Extract
Turn a proven pattern or debugging solution into a standalone reusable skill with SKILL.md, reference docs, and examples.
Before & after
Same prompt, same agent — the only difference is the skill.
That's a good idea to package up your authentication pattern for reuse. You'd want to document how it works, provide some code examples, and maybe make a reference guide. I could help you write documentation, but you'd need to think about how to structure it so other people can understand and use it. You might also want to include some examples showing how to integrate it into a new project. What specific parts of your authentication pattern do you want to highlight?
SKILL EXTRACTION OUTPUT: Custom Auth Pattern
FILE STRUCTURE
skill/
SKILL.md (1500 words)
reference/
API.md (endpoint specs, auth headers)
CONFIG.md (environment variables required)
EXAMPLES.md (3 real integration examples)
TROUBLESHOOTING.md (common errors, fixes)
templates/
middleware-jwt.ts (copy-paste middleware)
protected-api-route.ts (API example)
protected-component.tsx (React example)
SKILL.md OUTLINE
1. What it does (42-char headline)
2. When to use it (3 scenarios)
3. Setup in 5 steps (code blocks)
4. Advanced: rotation policy, token refresh, role-based access
5. Gotchas: clock skew in Docker, token size limits on headers
REFERENCE/API.md EXAMPLE
POST /auth/login
Request: { email, password }
Response: { access_token, refresh_token, expires_in: 3600 }
Headers: Content-Type: application/json
GET /auth/verify
Headers: Authorization: Bearer {access_token}
Response: { user_id, roles, exp }
EXAMPLES/INTEGRATION.md
Example 1: Express middleware setup
Example 2: Next.js API route protection
Example 3: React hook for token refresh
Each includes error handling and test assertions
TROUBLESHOOTING.md
Issue: "Invalid token signature in staging"
Cause: Different SIGNING_KEY between environments
Fix: Verify .env.staging has matching key
Issue: "Token expired immediately"
Cause: Server clock drift (Docker)
Fix: Run `ntpd` or use serverless timestamp service
Deliverable: skill.zip (ready to upload to agent marketplace)About this skill
name: extract description: Use when Turn a proven pattern or debugging solution into a standalone reusable skill with SKILL.md, reference docs, and examples.
Extract
Turn a proven pattern or debugging solution into a standalone reusable skill with SKILL.md, reference docs, and examples. Use when the user runs /si:extract or asks to package a recurring solution from memory into a skill.
What you get
- Public GitHub repo (alirezarezvani/claude-skills)
- the extract skill folder with SKILL.md. Part of a 337-skill / 30-agent / 70-command install.
Customize your output
- Fork the repo and adapt the skill's instructions and references to your workflow.
Example output
Activates automatically when your request matches Extract; chains with the other skills, agents, and commands in the collection.
Best for
Creators, builders, and teams using Claude Code.
SKILL.md preview
---
name: extract
description: Use when a recurring pattern or hard-won debugging solution should be packaged into a standalone, reusable skill rather than re-solved from scratch next time.
version: 1.0.0
category: Development / Engineering
author: AgentVolt
license: proprietary
tags:
- development
- engineering
---
# Extract
Packages a proven pattern or debugging fix into a standalone skill: a SKILL.md, reference docs, and worked examples.
## When to use
… (sign up to view the full skill)More development skills
View all Development skills →Generate
Scaffold code, tests, and boilerplate from a short spec.
Performance Profiler
Systematic performance profiling for Node.js, Python, and Go applications.
Threat Detection
Use when hunting for threats in an environment, analyzing IOCs, or detecting behavioral anomalies in telemetry.
Agent Harness
Turns a domain folder of skills into a bounded agentic loop: compile a goal into a task plan, execute with the domain's tools, verify every task, retry within a budget.