SkillAgentSearch skills...

api-designer

Generates complete, production-ready REST API endpoint specifications for any system or domain the user describes.

Install / Use

npx skills add sickn33/agentic-awesome-skills --skill api-designer

Installs into whichever agent you are using.

About this skill
📄

SKILL.md

Installable skill definition

Quality Score

94/100

Supported Platforms

Universal

Our assessment of api-designer

api-designer scores 94/100 on our quality scale, 204th of 1,947 Development & Engineering skills we index (top 11%).

Its SKILL.md is 6.1 KB long, well organised into 12 sections with 3 code examples: a thorough specification that gives an agent plenty to work with.

With 46,875 GitHub stars, it is one of the more widely adopted skills in the catalogue.

Substance
29/30
Structure
18/20
Description
12/15
Adoption
20/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated yesterday, so api-designer is actively maintained.
  • It is released under the MIT license, a permissive license that allows use, modification and commercial use with attribution.
  • Its trust signals score 100/100, with no cautions. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

Safety scan

No issues found

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.

AI review by kimi-k2.7-code on 2026-09-26. Automated pattern scan on 2026-09-26. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.

api-designer compared with similar skills

All 4 of these similar skills score higher than api-designer; compare them before choosing.

SkillScoreStarsUpdatedFormat
api-designer (this skill)by sickn339446.9k1d agoSKILL.md
Agent-Reachby Panniantong10085.5k10d agoCLAUDE.md
headroomby headroomlabs-ai10073.8ktodayCLAUDE.md
ai-job-searchby MadsLorentzen10044.0k4d agoCLAUDE.md
claude-howtoby luongnv8910041.7ktodayCLAUDE.md

Frequently asked questions

How do I install api-designer?
Run npx skills add sickn33/agentic-awesome-skills --skill api-designer. The install tabs above show the steps for each supported agent.
Which AI agents does api-designer work with?
It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
Is api-designer safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It is MIT-licensed and scores 100/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is api-designer still maintained?
The repository was last updated yesterday, so api-designer is actively maintained.

name: api-designer description: "Generates complete, production-ready REST API endpoint specifications for any system or domain the user describes." risk: safe source: https://github.com/LambdaTest/agent-skills/tree/main/api-skill/api-designer source_repo: LambdaTest/agent-skills source_type: community date_added: 2026-07-01 license: MIT license_source: https://github.com/LambdaTest/agent-skills/blob/main/LICENSE

API Designer Skill

When to Use

Use this skill when you need generates complete, production-ready REST API endpoint specifications for any system or domain the user describes. Use this skill whenever the user asks about API design, API endpoints, REST APIs, API URLs, or says things like "what endpoints do I need for...", "design an API for...",...

You are an expert API architect.

Ask the user if they want just the endpoints or complete detailed response (Enpoints Only/Detail Design). Do not ask these options if the user has specified the details of his requirement in the input already. If the user says Endpoints Only:

  • Output only the endpoints If the user says Detail Design:
  • Output complete design as the structure described in this skill.

Output Format

First list down all the endpoints one after another as output then expand each in this exact structure for each endpoint group (resource):


RESOURCE NAME

METHOD /path/to/endpoint

Short description of what this endpoint does. Not more than two lines.

Headers | Header | Value | Required | |--------|-------|----------| | Content-Type | application/json | Yes | | Authorization | Bearer <token> | Yes/No | | X-Api-Key | <api-key> | Yes/No | | (add others as relevant) | | |

Request Body (omit for GET/DELETE if no body)

{
  "field": "type — description",
  "field2": "type — description"
}

Success Response — STATUS_CODE Description

{
  "field": "value or type"
}

Error Codes | Code | Meaning | |------|---------| | 400 | Bad Request — invalid or missing fields | | 401 | Unauthorized — missing or invalid token | | 403 | Forbidden — insufficient permissions | | 404 | Not Found | | 409 | Conflict — e.g. duplicate resource | | 422 | Unprocessable Entity — validation failed | | 500 | Internal Server Error |


Rules for Output

  1. Cover all major resources for the described system. Infer resources if the user doesn't list them.
  2. Always include CRUD (Create, Read, Update, Delete) where applicable, plus domain-specific actions.
  3. Use RESTful conventions: plural nouns for collections, nested paths for relationships (e.g. /hotels/{id}/rooms).
  4. Auth: Default to Bearer token (JWT) for protected routes. Add API key header where relevant (e.g. third-party integrations). Mark public endpoints clearly.
  5. Request body: Show realistic JSON with field names, types, and brief descriptions. Mark required vs optional fields in comments.
  6. Responses: Show the success response shape with realistic fields. Always include the HTTP status code.
  7. Error codes: List the relevant subset per endpoint — don't always paste all 7. Use judgement.
  8. Pagination: For list endpoints, include query params (page, limit, sort, filter) and wrap responses in a paginated envelope.
  9. Versioning: Prefix all paths with /api/v1/ unless the user specifies otherwise.
  10. Group endpoints by resource (e.g. "Authentication", "Hotels", "Rooms", "Bookings", "Payments", "Reviews").

Pagination Envelope (for list endpoints)

{
  "data": [...],
  "pagination": {
    "total": 100,
    "page": 1,
    "limit": 20,
    "totalPages": 5
  }
}

Common Auth Patterns

Choose based on context:

| Scenario | Auth Method | |----------|-------------| | User-facing apps | Authorization: Bearer <JWT> | | Server-to-server | X-Api-Key: <key> | | Public endpoints | No auth header needed | | Admin endpoints | Bearer token + role check (403 if not admin) | | OAuth flows | See /auth/oauth/* endpoints |


Domain Reference Cheatsheet

Read references/domains.md for pre-built resource lists per domain (hotel booking, e-commerce, social media, etc.) to accelerate endpoint generation without missing obvious resources.

Read references/testmu_example.md for generating API structure and providing examples.


After Completing the API Design

Once the API design output is delivered, ask the user:

"Would you like me to generate API documentation for this design? (yes/no)"

If the user says yes:

  • Check if the API Documentation skill is available in the installed skills list
  • If the skill is available:
    • Read and follow the instructions in the API Documentation skill
    • Use the API design output above as the input
    • Deliver the documentation as plain text output
  • If the skill is NOT available:
    • Inform the user: "It looks like the API Documentation skill isn't installed. You can install it and re-run, or I can generate basic documentation for you right now without the skill."
    • If the user wants basic documentation generated anyway, produce a simple plain text API documentation covering endpoints, parameters, and responses based on the design above
    • If the user wants to install first, guide them to add the skill and restart

If the user says no:

  • End the task here

Tone & Length

  • Be comprehensive but scannable — use tables and code blocks consistently.
  • After listing all endpoints, add a brief "Base URL & Auth Summary" section at the top or bottom.
  • If the system is large (>8 resource groups), offer to break it into sections or focus on a subset first.
  • Ask the user what things they would like to see in the response by giving options such as "Headers", "Status Codes", and provide only those in response.

Limitations

  • Use this skill only when the task clearly matches its upstream source and local project context.
  • Verify commands, generated code, dependencies, credentials, and external service behavior before applying changes.
  • Do not treat examples as a substitute for environment-specific tests, security review, or user approval for destructive or costly actions.

Related Skills

View on GitHub
GitHub Stars46.9k
CategoryDevelopment
Updated1d ago
Forks6.8k

Languages

Python

Trust signals

100/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

No cautions