How do I install the Do Skills Audit skill?

Run npx skillmds@latest add aibot88/do-skills-audit in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Do Skills Audit safe to use?

This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. Capability flags: makes network calls. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Do Skills Audit?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Do Skills Audit free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Do Skills Audit?

aibot88 (@aibot88) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Do Skills Audit by aibot88 — Agent Skill

Name: Do Skills Audit
Rating: 4.2 (5 reviews)
Author: aibot88

Do Skills Audit

Audit all Claude Code skills for compliance with canonical template standards. Use when checking skill quality, validating skill structure, linting SKILL.md files, verifying frontmatter, or scanning for skill issues. Runs deterministic validation rules and best practices sync against latest Anthropic docs by default.

aibot88 Updated Sep 9, 2026 3 repo stars

File contents

Skills Audit

Validates all .claude/skills/*/SKILL.md files against canonical template standards and Anthropic's latest published best practices.

What this skill does

Runs 12 deterministic validation rules (frontmatter, structure, classification, content)
Fetches latest Anthropic skill docs and compares against our standards (by default)
Produces a structured PASS/WARN/FAIL report per skill
Optionally auto-fixes trivial issues

Quick start

python .claude/skills/do-skills-audit/scripts/audit_skills.py $ARGUMENTS

If $ARGUMENTS was not substituted (the command shows a literal $ARGUMENTS): Look at the user's original message — they invoked this as /do-skills-audit <flags>. Extract whatever follows /do-skills-audit and pass it to the script. If no flags were provided, run the script with no arguments (default behavior).

Arguments

Flag	Description
`--fix`	Auto-fix trivial issues (missing name, trailing whitespace)
`--json`	Output JSON only
`--skill <name>`	Audit a single skill
`--no-sync`	Skip best practices sync (fast, offline)
`--apply`	Apply best practices updates to template/validator
`--update-skills`	Update existing skills to match new best practices
`--force-refresh`	Bypass doc cache and re-fetch

Validation Rules

Structural (FAIL): line count ≤500, frontmatter exists, name valid, broken sub-file links Quality (WARN): description trigger-oriented, description ≤1024 chars, known fields only, argument-hint presence Classification (WARN): infrastructure/background/fork skills have correct frontmatter flags Content (WARN): no duplicate descriptions across skills

After the Audit

With --fix: trivial issues (missing name field, trailing whitespace) are auto-corrected in place. Complex findings (classification mismatches, trigger phrasing, duplicate descriptions) are reported for human review. Without --fix: all findings are report-only.

---name: do-skills-auditdescription: Audit all Claude Code skills for compliance with canonical template standards. Use when checking skill quality, validating skill structure, linting SKILL.md files, verifying frontmatter, or scanning for skill issues. Runs deterministic validation rules and best practices sync against latest Anthropic docs by default.--- # Skills Audit Validates all `.claude/skills/*/SKILL.md` files against canonical template standards and Anthropic's latest published best practices. ## What this skill does 1. Runs 12 deterministic validation rules (frontmatter, structure, classification, content) 2. Fetches latest Anthropic skill docs and compares against our standards (by default) 3. Produces a structured PASS/WARN/FAIL report per skill 4. Optionally auto-fixes trivial issues ## Quick start ```bash python .claude/skills/do-skills-audit/scripts/audit_skills.py $ARGUMENTS ``` **If `$ARGUMENTS` was not substituted** (the command shows a literal `$ARGUMENTS`): Look at the user's original message — they invoked this as `/do-skills-audit <flags>`. Extract whatever follows `/do-skills-audit` and pass it to the script. If no flags were provided, run the script with no arguments (default behavior). ## Arguments | Flag | Description | |------|-------------| | `--fix` | Auto-fix trivial issues (missing name, trailing whitespace) | | `--json` | Output JSON only | | `--skill <name>` | Audit a single skill | | `--no-sync` | Skip best practices sync (fast, offline) | | `--apply` | Apply best practices updates to template/validator | | `--update-skills` | Update existing skills to match new best practices | | `--force-refresh` | Bypass doc cache and re-fetch | ## Validation Rules **Structural (FAIL):** line count ≤500, frontmatter exists, name valid, broken sub-file links **Quality (WARN):** description trigger-oriented, description ≤1024 chars, known fields only, argument-hint presence **Classification (WARN):** infrastructure/background/fork skills have correct frontmatter flags **Content (WARN):** no duplicate descriptions across skills ## After the Audit With `--fix`: trivial issues (missing name field, trailing whitespace) are auto-corrected in place. Complex findings (classification mismatches, trigger phrasing, duplicate descriptions) are reported for human review. Without `--fix`: all findings are report-only.

Frequently asked questions