jezweb

commands

@jezweb/commands
jezweb
162
21 forks
Updated 1/18/2026
View on GitHub

/review-skill - Skill Audit Command: Comprehensive skill documentation audit with automated checks and manual review phases.

Installation

$skills install @jezweb/commands
Claude Code
Cursor
Copilot
Codex
Antigravity

Details

Repositoryjezweb/claude-skills
Pathcommands/review-skill.md
Branchmain
Scoped Name@jezweb/commands

Usage

After installing, this skill will be available to your AI coding assistant.

Verify installation:

skills list

Skill Instructions

/review-skill - Skill Audit Command

Comprehensive skill documentation audit with automated checks and manual review phases.

Usage

/review-skill <skill-name>

Examples

/review-skill better-auth
/review-skill cloudflare-worker-base
/review-skill tiptap

What It Does

Phase 1: Automated Checks

Runs ./scripts/review-skill.sh <skill-name> to check:

  • YAML frontmatter syntax
  • Package version currency (npm/PyPI)
  • Broken links
  • TODO/FIXME comments
  • File organization
  • Staleness indicators

Phase 2: Manual Review

Systematically reviews:

  1. Accuracy - Code examples work, patterns current
  2. Completeness - Coverage vs official docs
  3. Error Prevention - Known issues documented
  4. Token Efficiency - Not bloated, well-organized

Phase 3: Gap Analysis

Identifies:

  • Missing features from latest package version
  • Deprecated patterns still recommended
  • Breaking changes not documented
  • Rules file needed but missing

Phase 4: Remediation

Applies fixes for:

  • Version updates (after npm verification)
  • Documentation inconsistencies
  • Missing sections
  • Stale dates

Output

Generates an audit report with:

## Skill Audit: [skill-name]

### Version Status
| Package | Current | Latest | Status |

### Gaps Found
1. [Issue] - [Severity] - [Evidence]

### Recommended Updates
| Priority | Task | Effort |

### Quality Score: X/10

When to Use

  • Before marketplace submission
  • After major package updates (check changelog first)
  • Skill last verified >90 days ago
  • Investigating patterns that seem outdated
  • User reports skill doesn't work

Related

  • Script: ./scripts/review-skill.sh (automated portion)
  • Skill: skill-review (full methodology)
  • Protocol: planning/SKILL_REVIEW_PROCESS.md (9-phase guide)
  • Audit Protocol: planning/SKILL_AUDIT_PROTOCOL.md (verification-first approach)

Important

Version Verification: Per SKILL_AUDIT_PROTOCOL.md, always verify package versions with npm view before trusting audit agent recommendations. Training data has cutoffs and may suggest deprecated packages as current.

More by jezweb

View all
better-auth
162

Self-hosted auth for TypeScript/Cloudflare Workers with social auth, 2FA, passkeys, organizations, RBAC, and 15+ plugins. Requires Drizzle ORM or Kysely for D1 (no direct adapter). Self-hosted alternative to Clerk/Auth.js. Use when: self-hosting auth on D1, building OAuth provider, multi-tenant SaaS, or troubleshooting D1 adapter errors, session caching, rate limits.

tiptap
162

Build rich text editors with Tiptap - headless editor framework with React and Tailwind v4. Covers SSR-safe setup, image uploads, prose styling, and collaborative editing. Use when creating blog editors, comment systems, or Notion-like apps, or troubleshooting SSR hydration errors, typography issues, or image upload problems.

hono-routing
162

Build type-safe APIs with Hono for Cloudflare Workers, Deno, Bun, Node.js. Routing, middleware, validation (Zod/Valibot), RPC, streaming (SSE), WebSocket, security (CSRF, secureHeaders). Use when: building Hono APIs, streaming SSE, WebSocket, validation, RPC. Troubleshoot: validation hooks, RPC types, middleware chains.

cloudflare-workers-ai
162

Run LLMs and AI models on Cloudflare's GPU network with Workers AI. Includes Llama 4, Gemma 3, Mistral 3.1, Flux images, BGE embeddings, streaming, and AI Gateway. Handles 2025 breaking changes. Use when: implementing LLM inference, images, RAG, or troubleshooting AI_ERROR, rate limits, max_tokens, BGE pooling.