andersonamaral2/claude-code-to-deep-agents-skills-converter/deep-agents-output-3
Claude Code and agent skill by andersonamaral2/claude-code-to-deep-agents-skills-converter
- community
Checking that the SKILL.md file is still in the repository.
Builds a production-style Express.js REST API with JWT authentication, PostgreSQL, layered middleware, and Docker Compose for local development. Use when the user asks to scaffold a secure Node.js/Express API with login, protected routes, and a relational database.
Install
npx vskill@latest install andersonamaral2/claude-code-to-deep-agents-skills-converter/deep-agents-output-3SKILL.md
Skill: Express.js JWT API with PostgreSQL and Docker
Builds a production-style Express.js REST API with JWT authentication, a PostgreSQL database, layered middleware, and Docker Compose for local development.
Execution Context
This skill runs inside Deep Agents CLI (v0.0.34+). Available tools:
| Tool | Usage in this skill | |
|---|---|---|
write_todos | Plan the build steps | |
execute | Run npm, docker, curl, and inline tests | |
write_file | Create source files, SQL, compose, and .env | |
edit_file | Adjust files if a test reveals an issue |
Critical execution rules:
- Always start by creating the plan via
write_todos. - Create files one by one via
write_file— never generate everything at once. - Test each module via
executeimmediately after creating it. - Verify required environment variables before starting the server.
Execution Plan (use with write_todos)
- [ ] 1. Check prerequisites (Node.js 18+, npm, Docker, Docker Compose)
- [ ] 2. Verify environment variables (JWT_SECRET, DATABASE_URL, PORT)
- [ ] 3. Initialize project and install dependencies
- [ ] 4. Create src/db.js (PostgreSQL pool)
- [ ] 5. Create middleware (auth.js, logger.js)
- [ ] 6. Create routes (auth.js, notes.js)
- [ ] 7. Create src/index.js entry point
- [ ] 8. Create db/init.sql and docker-compose.yml
- [ ] 9. Create .env, start the database, run the API
- [ ] 10. Test the full register → login → create-note flow
Prerequisites Check
Use execute to verify the toolchain:
Environment Setup
Verify required environment variables via execute:
Security note: Never hardcode production secrets. The .env below uses placeholders; keep it out of version control via .gitignore.
Implementation
Initialize the project via execute:
Install dependencies via execute:
Use write_file to create src/db.js:
Test via execute:
Use write_file to create src/middleware/auth.js:
Use write_file to create src/middleware/logger.js:
Test the middleware via execute:
Use write_file to create src/routes/auth.js with POST /auth/register (bcrypt-hash the password and insert the user) and POST /auth/login (verify the password and return a signed JWT).
Use write_file to create src/routes/notes.js with CRUD endpoints (GET/POST/PUT/DELETE /notes) guarded by the authRequired middleware and scoped to req.user.id.
Test the routers via execute:
Use write_file to create src/index.js:
Use write_file to create db/init.sql:
Use write_file to create docker-compose.yml:
Use write_file to create .env:
Security note: These are placeholder secrets. Replace them with real values from your secret manager before deploying, and add .env to .gitignore.
Start the database via execute:
Add a dev script and run the API via execute:
Test the full flow via execute:
Document the project architecture and conventions in AGENTS.md at the root (the Deep Agents equivalent of a project memory file).
Usage with Deep Agents CLI
Mode 1 — Build (one-shot)
Mode 2 — Interactive
Mode 3 — Non-interactive (CI/CD)
Troubleshooting
Node.js not found
Database connection refused
JWT verify fails on protected routes
Port 3000 already in use
Context window overflow
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 repositoryCheckingexamples/deep-agents-output-3/SKILL.md
Popularity
- Repository stars
- 55
- Repository forks
- 8
- 7-day trend score
- 20
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/andersonamaral2/claude-code-to-deep-agents-skills-converter/deep-agents-output-3)