api-design — community api-design, on_prem_rag, community, ide skills, Claude Code, Cursor, Windsurf

v1.0.0
GitHub

About this Skill

Perfect for API Development Agents needing structured endpoint design and management capabilities. On-Premises RAG Solution: Talk with your documents and data without the Cloud concerns

pkuppens pkuppens
[1]
[0]
Updated: 3/2/2026

Agent Capability Analysis

The api-design skill by pkuppens is an open-source community AI agent skill for Claude Code and other IDE workflows, helping agents execute tasks with better context, repeatability, and domain-specific guidance.

Ideal Agent Persona

Perfect for API Development Agents needing structured endpoint design and management capabilities.

Core Value

Empowers agents to design and refactor API endpoints using HTTP verbs and status codes, incorporating lessons from v0→v1 redesign and supporting OpenAPI documentation.

↓ Capabilities Granted for api-design

Refactoring existing API routes for better performance
Designing new API endpoints with proper request/response models
Reviewing and optimizing API documentation for clarity and accuracy

! Prerequisites & Limits

  • Requires knowledge of HTTP verbs and status codes
  • Limited to API design and refactoring, not implementation
Labs Demo

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

api-design

Install api-design, an AI agent skill for AI agent workflows and automation. Works with Claude Code, Cursor, and Windsurf with one-command setup.

SKILL.md
Readonly

API Design Skill

Use when designing new API endpoints, refactoring existing routes, or reviewing API changes. Incorporates lessons from the v0→v1 redesign.

When to Invoke

  • Adding a new route or router
  • Changing request/response models
  • Refactoring document upload, ask, query, or chat endpoints
  • Reviewing API documentation (OpenAPI, /docs, /redoc)
  • Deciding between new endpoint vs extending existing

Core Rules (from API_DESIGN.md)

1. HTTP Verbs and Status Codes

VerbUseIdempotent
GETRetrieve, list, healthYes
POSTCreate, action (ask, transcribe)No (unless designed)
PUTReplace resourceYes
DELETERemoveYes

Upload semantics (implemented):

  • New: 201 Created, created: true
  • Duplicate (hash match): 200 OK, created: false — no file saved, no processing

2. Resource Naming

  • Plural nouns: /api/documents, not /api/document
  • Hierarchical: /api/documents/{id}/chunks
  • No verbs in URLs; use HTTP method
  • RPC-style actions OK for domain operations: /api/ask, /api/ask/voice

3. New vs Extend

Create new when: different resource, different contract, clear separation. Extend when: same resource, minor variant, additive params.

Example: /api/ask + /api/ask/voice — extend. /api/query vs /api/ask — separate (chunks vs answer).

4. Anti-Patterns (from current codebase)

  • Duplicate endpoints: POST /api/documents/upload and POST /api/v1/upload — consolidate in v1.
  • Overlapping semantics: document list by router — unify contract.
  • Missing OpenAPI metadata: add tags, summary, description, examples.

5. Checklist Before PR

  • Correct HTTP verb
  • Consistent naming
  • OpenAPI tags, description, examples
  • Pydantic models for request/response
  • Unit tests for route
  • API_ENDPOINTS.md updated

References

FAQ & Installation Steps

These questions and steps mirror the structured data on this page for better search understanding.

? Frequently Asked Questions

What is api-design?

Perfect for API Development Agents needing structured endpoint design and management capabilities. On-Premises RAG Solution: Talk with your documents and data without the Cloud concerns

How do I install api-design?

Run the command: npx killer-skills add pkuppens/on_prem_rag. It works with Cursor, Windsurf, VS Code, Claude Code, and 19+ other IDEs.

What are the use cases for api-design?

Key use cases include: Refactoring existing API routes for better performance, Designing new API endpoints with proper request/response models, Reviewing and optimizing API documentation for clarity and accuracy.

Which IDEs are compatible with api-design?

This skill is compatible with Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer. Use the Killer-Skills CLI for universal one-command installation.

Are there any limitations for api-design?

Requires knowledge of HTTP verbs and status codes. Limited to API design and refactoring, not implementation.

↓ How To Install

  1. 1. Open your terminal

    Open the terminal or command line in your project directory.

  2. 2. Run the install command

    Run: npx killer-skills add pkuppens/on_prem_rag. The CLI will automatically detect your IDE or AI agent and configure the skill.

  3. 3. Start using the skill

    The skill is now active. Your AI agent can use api-design immediately in the current project.

Related Skills

Looking for an alternative to api-design or another community skill for your workflow? Explore these related open-source skills.

View All

widget-generator

Logo of f
f

f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.

★ 149.6k
⑂ 0
AI

flags

Logo of vercel
vercel

flags is a Next.js feature management skill that enables developers to efficiently add or modify framework feature flags, streamlining React application development.

★ 138.4k
⑂ 0
Browser

zustand

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

★ 72.8k
⑂ 0
AI

data-fetching

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

★ 72.8k
⑂ 0
AI