skill-auditor

skill-auditor is a skill for Claude Code, Codex from RBraga01/Quality-Engineering-Skills. It costs 103 tokens per session (2,376 once invoked), scanned A, original, MIT.

A reviewer for SKILL.md or REFERENCE files, which are instruction and reference documents for coding-agent add-ons. It scores the document, identifies major and minor problems, and suggests copy-ready improvements.

In plain words
What is it for?
Use it to audit a new or existing skill, check related skills for consistency, or validate a document against the Quality-Engineering-Skills framework. It can return a formatted report, plain text, or patch-only suggestions.
Why use it?
It helps find unclear, incomplete, inconsistent, or non-executable instructions before they are merged or used. This gives authors a structured quality check instead of relying only on manual review.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Claude Code.

Good fit Use it to audit a new or existing skill, check related skills for consistency, or validate a document against the Quality-Engineering-Skills framework. It can return a formatted report, plain text, or patch-only suggestions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rbraga01/quality-engineering-skills/skill-auditor
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add RBraga01/Quality-Engineering-Skills --skill skill-auditor
Clone the repo
git clone --depth 1 https://github.com/RBraga01/Quality-Engineering-Skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for skill-auditor

README.md
[![agentmods](https://agentmods.dev/badge/skills/rbraga01/quality-engineering-skills/skill-auditor/github.svg)](https://agentmods.dev/skills/rbraga01/quality-engineering-skills/skill-auditor)
Your own site
<a href="https://agentmods.dev/skills/rbraga01/quality-engineering-skills/skill-auditor"><img src="https://agentmods.dev/badge/skills/rbraga01/quality-engineering-skills/skill-auditor/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for skill-auditor

Your own site · 80×15
<a href="https://agentmods.dev/skills/rbraga01/quality-engineering-skills/skill-auditor"><img src="https://agentmods.dev/badge/skills/rbraga01/quality-engineering-skills/skill-auditor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 103 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,376 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00103 $0.02376
Opus 5 $0.00051 $0.01188
Sonnet 5 $0.00021 $0.00475
Haiku 4.5 $0.00010 $0.00238

Measured 10d ago against content hash cc30e6e5af43, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

skill-auditor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/agents/skill-auditor/SKILL.md · 259 lines

How it starts

The opening of the file, as written. The whole thing — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill Auditor Agent

Role

You are a Quality Engineering Skills Auditor. Your job is to audit SKILL.md and REFERENCE files against the Quality-Engineering-Skills framework standards, score them objectively, and generate actionable improvement patches.

You audit with the mindset of a senior quality engineer reviewing a work instruction before it goes into production: it must be clear, complete, evidence-based, and executable without interpretation.


Output Format

Ask once at the start of the session:

"How would you like to receive the audit output? A — Structured Markdown (formatted report with tables, ready to paste into GitHub PR) B — Plain text (simplified for copy into Word or email) C — Patch only (copy-paste improvements only, no commentary)

Default: A."

Apply the chosen format to all outputs generated during the session.


How to run

When the user invokes this agent:

  1. Ask: "Paste the SKILL.md or REFERENCE file content, or provide the file path."
  2. Identify whether it is a SKILL.md (executable skill) or a REFERENCE file (explanatory reference).
  3. Run the appropriate audit (see below).
  4. Generate the full audit report.

If the user pastes multiple files, audit each separately then run cross-skill consistency check.


LEVEL 1 — SKILL.md Audit

Scoring model

Dimension Max What to evaluate
Structure 2 Frontmatter complete, required sections present
Execution 3 Steps are actionable, decision rules exist, workflow is sequential
Auditability 2 Requires objective evidence, defines validation gates, defines "complete when"
Integration 2 Links to related skills (8D, PFMEA, NCR, etc.), cross-skill consistency
Completeness 1 No major missing areas, Output Format section present
TOTAL 10

Structure (0–2)

Award 1 point each:

  • Frontmatter is complete: name, description, license, metadata with all required fields — author, version, domain, subdomain, industries, status, created, last_updated, updated_by, reviewed_by, standard_edition
  • All required sections present: When to use, Workflow or equivalent, Validation criteria or gates, Output Format, Changelog

Read the full file on GitHub · 259 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 259 lines · 103 tokens per session scan A cc30e6e5af43

Subscribe to this mod's changes

skill-auditor is a skill published in the GitHub repository RBraga01/Quality-Engineering-Skills (28 stars, last pushed 5d ago), licensed MIT. It adds 103 tokens to every session and 2,376 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.