DiscordSign up
SKILLS.SH

skill-review

Systematic 9-phase audit for claude-skills covering standards, docs verification, code accuracy, and version drift. Validates YAML structure, keywords, third-person style, and directory organization against skill standards Verifies API patterns, imports, and code examples against official documentation, GitHub repos, and npm packages Cross-checks consistency between SKILL.md and README.md, detects stale dependencies (>90 days), and identifies breaking changes Categorizes issues by severity (Critical/High/Medium/Low) with evidence links, auto-fixes unambiguous problems, and bumps versions appropriately Prevents 10 common issues including fake API adapters, outdated method signatures, schema inconsistencies, and broken links

INSTALLATION
npx skills add https://github.com/jezweb/claude-skills --skill skill-review
Run in your project or agent environment. Adjust flags if your CLI version differs.

SKILL.md

Skill Review Skill

Process

Invoke: /review-skill <skill-name> or use this skill when detecting outdated patterns

Production evidence: better-auth audit (2025-11-08) - found 6 critical issues including non-existent API imports, removed 665 lines incorrect code, implemented v2.0.0

9-Phase Audit

  • Pre-Review: Install skill, check version/date, test discovery
  • Standards: Validate YAML, keywords, third-person style, directory structure
  • Official Docs: WebFetch/Context7 verify API patterns, GitHub updates, npm versions, production repos
  • Code Examples: Verify imports exist, API signatures match, schema consistency, templates work
  • Cross-File Consistency: Compare SKILL.md vs README.md, bundled resources match files
  • Dependencies: Run ./scripts/check-versions.sh, check breaking changes, verify "Last Verified"
  • Categorize: Severity (🔴 Critical / 🟡 High / 🟠 Medium / 🟢 Low) with evidence (GitHub/docs/npm)
  • Fix: Auto-fix unambiguous, ask user for architectural, update all files, bump version
  • Verify: Test discovery, templates work, no contradictions, commit with changelog

Automated (via ./scripts/review-skill.sh): YAML syntax, package versions, broken links, TODOs, file org, staleness

Manual (AI): API methods vs docs, GitHub issues, production comparisons, code correctness, schema consistency

Severity Classification

🔴 CRITICAL: Non-existent API/imports, invalid config, missing dependencies

🟡 HIGH: Contradictory examples, inconsistent patterns, outdated major versions

🟠 MEDIUM: Stale minors (>90d), missing docs sections, incomplete errors

🟢 LOW: Typos, formatting, missing optional metadata

Fix Decision

Auto-fix: Unambiguous (correct import from docs), clear evidence, no architectural impact

Ask user: Multiple valid approaches, breaking changes, architectural choices

Version Bumps

  • Major (v1→v2): API patterns change
  • Minor (v1.0→v1.1): New features, backward compatible
  • Patch (v1.0.0→v1.0.1): Bug fixes only

Example: better-auth Audit (2025-11-08)

🔴 CRITICAL #1: Non-existent d1Adapter import from 'better-auth/adapters/d1'

  • Evidence: Official docs show drizzleAdapter, GitHub has no d1Adapter export, 4 production repos use Drizzle/Kysely
  • Fix: Replaced with drizzleAdapter from 'better-auth/adapters/drizzle'

Result: 3 files deleted (obsolete), 3 created (correct patterns), +1,266 lines, v1.0→v2.0, 3.5 hours

Issues Prevented (10)

  • Fake API adapters - Non-existent imports
  • Stale API methods - Changed signatures
  • Schema inconsistency - Different table names
  • Outdated scripts - Deprecated approaches
  • Version drift - Packages >90 days old
  • Contradictory examples - Multiple conflicting patterns
  • Broken links - 404 URLs
  • YAML errors - Invalid frontmatter
  • Missing keywords - Poor discoverability
  • Incomplete bundled resources - Listed files don't exist

Bundled Resources

Planning: ~/.claude/skills/../planning/SKILL_REVIEW_PROCESS.md or repo planning/SKILL_REVIEW_PROCESS.md (complete 9-phase guide)

Scripts: Repo root scripts/review-skill.sh (automated validation)

Commands: Repo root commands/review-skill.md (slash command, symlinked to ~/.claude/commands/)

References: references/audit-report-template.md (output template)

Last Verified: 2026-01-09 | Version: 1.0.1

BrowserAct

Let your agent run on any real-world website

Bypass CAPTCHA & anti-bot for free. Start local, scale to cloud.

Explore BrowserAct Skills →

Related skills

find-skills
2/3

Discover and install specialized agent skills from the open ecosystem when users need extended capabilities. Helps identify relevant skills by domain and task when users ask "how do I do X" or "find a skill for X" Integrates with the Skills CLI ( npx skills find , npx skills add ) to search, verify, and install packages from the skills.sh directory Recommends skills based on install count, source reputation, and GitHub stars to ensure quality before suggesting installation Presents skill options with install commands and links to skills.sh for user review and one-click installation

Verified authorvercel-labs
SKILLS.SH
1.5M19.6K
2026-05-22
vercel-react-best-practices
3/3

React and Next.js performance optimization guide with 64 prioritized rules across 8 categories. Organized by impact level, from critical waterfalls and bundle optimization down to advanced patterns, each rule includes incorrect/correct code examples and explanations Covers eight domains: async patterns, bundle size, server-side caching, client-side data fetching, re-render optimization, rendering performance, JavaScript efficiency, and advanced patterns Designed for use during component writing, code review, refactoring, and performance audits on React and Next.js applications Each rule has a prefix code (e.g., async-parallel , bundle-barrel-imports ) for easy reference in automated tooling and documentation

Verified authorvercel-labs
SKILLS.SH
389K26.9K
2026-05-22
azure-validate
2/3

Pre-deployment validation for Azure infrastructure, configuration, and permissions before deployment. Requires .azure/plan.md from a prior azure-prepare run; stops immediately if the plan is missing Executes recipe-specific validation commands (azd provision, bicep build, terraform validate) and records proof in the plan document Performs build verification, configuration checks, and permission validation; blocks deployment if any check fails Only authorized method to set plan status to Validated ; must be followed by azure-deploy skill to execute the actual deployment

Verified authormicrosoft
SKILLS.SH
324K1.1K
2026-05-22
appinsights-instrumentation
3/3

Guidance and reference material for instrumenting webapps with Azure Application Insights. Covers SDK setup, telemetry patterns, and configuration for ASP.NET Core and Node.js applications hosted in Azure Distinguishes between this skill (reference and guidance) and azure-prepare (actual implementation); invoke azure-prepare when the user wants to add instrumentation to their project Provides auto-instrumentation guidance for C# ASP.NET Core apps in Azure App Service, plus manual instrumentation paths for creating App Insights resources via Bicep templates or Azure CLI Includes language-specific code modification guides for ASP.NET Core, Node.js, and Python, plus quick references for OpenTelemetry SDKs and exporters

Verified authormicrosoft
SKILLS.SH
324K1.1K
2026-05-22

Stop writing automation&scrapers

Install the CLI. Run your first Skill in 30 seconds. Scale when you're ready.

Start free
free · no credit card