audit
Audit an existing skill against best practices — checks structure, frontmatter, invocation control, description quality, and anti-patterns.
Skill by mistakeknot
Chalk Labs
Need help deploying audit?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/mistakeknot-audit
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: security
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/audit
What's inside
- Skill name
audit- Description
- Audit an existing skill against best practices — checks structure, frontmatter, invocation control, description quality, and anti-patterns. Use when verifying a skill before deployment.
- License
- MIT
- Instructions
- 61 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Skill Audit
Verify a skill follows best practices and the official specification.
## Instructions
Given a skill path (SKILL.md or skill directory), check each item below. Report findings as PASS/WARN/FAIL.
## Audit Checklist
### Structure
- [ ] Valid YAML frontmatter with `---` delimiters
- [ ] `name` field present (lowercase, hyphens, max 64 chars)
- [ ] `description` field present and specific (includes trigger keywords)
- [ ] SKILL.md under 500 lines
- [ ] References one level deep from SKILL.md (no nested chains)
- [ ] SKILL-compact.md exists if SKILL.md > 200 lines (run `gen-skill-compact.sh --check <dir>` to verify freshness)
### Invocation Control
- [ ] `disable-model-invocation: true` set if skill has side effects (deploy, commit, send)
- [ ] `user-invocable: false` set if skill is background knowledge only
- [ ] `allowed-tools` declared if specific tools needed
- [ ] `context: fork` used for isolation where appropriate
### Content Quality
- [ ] Uses standard markdown headings (NOT XML tags)
- [ ] Description includes both "what" and "when" triggers
- [ ] Examples are concrete, not abstract
- [ ] Has Quick Start or Instructions section
- [ ] No vague guidance ("use best judgment") — specific steps
### Anti-Patterns
- [ ] No XML tags in body
- [ ] No deep reference nesting
- [ ] No "punting" patterns (scripts handle errors, not "ask Claude to fix")
- [ ] No overly broad descriptions ("helps with things")
### Optional Intermesh Manifest
- [ ] If `intermesh.yaml` exists and `command -v intermesh >/dev/null 2>&1` succeeds, run `intermesh manifest validate <path>/intermesh.yaml`; report its diagnostics as normal audit findings.
- [ ] If Intermesh is unavailable, mark manifest validation `SKIP` rather than WARN/FAIL and continue the existing audit unchanged.
- [ ] The absence of `intermesh.yaml` is not an audit finding unless the user explicitly requires Intermesh routing metadata.
## Output Format
```
Skill Audit: {skill-name}
──────────────────────────────
Structure: {N}/6 pass
Invocation Control: {N}/4 pass
Content Quality: {N}/5 pass
Anti-Patterns: {N}/4 pass
──────────────────────────────
Overall: {PASS | WARN (N issues) | FAIL (N issues)}
Issues:
- [WARN] Description could be more specific
- [FAIL] Missing disable-model-invocation for deploy workflow
```From mistakeknot/interskill, MIT.
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jul 14, 2026 (3 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/mistakeknot/interskill
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from mistakeknot
- 0.537score
interstat-cost
mistakeknot
Show API-equivalent cost analysis with model-specific pricing, context-per-turn, and completed-task cost
SkillBFreshness: B★ 1Claude Code +9 - 0.476score
skill
mistakeknot
Expert guidance for creating Claude Code skills and slash commands — SKILL.md authoring, frontmatter, TDD pressure testing.
SkillCFreshness: CClaude Code +9 - 0.422score
interstat-analyze
mistakeknot
Parse conversation JSONL files and backfill token counts into SQLite
SkillDFreshness: D★ 1Claude Code +9 - 0.419score
interstat-report
mistakeknot
Show token efficiency analysis and decision gate verdict
SkillDFreshness: D★ 1Claude Code +9 - 0.414score
interstat-status
mistakeknot
Show collection progress and pending parse status
SkillDFreshness: D★ 1Claude Code +9 - 0.406score
quality
mistakeknot
Show code quality metrics for this session — syntax errors, auto-format runs.
SkillDFreshness: DClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get audit running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
audit skill. Agent Mart. https://agentmart.dev/skills/mistakeknot-audit (last updated 2026-10-24)