Agent skill

Skill Auditor

by rshankras in rshankras/claude-code-apple-skills

Audits skills in this repo for consistency, API drift, and structural gaps.

MITAuto-check: notes

Install Skill Auditor

skills CLI
$ npx skills add rshankras/claude-code-apple-skills --skill skill-auditor -a claude-code

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

GitHub CLI
$ gh skill install rshankras/claude-code-apple-skills 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/rshankras/claude-code-apple-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/shared/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
785
Token cost
~4.2k tokens
SKILL.md length
1,797 words
Files
1
Skills in repo
41
Repo updated
First seen
Licence
MIT

At a glance

Audits skills in this repo for consistency, API drift, and structural gaps.

  • Works in 5 steps: Enumerate → Parse Frontmatter (Cached) → Run Checks → …
  • Asked to audit skills
  • SKILL.md covers When This Skill Activates, Scope, Process and Checks, plus 8 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Skill Auditor is an agent skill from rshankras/claude-code-apple-skills. Audits skills in this repo for consistency, API drift, and structural gaps. Produces a prioritized report grouped by severity (Critical/High/Medium/Low). Use when asked to "audit skills", "check the skill repo for drift", or when planning bulk skill cleanup. Read-only — does not apply fixes.

Its SKILL.md is about 4.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: Claude Code skills for Apple platform development (iOS, macOS, iPadOS) — product validation, code generation, App Store optimization, and more. The licence is MIT.

When your agent uses it

  • Asked to audit skills
  • Check the skill repo for drift
  • Planning bulk skill cleanup

Example prompts

  • “audit skills”
  • “check the skill repo for drift”
  • “Use the skill-auditor skill to audit skills in this repo for consistency, API drift, and structural gaps”
  • “/skill-auditor”

Requirements

  • Pre-approved tools (allowed-tools): Read, Glob, Grep, Bash

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Enumerate
  2. Parse Frontmatter (Cached)
  3. Run Checks
  4. Classify Aggregator vs Leaf
  5. Rank and Emit

What it can do on your machine

Read from SKILL.md and the folder at commit 9ffb831. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read
    • Glob
    • Grep
    • Bash

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

    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.

Context cost

Skill Auditor loads about 4.2k tokens when it runs. Until then it costs about 77 tokens; SKILL.md has 1,797 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~77
When it runs · the whole SKILL.md, loaded when a task matches
~4.2k

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: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Read, Glob, Grep, Bash

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 rshankras/claude-code-apple-skills at commit 9ffb831, republished under its MIT licence (© rshankras). 1,797 words, ~4,157 tokens.

Download SKILL.mdSave it as .claude/skills/skill-auditor/SKILL.md (or your agent's skills folder).
name
skill-auditor
description
Audits skills in this repo for consistency, API drift, and structural gaps. Produces a prioritized report grouped by severity (Critical/High/Medium/Low). Use when asked to "audit skills", "check the skill repo for drift", or when planning bulk skill cleanup. Read-only — does not apply fixes.
allowed-tools
Read, Glob, Grep, Bash
last_verified
2026-07-16
review_by
2027-06-22
os_version
iOS 27 / macOS 27

Skill Auditor

Audits every SKILL.md in skills/ for frontmatter correctness, structural completeness, API/version drift, and cross-file reference integrity. Produces a prioritized markdown report. Read-only — never applies fixes.

When This Skill Activates

Use this skill when the user:

  • Says "audit skills", "audit my skills", "run the skill auditor"
  • Asks to "check the skill repo for drift", "review skills for consistency"
  • Says "find broken skills", "validate skill frontmatter"
  • Is planning a bulk cleanup of the skill repo
  • References a specific category to audit (e.g., "audit the generators/ skills")

Does NOT activate for: creating new skills (use skill-creator), applying fixes (follow-up flow after this auditor reports), or auditing Swift code inside skills (use ios/coding-best-practices or macos/coding-best-practices).

Scope

Resolve the invocation argument in this order:

  1. No argument → audit all of skills/**/SKILL.md
  2. Category path (e.g., generators/, ios/) → audit skills/<arg>/**/SKILL.md
  3. Single file path (e.g., skills/liquid-glass/SKILL.md) → audit one file
  4. Fuzzy match → if arg doesn't resolve, try skills/<arg>/SKILL.md; fall back to asking the user

Process

1. Enumerate

Use Glob with pattern skills/**/SKILL.md from the repo root. Filter by scope if an argument was passed. Record the canonical file list — every subsequent step operates on this list.

2. Parse Frontmatter (Cached)

Read the first 20 lines of each SKILL.md. Parse:

  • Whether --- frontmatter block exists
  • name:, description:, allowed-tools: field values
  • Freshness keys: last_verified:, review_by: (dates, required — enforced by scripts/check-frontmatter.sh), optional os_version:. Overdue review_by dates are the stale-skills workflow's job, not a finding here.

Cache this result. Checks C-01, H-01, H-03, L-02 all read from this cache — do not re-read.

3. Run Checks

Execute bulk Grep passes in parallel (single tool-call batch) wherever possible. Per-file operations come after. The 11 checks are in the table below; the order is as-listed.

4. Classify Aggregator vs Leaf

For each file, mark it as aggregator or leaf using the rules in the "Aggregator Detection" section below. Some checks relax for aggregators.

5. Rank and Emit

Group findings by severity (🔴 → 🟢), sort within each group by file path, print the report inline using the template in "Output Format".

Checks

🔴 Critical

C-01 · Missing frontmatter. The file has no leading --- YAML block.

  • Detection: multiline Grep for \A---\n[\s\S]*?\n--- across all SKILL.md. Files with no match → C-01.
  • Fix: Add YAML frontmatter with name, description, allowed-tools.
🟠 High

H-01 · Missing allowed-tools field. Frontmatter exists but allowed-tools: key is absent.

  • Detection: from cached frontmatter parse.
  • Fix: Add allowed-tools: [Read, Glob, Grep] (adjust based on what the skill actually does).

H-02 · Broken supporting-file reference. The SKILL.md references a *.md file that does not exist on disk in the same directory.

  • Detection: Grep each SKILL.md for [a-z0-9][a-z0-9-]*\.md matches; resolve each relative to the SKILL.md's directory; ls to confirm. Missing files → H-02. Ignore matches inside fenced code blocks. Also resolve rules/swiftlint.yml references the same way (fragment fixtures themselves are CI's job — scripts/check-lint-fragments.sh).
  • Fix: Create the file or remove the reference.

H-03 · H1 title does not match name:. The first # heading after the frontmatter, slugified (lowercase, spaces → -), differs from the name: field.

  • Detection: from cached frontmatter parse + per-file line-after-frontmatter.
  • Fix: Rename the H1 or the name: to match.
🟡 Medium

M-01 · Missing "When This Skill Activates" section. No ## When This Skill Activates heading anywhere in the file.

  • Detection: Grep -L for ^## When This Skill Activates across all SKILL.md.
  • Fix: Add section with 3–5 user trigger phrases. See shared/skill-creator/SKILL.md for the canonical format.

M-02 · Outdated version reference (drift). Mentions iOS 17–25, macOS 13–25, or Swift 5.x with drift context (treated as current/latest/target).

  • Detection (two-stage):
    1. Stage 1 — Grep for \biOS (1[7-9]|2[0-5])\b|\bSwift 5\.\d+\b|\bmacOS (1[3-9]|2[0-5])\b, capturing line numbers.
    2. Stage 2 — for each hit, examine ±2 surrounding lines. Classify:
      • Flag M-02 if surrounding lines contain: latest, newest, current, target, deployment target, requires, minimum, as of, new in, now supports, today
      • Suppress if surrounding lines contain: legacy, pre-, prior to, before, deprecated, old, migrate from, backport, fallback, if available, #available, or the version mention has a trailing + (e.g., iOS 17+)
      • Neither → L-03 (ambiguous)
  • Known-current constants (dated 2026-07-11, update per WWDC): iOS 27, macOS 27 (announced WWDC26; iOS 26 / macOS 26 are within the one-generation grace), Swift 6.x. Normative source: scripts/versions.env. Mentions of these with drift context are always clean.
  • Fix: Update the reference to the current generation (see scripts/versions.env), or annotate as legacy context with one of the suppression keywords.

M-03 · Pre-@Observable pattern without deprecation callout. Uses @StateObject or ObservableObject without acknowledging that @Observable is the current pattern.

  • Detection: Grep for @StateObject|ObservableObject with line numbers; for each hit, secondary Grep of the same file for @Observable|deprecated|legacy|pre-@Observable|migration|old pattern within ±10 lines. No secondary match → M-03.
  • Fix: Either replace with @Observable + @State, or add a migration note explaining why the older pattern is shown.

M-04 · Oversized single-file skill. SKILL.md exceeds 400 lines and its directory contains no sibling .md files.

  • Detection: wc -l via Bash on each SKILL.md; if >400, check sibling file list via ls for any other .md. None → M-04.
  • Fix: Modularize — extract sections into patterns.md, templates.md, checklist.md, or examples.md per skill-creator conventions.
🟢 Low

L-01 · No ✅/❌ examples in prose. The file has no ✅ or ❌ markers anywhere.

  • Detection: Grep -L for ✅|❌.
  • Fix: Add at least one good/bad example pair.

L-02 · Description length out of range. description: is <20 or >300 characters.

  • Detection: from cached frontmatter parse.
  • Fix: Expand or shorten the description. Include a "use when…" clause to anchor activation.

L-03 · Ambiguous version mention. A version keyword matched stage 1 of the drift check but surrounding lines contained neither drift nor legacy context. User reviews manually.

  • Detection: fallthrough from M-02 stage-2 classification.
  • Fix: Add a drift or legacy keyword to disambiguate, or leave as-is if the context is clearly a one-off mention.

Aggregator vs Leaf Detection

A SKILL.md is an aggregator if any of the following hold:

  • It sits at depth 2 under the repo root — i.e., skills/<category>/SKILL.md
  • It contains the heading ## Available Modules or ## Available Skills
  • It links to ./<subdir>/SKILL.md or contains two or more references of the form skills/<category>/<subskill>/

Otherwise it is a leaf.

Relaxations for aggregators
CheckBehaviour
M-01 (activation section)Still enforced — aggregators must describe activation
M-03 (pre-@Observable)Suppressed — aggregators are prose, not code
M-04 (>400 lines)Suppressed — aggregators are allowed to be long when enumerating modules
L-01 (no ✅/❌ examples)Suppressed — aggregators don't carry patterns

Tag every finding in the report with (aggregator) or (leaf) so severity can be read at a glance.

Output Format

Print the report inline to the conversation using this template. Use exact headings — downstream tooling may grep them.

markdown
# Skill Audit Report — <YYYY-MM-DD> — <N> files scanned

## Summary
- 🔴 Critical: <count>
- 🟠 High: <count>
- 🟡 Medium: <count>
- 🟢 Low: <count>
- ✅ Files clean: <clean-count> / <N>

Scope: <all | category | single file>

## 🔴 Critical Findings
### C-01 · Missing frontmatter
- `skills/<path>/SKILL.md` (leaf) — **Fix:** Add YAML frontmatter with `name`, `description`, `allowed-tools`.

## 🟠 High Findings
### H-01 · Missing `allowed-tools` field
- `skills/liquid-glass/SKILL.md:1-4` (leaf) — **Fix:** Add `allowed-tools: [Read, Glob, Grep]`.
- `skills/macos/macos-tahoe-apis/SKILL.md:1-4` (leaf) — **Fix:** Same.

### H-02 · Broken supporting-file reference
- `skills/<path>/SKILL.md:<line>` — references `patterns.md`, not found. **Fix:** Create the file or remove the reference.

### H-03 · H1 title does not match `name:`
- `skills/<path>/SKILL.md` — `name: foo-bar`, H1 is `# Foo Bars`. **Fix:** Rename one to match.

## 🟡 Medium Findings
### M-01 · Missing "When This Skill Activates" section (<count>)
- `skills/design/liquid-glass/SKILL.md` (leaf)
- `skills/macos/coding-best-practices/SKILL.md` (leaf)
- [collapsed list of remaining offenders]
- **Fix:** Add section with 3–5 user trigger phrases.

### M-02 · Outdated version reference (<count>)
- `skills/<path>/SKILL.md:87` (leaf) — "latest iOS 17" in drift context. **Fix:** Update to iOS 26.

### M-03 · Pre-`@Observable` pattern without callout (<count>)
- `skills/<path>/SKILL.md:142` (leaf) — `@StateObject` without migration note. **Fix:** Replace with `@Observable` or add callout.

### M-04 · Oversized single-file skill (<count>)
- `skills/<path>/SKILL.md` — <NNN> lines, no sibling .md files. **Fix:** Modularize into `patterns.md` / `templates.md`.

## 🟢 Low Findings
### L-01 · No ✅/❌ examples
- `skills/<path>/SKILL.md` (leaf) — **Fix:** Add at least one good/bad example pair.

### L-02 · Description length out of range
- `skills/<path>/SKILL.md` — description is <N> chars. **Fix:** Expand/shorten to 20–300 chars.

### L-03 · Ambiguous version mention
- `skills/<path>/SKILL.md:<line>` — "iOS 18" with no drift/legacy context. **Fix:** Review manually.

## ✅ Clean Files
<collapsed list of files that passed all checks>

## Next Steps
- Review 🔴/🟠 findings first — they block skills from working as intended.
- Batch-fix 🟡 M-01 and M-02 mechanically — suggested find/replace scripts shown per-file.
- 🟢 findings are polish; address opportunistically.
Show full SKILL.md (739 more words)Show less

Implementation Notes

  • Parallelize bulk Greps in a single tool-call batch where possible. Activation, frontmatter, @StateObject, and drift-stage-1 can all run at once.
  • Cache the frontmatter parse. Four checks read it; only parse once.
  • Resolve *.md references inside fenced code blocks carefully — they're examples, not references. Strip fenced blocks before running H-02's regex.
  • Progress pings — for full-repo scans (148 files), emit a short "scanning <N>/<total>…" before each phase so the user sees liveness.
  • Idempotence — the report body (everything below the ## Summary) should be deterministic for a given repo state. Only the date in the H1 varies across runs.
  • Never write files. This skill's allowed-tools lists Bash, but only for read-only ops (wc, ls). If you find yourself needing to write, stop and ask the user to invoke a fix flow separately.

Non-Goals

  • No auto-fix. The report includes one-line fix suggestions per finding; applying them is a separate user-initiated task.
  • No network calls. This auditor does not verify URL liveness or check Apple doc availability.
  • No Swift compilation. Code-block validity is beyond scope; patterns are matched textually.
  • No WWDC session cross-referencing. A future wwdc-to-skill-workflow skill owns that.

Relationship to CI

CI (scripts/check-freshness.sh) owns the deterministic subset of M-02: a recency keyword AND a stale version (major ≤ current−2) on the same line is a blocking build failure. This auditor's M-02 remains the broader net — ±2-line context, current/target/requires keywords, human-reviewed. Findings unique to M-02 are review candidates, not CI failures; anything CI already blocks will never appear here because it can't merge. C-01 is likewise fully delegated: scripts/check-frontmatter.sh blocks missing frontmatter at PR time.

Maintenance

The drift heuristic hardcodes "known-current" version constants:

  • iOS 27, macOS 27, Swift 6.x (dated 2026-07-11; announced WWDC26)

Update these constants when Apple ships a new major platform version (usually post-WWDC each June), together with scripts/versions.env — CI's check-freshness.sh cross-checks that this file mentions the manifest's current iOS generation and fails if they drift apart. The stage-1 regex ranges (iOS 1[7-9]|2[0-5], macOS 1[3-9]|2[0-5]) must also be widened each cycle so their upper bound stays at CURRENT−2 (the previous generation sits inside a one-generation grace and is not stale; the ranges are unchanged for the iOS 27 cycle since 17–25 already ends at 27−2).

Verification

After running the auditor on the full repo, counts should fall within this tolerance band (baseline re-taken 2026-07-16 after the blind-test audit deletions, 178 total SKILL.md files scanned — 155 leaf skills + 23 category indexes; the README's "159 skills" counts leaf dirs plus the 4 single-skill categories):

FindingExpected
C-01 missing frontmatter0 — the 2026-04 legacy batch was fixed, and scripts/check-frontmatter.sh now blocks regressions in CI
H-01 missing allowed-tools0
H-02 broken supporting refs0
H-03 H1 mismatchflag outliers manually
M-01 missing activation section6 — ui-prototyping, iap-finalizer, originality-check, store-signals, flow-walkthrough, privacy-publish
M-02 version driftstage-1 Grep returns ~369 raw hit lines across ~147 files (2026-07-11); the stage-2 narrowed band must be re-derived on the next full run — the pre-hardening band (~50±10) was measured against ~228 raw hits, and CI's check-freshness.sh has since removed the same-line recency subset
M-03 pre-@Observable no callout~29 (±5) — re-verify on the next full run
M-04 oversized single-fileTBD — flag outliers
Known legacy pattern: ## When to Use (resolved)

The 2026-04 batch of files using ## When to Use as their activation heading has been fully normalized — as of 2026-07-11 no SKILL.md uses it in place of the canonical heading. The rule stands for future contributions: do not widen the M-01 regex to accept ## When to Use — the whole point is to normalize onto the canonical heading. (A ## When to Use … heading deeper in a file as content — e.g. swift/memory's "When to Use / When NOT to Use" section about the technique itself — is fine and not an M-01 signal.)

Smoke tests
  1. Full-repo run — invoke with no arg. Counts must fall within tolerance above.
  2. Scoped run — invoke with generators/. Only skills/generators/** paths appear.
  3. Single-file run — invoke with skills/liquid-glass/SKILL.md. Report has exactly one H-01 finding.
  4. Idempotence — re-run immediately. Report body is byte-identical; only the date in the H1 may differ.
  5. Drift heuristic sanity — spot-check 5 M-02 hits and 5 suppressed legacy mentions. If any legacy mention is mis-flagged, extend the suppression keyword list and re-run.

References

  • ../../../CLAUDE.md (repo root, resolved relative to this SKILL.md — not the project cwd) — normative source for frontmatter schema, naming, emoji convention. If absent (skills-only copies), use https://github.com/rshankras/claude-code-apple-skills/blob/main/CLAUDE.md
  • skills/shared/skill-creator/SKILL.md — companion meta-skill for creating new skills (this auditor only audits; it does not create)
  • skills/ios/SKILL.md — canonical aggregator example

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

Files

Just SKILL.md in skills/shared/skill-auditor of rshankras/claude-code-apple-skills.

Open the folder on GitHubat commit 9ffb831

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 skillrshankras/claude-code-apple-skills785—~4.2kAutomated safety check: NotesMIT
Test Gap Auditgithub/awesome-copilot40k—~3.4kAutomated safety check: PassMIT
MCP Dependency Drift Auditsickn33/agentic-awesome-skills47k1 repos~2kAutomated safety check: PassMIT
Audit Coverage Gapsben-manes/caffeine18k—~448Automated safety check: PassApache-2.0
Phoenix Docs Gap AuditArize-ai/phoenix12k—~4.8kAutomated safety check: PassCustom licence
Audit Contract Driftben-manes/caffeine18k—~1.1kAutomated safety check: PassApache-2.0

Similar skills

  • Test Gap Audit

    github/awesome-copilot

    Official

    Run a read-only audit for missing, weak, stale, or mis-scoped test coverage.

    40k GitHub stars~3.4k tokensUpdated today
    Testing & QAAuto-check passed
  • MCP Dependency Drift Audit

    sickn33/agentic-awesome-skills

    Statically audit MCP configs for mutable npm/npx package references before approval or CI, without executing discovered MCP servers.

    47k GitHub starsUsed in 1 repo~2k tokens
    Agent WorkflowsAuto-check passed
  • Audit Coverage Gaps

    ben-manes/caffeine

    Discover test coverage gaps that could hide correctness defects

    18k GitHub stars~448 tokensUpdated today
    Testing & QAAuto-check passed
  • Phoenix Docs Gap Audit

    Arize-ai/phoenix

    Audit documentation gaps across the Phoenix repo by analyzing recent commits to main (default: last 7 days).

    12k GitHub stars~4.8k tokensUpdated today
    DevelopmentAuto-check passed
  • Audit Contract Drift

    ben-manes/caffeine

    Find places where documented API contracts and the implementation diverge

    18k GitHub stars~1.1k tokensUpdated today
    Backend & APIsAuto-check passed
  • Semantic Consistency Auditor

    aipoch/medical-research-skills

    Use semantic consistency auditor for academic writing workflows that need structured execution, explicit assumptions, and clear output boundaries.

    2k GitHub stars~3.1k tokensUpdated 22 days ago
    Research & ScienceAuto-check passed

More from rshankras/claude-code-apple-skills

All 41 skills in this repo
  • Accessibility Generator

    rshankras/claude-code-apple-skills

    Generate accessibility infrastructure for VoiceOver, Dynamic Type, and accessibility features.

    785 GitHub stars~1.4k tokensUpdated 2 mo ago
    Auto-check: notes
  • Animation Patterns

    rshankras/claude-code-apple-skills

    SwiftUI animation patterns including springs, transitions, PhaseAnimator, KeyframeAnimator, SF Symbol effects, scroll-driven effects, mesh gradients, text renderers, and shader effects.

    785 GitHub stars~2.1k tokensUpdated 2 mo ago
    Auto-check passed
  • App Description Writer

    rshankras/claude-code-apple-skills

    Generate compelling App Store descriptions that convert browsers into users.

    785 GitHub stars~1.3k tokensUpdated 2 mo ago
    Auto-check passed
  • App Icon Generator

    rshankras/claude-code-apple-skills

    Generates an app icon for macOS or iOS — a fast CoreGraphics placeholder and/or flat layered source art to finish in Icon Composer (the Liquid Glass / iOS 26+ standard).

    785 GitHub stars~5.1k tokensUpdated 2 mo ago
    Auto-check: notes
  • App Namer

    rshankras/claude-code-apple-skills

    Turn an app idea into validated, App-Store-ready name candidates.

    785 GitHub stars~3.4k tokensUpdated 2 mo ago
    Auto-check passed
  • Bundles And Licensing

    rshankras/claude-code-apple-skills

    Revenue beyond the single-app price tag — own-app bundles, Family Sharing as a conversion lever, cross-developer bundles & suites, and institutional licensing via Group Purchases / Apple School &…

    785 GitHub stars~1.8k tokensUpdated 2 mo ago
    Auto-check passed

Questions about Skill Auditor

What does Skill Auditor do?

Audits skills in this repo for consistency, API drift, and structural gaps. Skill Auditor is an agent skill from rshankras/claude-code-apple-skills. Audits skills in this repo for consistency, API drift, and structural gaps.

When should I use Skill Auditor?

Skill Auditor fits situations like: asked to audit skills; check the skill repo for drift; planning bulk skill cleanup.

How do I install Skill Auditor in Claude Code?

Run `npx skills add rshankras/claude-code-apple-skills --skill skill-auditor -a claude-code`. Or copy the skill folder (skills/shared/skill-auditor in rshankras/claude-code-apple-skills) 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 rshankras/claude-code-apple-skills --skill skill-auditor -a codex`. Or copy the skill folder (skills/shared/skill-auditor in rshankras/claude-code-apple-skills) 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 rshankras/claude-code-apple-skills --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. Its frontmatter pre-approves these tools: Read, Glob, Grep, Bash.

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 notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Skill Auditor use?

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

How many tokens does Skill Auditor use?

About 4.2k tokens (SKILL.md is roughly 17k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Skill Auditor?

Skills that share tags, products or a category with Skill Auditor: Test Gap Audit (github/awesome-copilot, 40k stars), MCP Dependency Drift Audit (sickn33/agentic-awesome-skills, 47k stars), Audit Coverage Gaps (ben-manes/caffeine, 18k stars) and Phoenix Docs Gap Audit (Arize-ai/phoenix, 12k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Skill Auditor?

rshankras (a GitHub user) maintains it in rshankras/claude-code-apple-skills, which has 785 GitHub stars. The repository holds 41 skills in this directory. The repository was last updated on July 24, 2026.

Source: rshankras/claude-code-apple-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.