porcupine-md/jonggrang/auth
Claude Code and agent skill by porcupine-md/jonggrang
Trust tier 3
- community
Source check pending
Checking that the SKILL.md file is still in the repository.
Setup authentication flow (register, login, session/JWT, middleware)
Install
npx vskill@latest install porcupine-md/jonggrang/authSKILL.md
Context
Project {{project_name}} uses {{stack}}. Setup authentication with strategy: {{input.strategy}}.
Read AGENTS.md for security conventions.
Instructions
- Analyze existing auth setup
- Check if auth middleware / auth routes already exist
- Check already installed dependencies (bcrypt, jsonwebtoken, passport, next-auth, etc.)
- Identify existing user model/schema
- Setup dependencies
Adjust based on strategy:
- JWT: bcrypt/argon2, jsonwebtoken/jose
- Session: express-session, connect-redis (optional)
- OAuth: next-auth / passport + passport-google-oauth20, etc.
- Create/update user model
- Fields: id, email, password_hash, name, created_at, updated_at
- If OAuth: add provider, provider_id fields
- Migration if needed (use migration skill)
- Create auth service
- Register: validate input, hash password, create user, return token
- Login: find user, verify password, return token
- Verify: validate token, return user
- Refresh: refresh expired token (if JWT)
- Create auth routes
- POST /api/auth/register
- POST /api/auth/login
- POST /api/auth/logout
- GET /api/auth/me (current user)
- POST /api/auth/refresh (if JWT)
- Create auth middleware
- Extract token from header/cookie
- Verify token
- Attach user to request
- Return 401 if invalid
- Create tests
- Register: success, duplicate email, weak password
- Login: success, wrong password, user not found
- Protected route: with token, without token, expired token
- Middleware: valid token, invalid token, no token
Script
Validation
- [ ] User model/schema created with proper fields
- [ ] Password hashing works (not stored as plaintext)
- [ ] Register endpoint works (happy path + errors)
- [ ] Login endpoint works (happy path + errors)
- [ ] Auth middleware protects routes correctly
- [ ] Token validation works
- [ ] Tests passing (minimum 8 test cases)
- [ ] No security vulnerabilities (no secret in code, proper CORS, etc)
- [ ] Typecheck passing
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/core/auth/SKILL.md
Popularity
- Repository stars
- 14
- Repository forks
- 3
- 7-day trend score
- 19
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/porcupine-md/jonggrang/auth)