New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Skill Auditor

by hashgraph-online in hashgraph-online/awesome-codex-plugins

Audit a SKILL.md or REFERENCE file, score it 0–10, identify major and minor findings, and generate copy-paste improvements.

MITAuto-check passed

Install Skill Auditor

skills CLI
$ npx skills add hashgraph-online/awesome-codex-plugins --skill skill-auditor -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install hashgraph-online/awesome-codex-plugins skill-auditor --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/hashgraph-online/awesome-codex-plugins.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/RBraga01/Quality-Engineering-Skills/skills/agents/skill-auditor .claude/skills/skill-auditor && rm -rf skills-src

Use ~/.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/

Facts

Skill name
skill-auditor
GitHub stars
1.2k
Token cost
~2.4k tokens
SKILL.md length
1,047 words
Files
2 (incl. references)
Skills in repo
686
Repo updated
First seen
Licence
MIT

At a glance

Audit a SKILL.md or REFERENCE file, score it 0–10, identify major and minor findings, and generate copy-paste improvements.

  • Works in 4 steps: Ask: "Paste the SKILL.md or REFERENCE… → Identify whether it is a SKILL.md… → Run the appropriate audit (see below). → …
  • Reviewing a new skill before merging
  • SKILL.md covers Role, Output Format, How to run and LEVEL 1 — SKILL.md Audit, plus 6 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Skill Auditor is an agent skill from hashgraph-online/awesome-codex-plugins. Audit a SKILL.md or REFERENCE file, score it 0–10, identify major and minor findings, and generate copy-paste improvements. Use when reviewing a new skill before merging, auditing an existing skill for gaps, checking cross-skill consistency, or validating that a skill meets the Quality-Engineering-Skills framework standards. Triggers: audit this skill, score this SKILL.md, review reference file, check skill quality, find gaps in skill, validate skill before PR.

Its SKILL.md is about 2.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/cross-skill-rules.md`). Compatibility notes: Designed for Claude Code and similar interactive AI coding agents

The repository describes itself as: A curated list of awesome OpenAI Codex / ChatGPT plugins, skills, and resources. The 1 Codex Marketplace. See live plugins at: https://hol.org/plugins/best-codex-plugins. The licence is MIT.

When your agent uses it

  • Reviewing a new skill before merging
  • Auditing an existing skill for gaps
  • Checking cross-skill consistency
  • Validating that a skill meets the Quality-Engineering-Skills framework standards

Example prompts

  • “/skill-auditor”

Requirements

  • Compatibility (from SKILL.md): Designed for Claude Code and similar interactive AI coding agents

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  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.

What it can do on your machine

Read from SKILL.md and the folder at commit 78497e5. 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

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    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.

  • Compatibility

    Designed for Claude Code and similar interactive AI coding agents

    From compatibility in the SKILL.md frontmatter.

Context cost

Skill Auditor loads about 2.4k tokens when it runs, and up to ~4k if it reads all its reference files. Until then it costs about 120 tokens; SKILL.md has 1,047 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~120
When it runs · the whole SKILL.md, loaded when a task matches
~2.4k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~4k

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 hashgraph-online/awesome-codex-plugins at commit 78497e5, republished under its MIT licence (© hashgraph-online). 1,047 words, ~2,402 tokens.

Download SKILL.mdSave it as .claude/skills/skill-auditor/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
skill-auditor
description
Audit a SKILL.md or REFERENCE file, score it 0–10, identify major and minor findings, and generate copy-paste improvements. Use when reviewing a new skill before merging, auditing an existing skill for gaps, checking cross-skill consistency, or validating that a skill meets the Quality-Engineering-Skills framework standards. Triggers: audit this skill, score this SKILL.md, review reference file, check skill quality, find gaps in skill, validate skill before PR.
compatibility
Designed for Claude Code and similar interactive AI coding agents
license
MIT
metadata.author
RBraga01
metadata.version
1.1
metadata.domain
quality-engineering
metadata.subdomain
agents
metadata.industries
automotive,electronics,aerospace,medical,general
metadata.status
approved
metadata.created
2026-06-05
metadata.last_updated
2026-06-05
metadata.updated_by
RBraga01

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
DimensionMaxWhat to evaluate
Structure2Frontmatter complete, required sections present
Execution3Steps are actionable, decision rules exist, workflow is sequential
Auditability2Requires objective evidence, defines validation gates, defines "complete when"
Integration2Links to related skills (8D, PFMEA, NCR, etc.), cross-skill consistency
Completeness1No major missing areas, Output Format section present
TOTAL10
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

Deduct 0.5 for each:

  • description trigger phrases not in first 400 characters
  • description exceeds 1024 characters
  • name does not match directory name
  • Any document control field missing (status, reviewed_by, standard_edition, last_updated)
Execution (0–3)

Award 1 point each:

  • Steps are actionable: each step says what to DO, not just what to know
  • Decision rules exist: if/then logic, validation gates, rejection criteria
  • Workflow is sequential and complete: start → process → validated output

Deduct 0.5 for each:

  • Step is purely descriptive with no instruction
  • Vague language: "ensure", "consider", "try to" without specifics
  • Missing rejection criteria (what constitutes a fail at each step)
Auditability (0–2)

Award 1 point each:

  • Requires objective evidence at key steps (measurements, records, dates — not verbal confirmation)
  • Defines validation gates or "complete when" criteria

Deduct 0.5 for each:

  • Accepts opinion or verbal confirmation as sufficient
  • No way to verify output quality from the skill instructions alone
Integration (0–2)

Award 1 point each:

  • Links to at least one related skill or standard (e.g., "transfer to DFMEA Step 4", "see pfmea-process")
  • Cross-skill logic is consistent with the framework (see cross-skill rules in references/cross-skill-rules.md)

Deduct 0.5 for each:

  • Contradicts another skill in the framework
  • Missing link to an obviously related process (e.g., NCR skill with no link to 8D trigger)
Completeness (0–1)

Award 1 point if:

  • Output Format section is present with A/B/C mechanism (or session-level equivalent for agents)

Award 0 if:

  • Output Format section is missing

LEVEL 2 — REFERENCE File Audit

Reference files are explanatory, not executable. They support SKILL.md files with detailed methodology, tables, and examples.

Required frontmatter for REFERENCE/ASSET files: name, type, parent_skill, author, version, status, created, last_updated, updated_by, reviewed_by, license. Missing frontmatter is a Major Finding.

Scoring model
DimensionMaxWhat to evaluate
Coverage3Full methodology covered, no major gaps
Standard alignment2Aligns with cited standard (ISO / IATF / AIAG-VDA)
Usability2Examples (good vs bad), tables, failure mode patterns
Auditability2Audit questions, validation rules, common mistakes
Integration1Maps to related tools and processes
TOTAL10
Show full SKILL.md (419 more words)Show less
Coverage (0–3)
  • 3: Full methodology with no obvious gaps
  • 2: Most areas covered, 1–2 minor gaps
  • 1: Partial coverage, significant areas missing
  • 0: Skeleton or placeholder only
Standard alignment (0–2)
  • 2: Every claim traceable to the cited standard edition
  • 1: Mostly aligned, minor discrepancies or missing edition references
  • 0: No standard cited, or content contradicts the standard
Usability (0–2)
  • 1 point: Includes concrete examples (good vs bad, worked example, or table of patterns)
  • 1 point: Includes failure mode patterns or common mistakes
Auditability (0–2)
  • 1 point: Includes audit questions or validation rules
  • 1 point: Includes escalation or governance rules (not just theory)
Integration (0–1)
  • 1: Maps to at least one related process (e.g., "→ DFMEA Step 4", "→ 8D D7")
  • 0: No mapping to surrounding framework

LEVEL 3 — Cross-Skill Consistency Check

Run this when auditing multiple skills or reviewing a PR that touches more than one skill.

See full rules in references/cross-skill-rules.md.

Quick checks:

RuleCheck
NCR ↔ 8D D2NCR description standard matches 8D D2 problem description standard
5Why ↔ 8D D45Why output format is compatible with 8D D4 root cause requirement
PFMEA ↔ 8D D78D D7 explicitly requires PFMEA update; PFMEA skill references 8D as trigger
AP logicAP=H governance rule is identical across action-priority-ap, pfmea-process, and dfmea-design
OEM rulesOEM-specific requirements in oem-requirements.md are consistent with 8d-report-writing and oem-formats.md
ContainmentICA definition in 8D D3 is consistent with ncr-writing disposition logic

Quality Gates — Block conditions

A skill MUST be blocked (not merged) if any of the following are true:

  • Score < 8.0
  • Any of these findings:
    • No workflow section
    • No validation logic (pure description with no decision rules)
    • Accepts verbal confirmation or opinion as sufficient evidence
    • Contradicts another skill in the framework
    • Missing Output Format section
    • Missing Changelog section
    • Missing document control fields: status, reviewed_by, or standard_edition absent from frontmatter
    • Methodology is incorrect (contradicts cited standard)
    • name does not match directory name

Audit report format

Generate this report for every audit:

## Skill Audit Report — [skill-name]
**File type:** SKILL.md / REFERENCE
**Audited:** [date]

### Score
| Dimension | Score | Max |
|-----------|-------|-----|
| [dimension] | x | y |
| **TOTAL** | **x.x** | **10** |

### Verdict
[One line: PASS / PASS WITH NOTES / FAIL — reason]

### Major Findings (block merge if any)
1. [Finding — specific, with line reference if possible]

### Minor Findings (improve before next version)
1. [Finding]

### Copy-paste Improvements
[Exact markdown blocks ready to add to the file]

Maturity model

Use this to contextualise the score:

LevelScoreDescription
1 — Documentation0–4Basic content, not yet executable
2 — Structured4–6Has workflow, missing validation logic
3 — Validated6–7.5Workflow + validation gates, limited integration
4 — Integrated7.5–9Full workflow + integration with related skills
5 — Audit-ready9–10Automated + self-consistent + cross-skill verified

Target for all skills in this repo: Level 4 minimum, Level 5 at launch.

Changelog

VersionDateAuthorChange
1.02026-06-05@RBraga01Initial release - scoring model, quality gates, maturity model
1.12026-06-05@RBraga01Added document control field checks to Structure scoring, block conditions, and Level 2 reference audit

© hashgraph-online, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (references) in plugins/RBraga01/Quality-Engineering-Skills/skills/agents/skill-auditor of hashgraph-online/awesome-codex-plugins.

  • SKILL.md
  • references/cross-skill-rules.md

Open the folder on GitHubat commit 78497e5

Compare with similar skills

Skill Auditor 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 Auditor compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Skill Auditor this skillhashgraph-online/awesome-codex-plugins1.2k—~2.4kAutomated safety check: PassMIT
Claw Scoreopenclaw/openclaw392k—~2.5kAutomated safety check: PassMIT
Harness Scoreruvnet/ruflo74k—~605Automated safety check: NotesMIT
Score Evalsickn33/agentic-awesome-skills47k1 repos~304Automated safety check: PassMIT
UI Scoresickn33/agentic-awesome-skills47k1 repos~1.8kAutomated safety check: PassMIT
Indexing Issue Auditorsickn33/agentic-awesome-skills47k1 repos~1.5kAutomated safety check: PassMIT

Similar skills

  • Claw Score

    openclaw/openclaw

    Audit or refresh OpenClaw maturity scorecard docs from root taxonomy, maturity scores, and QA evidence artifacts without using maintainer discrawl data or committed inventory reports.

    392k GitHub stars~2.5k tokensUpdated today
    Auto-check passed

  • Harness Score

    ruvnet/ruflo

    5-dimension harness readiness scorecard from metaharness score <path.

    74k GitHub stars~605 tokensUpdated today
    DevelopmentAuto-check: notes

  • Score Eval

    sickn33/agentic-awesome-skills

    Imported skill score-eval from upstream source. An agent skill from sickn33/agentic-awesome-skills.

    47k GitHub starsUsed in 1 repo~304 tokens
    EducationAuto-check passed

  • UI Score

    sickn33/agentic-awesome-skills

    Score a UI file's design quality 0-100 against StyleSeed's design language — per-category breakdown, the worst offenders, and a prioritized fix list.

    47k GitHub starsUsed in 1 repo~1.8k tokens
    Testing & QAAuto-check passed

  • Indexing Issue Auditor

    sickn33/agentic-awesome-skills

    High-level technical SEO and site architecture auditor. An agent skill from sickn33/agentic-awesome-skills.

    47k GitHub starsUsed in 1 repo~1.5k tokens
    Marketing & SEOAuto-check passed

  • Fda Food Safety Auditor

    sickn33/agentic-awesome-skills

    Expert AI auditor for FDA Food Safety (FSMA), HACCP, and PCQI compliance.

    47k GitHub starsUsed in 2 repos~759 tokens
    Legal & ComplianceAuto-check passed

More from hashgraph-online/awesome-codex-plugins

All 686 skills in this repo

  • Anime Reaction Gif

    hashgraph-online/awesome-codex-plugins

    Create original anime-style reaction stickers as looping GIFs and MP4 previews, using generated character pose sheets and timed key poses.

    1.2k GitHub stars~922 tokensUpdated today
    Auto-check passed

  • Calibredb

    hashgraph-online/awesome-codex-plugins

    Manage and query Calibre libraries with the calibredb CLI (local paths or Calibre Content server URLs).

    1.2k GitHub stars~1k tokensUpdated today
    Auto-check passed

  • Rust API Test Harness

    hashgraph-online/awesome-codex-plugins

    A skill your agent uses when adding, changing, testing, or debugging Rust HTTP APIs and services, especially when Codex needs black-box integration tests, random-port app startup, real database test…

    1.2k GitHub stars~1.7k tokensUpdated today
    Auto-check passed

  • Art

    hashgraph-online/awesome-codex-plugins

    Make a studio's game look like something at build time — a cover from a real frame of the game (free), painted covers, backdrops, textures and character plates from image models through the…

    1.2k GitHub stars~2.4k tokensUpdated today
    Auto-check passed

  • Game Balance Economy

    hashgraph-online/awesome-codex-plugins

    Balance game difficulty, resources, rewards, probability, progression, economies, and dominant strategies.

    1.2k GitHub stars~618 tokensUpdated today
    Auto-check passed

  • Manuscript Engagement Analytics

    hashgraph-online/awesome-codex-plugins

    Analyze nonfiction manuscripts for reader engagement signals, including heading-level word counts, slow starts, long slogs, weak takeaway titles, value pacing, beta-reader comment dropoff, and…

    1.2k GitHub stars~875 tokensUpdated today
    Auto-check passed

Questions about Skill Auditor

What does Skill Auditor do?

Audit a SKILL.md or REFERENCE file, score it 0–10, identify major and minor findings, and generate copy-paste improvements. Skill Auditor is an agent skill from hashgraph-online/awesome-codex-plugins.md or REFERENCE file, score it 0–10, identify major and minor findings, and generate copy-paste improvements.

When should I use Skill Auditor?

Skill Auditor fits situations like: reviewing a new skill before merging; auditing an existing skill for gaps; checking cross-skill consistency; validating that a skill meets the Quality-Engineering-Skills framework standards.

How do I install Skill Auditor in Claude Code?

Run `npx skills add hashgraph-online/awesome-codex-plugins --skill skill-auditor -a claude-code`. Or copy the skill folder (plugins/RBraga01/Quality-Engineering-Skills/skills/agents/skill-auditor in hashgraph-online/awesome-codex-plugins) into .claude/skills/skill-auditor in your project. Claude Code loads it when a task matches its description.

How do I install Skill Auditor in Codex?

Run `npx skills add hashgraph-online/awesome-codex-plugins --skill skill-auditor -a codex`. Or copy the skill folder (plugins/RBraga01/Quality-Engineering-Skills/skills/agents/skill-auditor in hashgraph-online/awesome-codex-plugins) into .agents/skills/skill-auditor in your project. Codex loads it when a task matches its description.

Can I use Skill Auditor 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 hashgraph-online/awesome-codex-plugins --skill skill-auditor -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/skill-auditor, .gemini/skills/skill-auditor, .github/skills/skill-auditor and .opencode/skills/skill-auditor in your project.

What does Skill Auditor need to run?

SKILL.md names no scripts, command-line tools or credentials: Skill Auditor is instructions for the agent only. Compatibility (from SKILL.md): Designed for Claude Code and similar interactive AI coding agents.

Does Skill Auditor access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Skill Auditor 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 Skill Auditor use?

Skill Auditor is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Skill Auditor use?

About 2.4k tokens (SKILL.md is roughly 9.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.6k tokens, read only when the agent opens those files.

What are the alternatives to Skill Auditor?

Skills that share tags, products or a category with Skill Auditor: Claw Score (openclaw/openclaw, 392k stars), Harness Score (ruvnet/ruflo, 74k stars), Score Eval (sickn33/agentic-awesome-skills, 47k stars) and UI Score (sickn33/agentic-awesome-skills, 47k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Skill Auditor?

hashgraph-online (a GitHub organization) maintains it in hashgraph-online/awesome-codex-plugins, which has 1,242 GitHub stars. The repository holds 686 skills in this directory. The repository was last updated on October 8, 2026.

Source: hashgraph-online/awesome-codex-plugins on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.