Using Agent Skills
addyosmani/agent-skills
Meta-skill for choosing which workflow skill fits the task at hand, plus always-on habits: surface assumptions, stop on confusion, push back, keep it simple and stay in scope.
Audits the instruction files (CLAUDE.md, .claude/rules, .claude/skills, tools/measuredax/CLAUDEWINDOWS.md) for accuracy and bloat against .claude/rules/instructions.md, and proposes a concrete edit…
Install Claude Md Audit
$ npx skills add antoinecellerier/speaker-tuning-to-easyeffects --skill claude-md-audit -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install antoinecellerier/speaker-tuning-to-easyeffects claude-md-audit --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/antoinecellerier/speaker-tuning-to-easyeffects.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/claude-md-audit .claude/skills/claude-md-audit && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "claude-md-audit" agent skill from https://github.com/antoinecellerier/speaker-tuning-to-easyeffects/tree/master/.claude/skills/claude-md-audit into .claude/skills/claude-md-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "claude-md-audit", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/antoinecellerier/speaker-tuning-to-easyeffects/tree/master/.claude/skills/claude-md-auditType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add antoinecellerier/speaker-tuning-to-easyeffects --skill claude-md-audit -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install antoinecellerier/speaker-tuning-to-easyeffects claude-md-audit --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/antoinecellerier/speaker-tuning-to-easyeffects.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/claude-md-audit .agents/skills/claude-md-audit && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "claude-md-audit" agent skill from https://github.com/antoinecellerier/speaker-tuning-to-easyeffects/tree/master/.claude/skills/claude-md-audit into .agents/skills/claude-md-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "claude-md-audit", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add antoinecellerier/speaker-tuning-to-easyeffects --skill claude-md-audit -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install antoinecellerier/speaker-tuning-to-easyeffects claude-md-audit --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/antoinecellerier/speaker-tuning-to-easyeffects.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/claude-md-audit .cursor/skills/claude-md-audit && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "claude-md-audit" agent skill from https://github.com/antoinecellerier/speaker-tuning-to-easyeffects/tree/master/.claude/skills/claude-md-audit into .cursor/skills/claude-md-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "claude-md-audit", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/antoinecellerier/speaker-tuning-to-easyeffects.git --path .claude/skills/claude-md-audit--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add antoinecellerier/speaker-tuning-to-easyeffects --skill claude-md-audit -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install antoinecellerier/speaker-tuning-to-easyeffects claude-md-audit --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/antoinecellerier/speaker-tuning-to-easyeffects.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/claude-md-audit .gemini/skills/claude-md-audit && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "claude-md-audit" agent skill from https://github.com/antoinecellerier/speaker-tuning-to-easyeffects/tree/master/.claude/skills/claude-md-audit into .gemini/skills/claude-md-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "claude-md-audit", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install antoinecellerier/speaker-tuning-to-easyeffects claude-md-auditInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add antoinecellerier/speaker-tuning-to-easyeffects --skill claude-md-audit -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/antoinecellerier/speaker-tuning-to-easyeffects.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/claude-md-audit .github/skills/claude-md-audit && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "claude-md-audit" agent skill from https://github.com/antoinecellerier/speaker-tuning-to-easyeffects/tree/master/.claude/skills/claude-md-audit into .github/skills/claude-md-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "claude-md-audit", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add antoinecellerier/speaker-tuning-to-easyeffects --skill claude-md-audit -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install antoinecellerier/speaker-tuning-to-easyeffects claude-md-audit --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/antoinecellerier/speaker-tuning-to-easyeffects.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/claude-md-audit .opencode/skills/claude-md-audit && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "claude-md-audit" agent skill from https://github.com/antoinecellerier/speaker-tuning-to-easyeffects/tree/master/.claude/skills/claude-md-audit into .opencode/skills/claude-md-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "claude-md-audit", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
claude-md-audit- GitHub stars
- 145
- Token cost
- ~1.2k tokens
- SKILL.md length
- 613 words
- Files
- 1
- Skills in repo
- 7
- Repo updated
- First seen
- Licence
- MIT
At a glance
Audits the instruction files (CLAUDE.md, .claude/rules, .claude/skills, tools/measuredax/CLAUDEWINDOWS.md) for accuracy and bloat against .claude/rules/instructions.md, and proposes a concrete edit…
- Works in 6 steps: Reference accuracy → No gitignored-path references → Bloat → …
- The user asks to audit / clean up / prune CLAUDE.md
- SKILL.md covers 1. Reference accuracy, 2. No gitignored-path references, 3. Bloat and 4. Duplication, plus 3 more sections
- Calls git
What it does
Claude Md Audit is an agent skill from antoinecellerier/speaker-tuning-to-easyeffects. Audits the instruction files (CLAUDE.md, .claude/rules, .claude/skills, tools/measuredax/CLAUDEWINDOWS.md) for accuracy and bloat against .claude/rules/instructions.md, and proposes a concrete edit list. Runs before committing a change to any of them, and periodically as a maintenance pass. It verifies every reference still resolves, flags references to gitignored file paths, checks line and description budgets, finds duplication across CLAUDE.md / rules / skills / docs / memory, and scans recent session…
Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Agent Workflows, covering Agent instruction files. The repository describes itself as: Convert OEM Dolby Atmos speaker tuning data to EasyEffects presets or PipeWire filter-chains for Linux. The licence is MIT.
When your agent uses it
- The user asks to audit / clean up / prune CLAUDE.md
- Before committing one
Example prompts
- “audit / clean up / prune CLAUDE.md”
- “Use the claude-md-audit skill to audit the instruction files (CLAUDE.md, .claude/rules, .claude/skills, tools/measuredax/CLAUDEWINDOWS.md) for…”
- “/claude-md-audit”
Workflow steps
6 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit e0aeb58. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
git
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Claude Md Audit loads about 1.2k tokens when it runs. Until then it costs about 179 tokens; SKILL.md has 613 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from antoinecellerier/speaker-tuning-to-easyeffects at commit e0aeb58, republished under its MIT licence (© antoinecellerier). 613 words, ~1,243 tokens.
Download SKILL.mdSave it as
.claude/skills/claude-md-audit/SKILL.md (or your agent's skills folder).- name
- claude-md-audit
- description
- Audits the instruction files (CLAUDE.md, .claude/rules, .claude/skills, tools/measure_dax/CLAUDE_WINDOWS.md) for accuracy and bloat against .claude/rules/instructions.md, and proposes a concrete edit list. Runs before committing a change to any of them, and periodically as a maintenance pass. It verifies every reference still resolves, flags references to gitignored file paths, checks line and description budgets, finds duplication across CLAUDE.md / rules / skills / docs / memory, and scans recent session transcripts and memory for durable rules worth promoting or rules now stale. Use when the user asks to "audit / clean up / prune CLAUDE.md" or the rules or skills, or before committing one.
- context
- fork
- agent
- general-purpose
- model
- opus
claude-md-audit
CLAUDE.md loads every session, so it bloats over time: each session adds a rule or a trap, and nothing removes one. Rules and skills drift the same way. This audit is the forcing function. It produces a punch list of concrete add, remove and relocate edits. Present them to the user; do not auto-apply.
The audit covers CLAUDE.md with its house-rules header comment, which states
the line budget, plus .claude/rules/*.md, .claude/skills/*/SKILL.md and
tools/measure_dax/CLAUDE_WINDOWS.md. With an argument naming files, audit only
those. Every line is judged against .claude/rules/instructions.md, so read it
first. Report findings grouped by check, each with the file, the specific
line(s) and a proposed fix.
1. Reference accuracy
Every file path, test name, script, docs/ link, commit hash, function name,
env var and CLI flag named in an audited file must still resolve. Run
tests/test_doc_refs.py, which checks doc links, anchors, r- tags,
cross-device § numbers and quoted headings, and fails any
Finding/entry/Follow-ups number cited outside design-notes "Legacy numbers", and
tests/test_layout.py, which checks tools/ paths. Verify the rest by hand:
- paths, files and dirs exist:
ls,test -e; - function and symbol names exist in the scripts or
lib/:rg; - commit hashes resolve:
git cat-file -t <hash>; - CLI flags appear in the argparse setup.
Flag each stale reference with what it should point to now.
2. No gitignored-path references
An audited file must not point at a specific file under a gitignored tree,
because such a path rots on clone. Check .gitignore, then grep the audited
files for paths under each ignored tree: localresearch/, driver-cache/,
*.xml, …
Of two cases, only the first is a violation:
- Violation: a path to a specific gitignored file, e.g.
localresearch/measure_ee/RESULTS.txt. Propose stating the lesson directly or relocating the content to a tracked doc. - Allowed: stating the convention itself, e.g. "Artifacts →
./localresearch/<area>/" or "Never referencelocalresearch/paths". That is the rule text, and it must stay.
3. Bloat
Report CLAUDE.md's loaded line count against the budget in the house-rules
header. Count only what enters context: exclude the leading block-level HTML
comment, <!-- … -->, which Claude Code strips before injection. If the count
is over, flag the longest prose passages and propose moving their rationale to
docs/ or a multi-step procedure to a skill, since CLAUDE.md holds the rule,
not the explanation. Check each skill against the size and description limits in
instructions.md, and apply its per-line test to every rule and skill line.
Show full SKILL.md (218 more words)Show less
4. Duplication
Find content repeated across CLAUDE.md, .claude/rules/, docs/, the
auto-memory files and .claude/skills/. Each fact has one home, as
instructions.md rule 5 assigns: the rule in CLAUDE.md or a path-scoped rule,
the rationale/evidence in docs/, the procedure in a skill. Recommend
collapsing duplicates to a pointer. A pointer between two rules whose paths:
always load together is itself redundant.
5. Friction scan — what to promote
Skim recent session transcripts under
~/.claude/projects/-home-antoine-stuff-atmos/ and the memory files in
…/memory/. Look for durable rules the user has stated more than once that
are not yet in CLAUDE.md or a rule: correction markers ("no", "don't",
"again", "I told you", "instead of") and repeated constraints. Propose
promotions, with the evidence. A rule belongs in CLAUDE.md only if it is a
durable project rule not derivable from the code, not session-specific
context.
6. Stale rules
Flag rules that no longer apply, and propose their removal: an investigation flag that was reverted, a feature or file that was removed, a trap that is now structurally impossible.
Output
A single punch list: for each finding, the line, the issue, and the exact proposed edit, as an add, remove or relocate. End with the projected new line count if all edits are applied. Hand the list to the user to approve before editing any audited file.
© antoinecellerier, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in .claude/skills/claude-md-audit of antoinecellerier/speaker-tuning-to-easyeffects.
Open the folder on GitHubat commit e0aeb58
Compare with similar skills
Claude Md Audit next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Claude Md Audit this skillantoinecellerier/speaker-tuning-to-easyeffects | 145 | — | ~1.2k | Automated safety check: Pass | MIT | |
| Using Agent Skillsaddyosmani/agent-skills | 105k | 4 repos | ~2.4k | Automated safety check: Pass | MIT | |
| Claude ReflectBayramAnnakov/claude-reflect | 1.8k | 2 repos | ~627 | Automated safety check: Pass | MIT | |
| Writing For Agentsbestofjs/bestofjs | 3.1k | 20 repos | ~2.7k | Automated safety check: Pass | MIT | |
| Neat-Freak Knowledge CloseoutKKKKhazix/khazix-skills | 21k | — | ~1.9k | Automated safety check: Pass | MIT | |
| Task Observerrebelytics/one-skill-to-rule-them-all | 3.2k | 1 repos | ~11k | Automated safety check: Pass | CC-BY-4.0 |
Similar skills
Claude Reflect
BayramAnnakov/claude-reflect
Self-learning system that captures corrections during sessions and reminds users to run /reflect to update CLAUDE.md.
Writing For Agents
bestofjs/bestofjs
Writing documents for agents. An agent skill from bestofjs/bestofjs.
Neat-Freak Knowledge Closeout
KKKKhazix/khazix-skills
Brings project docs, agent rule files, authorized memory and leftover workspace files back in line with what the code and runtime actually do at the end of a work session.
Task Observer
rebelytics/one-skill-to-rule-them-all
Monitors task execution for skill improvement opportunities.
- Official
SkillOpt Sleep Cycle
microsoft/SkillOpt
Runs an on-demand or nightly sleep cycle that reviews past Claude Code sessions and proposes validated updates to CLAUDE.md and skills.
More from antoinecellerier/speaker-tuning-to-easyeffects
Copy Audit
antoinecellerier/speaker-tuning-to-easyeffects
Audits the user-facing terminal copy changed over a git range for factual truth rather than readability, by fanning out reviewers partitioned by evidence source and triaging what survives.
Docs Review
antoinecellerier/speaker-tuning-to-easyeffects
Reviews the user-facing docs — README.md and the user guides under docs/README.md "Using it" — by running them past subagent reviewers role-playing fixed personas: a first-time visitor, a user…
Issue Replies
antoinecellerier/speaker-tuning-to-easyeffects
Guides triaging GitHub issues and drafting or posting replies in this repo.
Kernel Watch Triage
antoinecellerier/speaker-tuning-to-easyeffects
Guides triaging a kernel-sound-watch hit comment on the "Kernel sound-tree watch" issue (40) — the weekly workflow's per-tag report of .github/kernel-watchlist.txt grep hits against a new…
User Review
antoinecellerier/speaker-tuning-to-easyeffects
Reviews the scripts' user-facing terminal output by running it past subagent reviewers role-playing a first-time user, then reports severity-ranked findings.
Audio Validate
antoinecellerier/speaker-tuning-to-easyeffects
Validates a change to the audio output path against measured on-device ground truth.
Related
Categories
Questions about Claude Md Audit
What does Claude Md Audit do?
Audits the instruction files (CLAUDE.md, .claude/rules, .claude/skills, tools/measuredax/CLAUDEWINDOWS.md) for accuracy and bloat against .claude/rules/instructions.md, and proposes a concrete edit…. Claude Md Audit is an agent skill from antoinecellerier/speaker-tuning-to-easyeffects.md, and proposes a concrete edit list.
When should I use Claude Md Audit?
Claude Md Audit fits situations like: the user asks to audit / clean up / prune CLAUDE.md; before committing one.
How do I install Claude Md Audit in Claude Code?
Run `npx skills add antoinecellerier/speaker-tuning-to-easyeffects --skill claude-md-audit -a claude-code`. Or copy the skill folder (.claude/skills/claude-md-audit in antoinecellerier/speaker-tuning-to-easyeffects) into .claude/skills/claude-md-audit in your project. Claude Code loads it when a task matches its description.
How do I install Claude Md Audit in Codex?
Run `npx skills add antoinecellerier/speaker-tuning-to-easyeffects --skill claude-md-audit -a codex`. Or copy the skill folder (.claude/skills/claude-md-audit in antoinecellerier/speaker-tuning-to-easyeffects) into .agents/skills/claude-md-audit in your project. Codex loads it when a task matches its description.
Can I use Claude Md Audit in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add antoinecellerier/speaker-tuning-to-easyeffects --skill claude-md-audit -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/claude-md-audit, .gemini/skills/claude-md-audit, .github/skills/claude-md-audit and .opencode/skills/claude-md-audit in your project.
What does Claude Md Audit need to run?
Going by SKILL.md and its folder, Claude Md Audit needs the command-line tools its instructions call (git).
Does Claude Md Audit access the network?
SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Claude Md Audit safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Claude Md Audit use?
Claude Md Audit is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Claude Md Audit use?
About 1.2k tokens (SKILL.md is roughly 5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Claude Md Audit?
Skills that share tags, products or a category with Claude Md Audit: Using Agent Skills (addyosmani/agent-skills, 105k stars), Claude Reflect (BayramAnnakov/claude-reflect, 1.8k stars), Writing For Agents (bestofjs/bestofjs, 3.1k stars) and Neat-Freak Knowledge Closeout (KKKKhazix/khazix-skills, 21k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Claude Md Audit?
antoinecellerier (a GitHub user) maintains it in antoinecellerier/speaker-tuning-to-easyeffects, which has 145 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on October 10, 2026.
Source: antoinecellerier/speaker-tuning-to-easyeffects on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.