Backend Development
Build API endpoints, server logic, and backend services. Use this skill when a backend task is ready for implementation, including REST/GraphQL APIs, middleware, and server-side processing.
Best use case
Backend Development is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Build API endpoints, server logic, and backend services. Use this skill when a backend task is ready for implementation, including REST/GraphQL APIs, middleware, and server-side processing.
Teams using Backend Development should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/backend-dev/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How Backend Development Compares
| Feature / Agent | Backend Development | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Build API endpoints, server logic, and backend services. Use this skill when a backend task is ready for implementation, including REST/GraphQL APIs, middleware, and server-side processing.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Skill: Backend Development ## Metadata | Field | Value | |-------|-------| | **Skill ID** | SKL-0006 | | **Version** | 1.0 | | **Owner** | builder | | **Inputs** | Task description, DECISIONS.md, existing backend files | | **Outputs** | Backend files, STATE.md updated | | **Triggers** | `BACKEND_TASK_READY` | --- ## Purpose Build server-side logic — APIs, database models, business logic, and integrations. --- ## Procedure 1. **Read DECISIONS.md** — identify backend framework, database, ORM, auth approach. 2. **Design before building** — inputs, outputs, failure modes, database changes. 3. **Build with non-negotiables:** - Validate all inputs before processing - Never trust client-supplied data - Use parameterized queries — never string-concatenate SQL - Consistent error responses with appropriate HTTP status codes - Log errors with context, never log sensitive data 4. **Database operations:** - Use migrations for all schema changes - Every migration must be reversible - Index foreign keys and frequently queried fields 5. **Environment and secrets:** - Never hardcode credentials — all via environment variables - Document new env vars in .env.example 6. **Update STATE.md** with files created. --- ## Constraints - Never modifies frontend files - Never hardcodes secrets or credentials - Never writes raw SQL string concatenation - Always logs new stack/database decisions to DECISIONS.md --- ## Deployment Reference | Target | Tool | Notes | |--------|------|-------| | API server (beginner) | Railway | Auto-deploys, free tier | | API server (beginner) | Render | Good free tier | | API server (control) | Fly.io | Docker-based, scales to zero | | Serverless | Vercel/Netlify Functions | Lightweight APIs | --- ## Primary Agent builder --- ## Definition of Done - [ ] Stack and database confirmed from DECISIONS.md - [ ] All inputs validated - [ ] Parameterized queries used - [ ] Consistent error handling and HTTP status codes - [ ] No hardcoded credentials - [ ] Migrations created for schema changes - [ ] STATE.md updated ## Output Contract | Field | Value | |-------|-------| | **Artifacts** | Backend source files (routes, models, services, migrations) | | **State Update** | `.claude/project/STATE.md` — mark task complete, log files modified | | **Decision Log** | `.claude/project/knowledge/DECISIONS.md` — stack and database architecture decisions | | **Handoff Event** | `TASK_COMPLETED` (ready for code review) | ## Knowledge Enhancement (MCP mode) If Cortex MCP is available: 1. Call `search_knowledge` with query derived from task (e.g., "REST API patterns", "database migration patterns"), category="patterns" 2. If relevant results found, call `get_fragment` on the top result 3. Apply as supplementary context (does not override this skill's procedure)
Related Skills
Mobile Development
Build mobile app screens, navigation, and platform-specific features. Supports three platforms: React Native + Expo (cross-platform), Swift/SwiftUI (native iOS), and Kotlin/Jetpack Compose (native Android). Use this skill when a mobile task is ready for implementation.
Game Development
Build web-based games across four modes: adventure (narrative + puzzles), sandbox (open world + crafting), action (real-time combat + physics), and educational (learning objectives + adaptive difficulty). Covers game loop, scene management, asset pipeline, input handling, and state persistence.
Frontend Development
Build web UI components, pages, and styling. Includes a mandatory Visual Polish pass that adds scroll animations, micro-interactions, typography rhythm, and design depth. Use this skill when a frontend task is ready for implementation, including React components, CSS, layouts, and responsive design.
Supply Chain Audit
Audit the dependency supply chain for security risks beyond what `npm audit` or `pip audit` catches. Analyzes dependency health, maintainer trust signals, typosquatting risk, and transitive dependency exposure.
SEO Audit
Audit web pages for search engine optimization: meta tags, heading hierarchy, structured data, image optimization, mobile-friendliness, and content quality. Complements SKL-0013 (Growth & Distribution) by validating what was built.
Pitch Deck
Create a structured pitch deck outline for investors, stakeholders, or partners. Covers problem, solution, market, traction, team, and ask. Natural output after PRD + Problem Stress Test validation.
Launch Checklist
Pre-launch validation covering everything deployment (SKL-0021) doesn't: analytics, error tracking, social meta, legal pages, email setup, DNS, SSL, and go-live readiness. Produces a launch readiness report with pass/fail checklist. Use this skill before going live on any project.
Insecure Defaults Detection
Detect insecure default configurations, hardcoded credentials, fail-open security patterns, and dangerous default values in application code and configuration files. Complements SKL-0015 (Security Audit) by focusing on configuration-level vulnerabilities that dependency scanners miss.
Differential Security Review
Security-focused review of code changes using git diff analysis. Identifies security implications of recent modifications — new attack surfaces, removed protections, changed auth logic, and risky refactors. Complements SKL-0016 (Code Review) with a security lens on diffs.
Copywriting
Write conversion-focused copy using proven frameworks (AIDA, PAS, BAB). Produces headlines, CTAs, landing page copy, email sequences, and micro-copy. Ensures copy matches brand voice and target audience.
Competitor Analysis
Structured competitor research: features, pricing, positioning, gaps, and differentiation strategy. Feeds into PRD Writing (SKL-0004) and Problem Stress Test (SKL-0027) with better market context.
UX Design
Design user experiences including wireframes, flows, and interaction patterns. Use this skill when UX design work is requested, including onboarding flows and interface layouts.