How do I install the Audit Skill skill?

Run npx skillmds@latest add richfrem/audit-skill 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 Audit Skill safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: executes scripts. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Audit Skill?

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 Audit Skill free to use?

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

Who published Audit Skill?

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

Audit Skill by richfrem — Agent Skill

Name: Audit Skill
Rating: 4.2 (5 reviews)
Author: richfrem

File contents

audit-skill: Skill Alignment & Evolution Auditor

Audits an individual skill against the 6 ecosystem evolution invariants and provides automated refactoring recommendations to achieve full compliance.

The 6 Alignment Invariants

Layer 1 Procedural Core: SKILL.md target $\le 100$ lines. Offload domain depth to references/ via Progressive Disclosure.
Boolean Evals Schema: evals/evals.json must be a root JSON list with should_trigger: true/false.
Hub-and-Spoke Script Isolation (ADR-002/003): All scripts reside in plugin root scripts/ and are symlinked into skills/<skill>/scripts/. Zero un-symlinked real files.
Frontmatter Standards: name matches directory slug exactly; description is third-person active verb and $\le 1024$ chars.
Contract & Fallback Links: Must provide acceptance-criteria.md and fallback-tree.md in references/.
Spoke Hygiene: Zero session logs, raw wiki traces, or .agent/ state in skill folders.

Quick Execution

Run the bundled alignment script directly against any skill directory:

# Audit a single skill
python3 plugins/agent-scaffolders/scripts/audit_skill.py plugins/<plugin>/skills/<skill-name>

# Auto-repair fixable schema deviations (e.g. migrate evals.json)
python3 plugins/agent-scaffolders/scripts/audit_skill.py plugins/<plugin>/skills/<skill-name> --fix

# JSON output for automated pipelines
python3 plugins/agent-scaffolders/scripts/audit_skill.py plugins/<plugin>/skills/<skill-name> --json

Alignment & Refactoring Procedure

Phase 1: Diagnostic Assessment

Run audit_skill.py <path>. Note all errors and warnings.
If SKILL.md exceeds 100 lines:
- Identify detailed background, multi-page tables, or complex workflows.
- Extract them into references/<topic>.md.
- Replace in SKILL.md with concise procedural steps and markdown links.

Phase 2: Hub-and-Spoke Remediation (ADR-002/003)

If real scripts are found inside skills/<skill>/scripts/:

Move the real script to plugins/<plugin>/scripts/<script-name>.py.
Register the symlink in symlinks.json.
Run python3 .agents/skills/symlink-manager/scripts/symlink_manager.py restore.
Run symlink_manager.py diagnose to confirm zero imposters.

Phase 3: Contract Verification

Ensure evals/evals.json has at least 3 positive and 3 negative test cases using should_trigger.
Ensure references/acceptance-criteria.md and references/fallback-tree.md are linked.
Re-run audit_skill.py to confirm 100% PASS.

---name: audit-skilldescription: Audits and aligns individual agent skills and sub-agents against ecosystem evolution standards, verifying line budgets, evals schemas, and hub-and-spoke isolation.---# audit-skill: Skill Alignment & Evolution AuditorAudits an individual skill against the 6 ecosystem evolution invariants and provides automated refactoring recommendations to achieve full compliance.---## The 6 Alignment Invariants1. **Layer 1 Procedural Core:** `SKILL.md` target $\le 100$ lines. Offload domain depth to `references/` via Progressive Disclosure.2. **Boolean Evals Schema:** `evals/evals.json` must be a root JSON list with `should_trigger: true/false`.3. **Hub-and-Spoke Script Isolation (ADR-002/003):** All scripts reside in plugin root `scripts/` and are symlinked into `skills/<skill>/scripts/`. Zero un-symlinked real files.4. **Frontmatter Standards:** `name` matches directory slug exactly; `description` is third-person active verb and $\le 1024$ chars.5. **Contract & Fallback Links:** Must provide `acceptance-criteria.md` and `fallback-tree.md` in `references/`.6. **Spoke Hygiene:** Zero session logs, raw wiki traces, or `.agent/` state in skill folders.---## Quick ExecutionRun the bundled alignment script directly against any skill directory:```bash# Audit a single skillpython3 plugins/agent-scaffolders/scripts/audit_skill.py plugins/<plugin>/skills/<skill-name># Auto-repair fixable schema deviations (e.g. migrate evals.json)python3 plugins/agent-scaffolders/scripts/audit_skill.py plugins/<plugin>/skills/<skill-name> --fix# JSON output for automated pipelinespython3 plugins/agent-scaffolders/scripts/audit_skill.py plugins/<plugin>/skills/<skill-name> --json```---## Alignment & Refactoring Procedure### Phase 1: Diagnostic Assessment1. Run `audit_skill.py <path>`. Note all errors and warnings.2. If `SKILL.md` exceeds 100 lines: - Identify detailed background, multi-page tables, or complex workflows. - Extract them into `references/<topic>.md`. - Replace in `SKILL.md` with concise procedural steps and markdown links.### Phase 2: Hub-and-Spoke Remediation (ADR-002/003)If real scripts are found inside `skills/<skill>/scripts/`:1. Move the real script to `plugins/<plugin>/scripts/<script-name>.py`.2. Register the symlink in `symlinks.json`.3. Run `python3 .agents/skills/symlink-manager/scripts/symlink_manager.py restore`.4. Run `symlink_manager.py diagnose` to confirm zero imposters.### Phase 3: Contract Verification1. Ensure `evals/evals.json` has at least 3 positive and 3 negative test cases using `should_trigger`.2. Ensure `references/acceptance-criteria.md` and `references/fallback-tree.md` are linked.3. Re-run `audit_skill.py` to confirm 100% PASS.

Frequently asked questions

Audit Skill