or add --global to the npx line. The curl line replaces .claude/skills/local-skill-directory-usage-auditor/ only after the download succeeds, so files left there by another skill of the same name, or by an older release, do not mix in. A copy already there is moved aside, not deleted, and the line prints where. It appears as skill-check in Gemini CLI, Codex, Copilot and Grok (its own name); Claude Code lists it by the folder name, local-skill-directory-usage-auditor. Not in this download: 1 file of its source, which its SKILL.md or scripts read (which one, and why). Take it from its source.
Which clients pick it up on their own
A skill is a folder of text. Most of these read a skills folder and pick it up without being told; the rest take the same folder another way — an upload in the app, a parameter on an API call — and then choose it by its description just the same.
Versions
Its author publishes no version number, so there is nothing here to pin to: what you install is the folder as it stands today. Instructions change more often than APIs do — a skill can be rewritten entirely without anything it depends on moving.
Nothing to pin to: this skill carries no version number of its own. What you install is what the folder holds on the day you install it.
Reviews
Nobody has reviewed this skill yet. The rating is the mean of the reviews written here, so there is none until somebody writes the first.
A review is tied to an account so it can be answered, edited and taken down by the person who wrote it.
Sign inAnybody with an account, one review each. It carries the version that was current when you wrote it, and the publisher may reply once.