Agent skill

API Design

by cosmicstack-labs in cosmicstack-labs/mercury-agent-skills

REST and GraphQL API design principles, versioning, error handling, and documentation patterns

Install API Design

skills CLI

$ npx skills add cosmicstack-labs/mercury-agent-skills --skill api-design -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install cosmicstack-labs/mercury-agent-skills api-design --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/cosmicstack-labs/mercury-agent-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/categories/backend/api-design .claude/skills/api-design && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "api-design" agent skill from https://github.com/cosmicstack-labs/mercury-agent-skills/tree/main/categories/backend/api-design into .claude/skills/api-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "api-design", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/cosmicstack-labs/mercury-agent-skills/tree/main/categories/backend/api-design

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add cosmicstack-labs/mercury-agent-skills --skill api-design -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install cosmicstack-labs/mercury-agent-skills api-design --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/cosmicstack-labs/mercury-agent-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/categories/backend/api-design .agents/skills/api-design && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "api-design" agent skill from https://github.com/cosmicstack-labs/mercury-agent-skills/tree/main/categories/backend/api-design into .agents/skills/api-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "api-design", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add cosmicstack-labs/mercury-agent-skills --skill api-design -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install cosmicstack-labs/mercury-agent-skills api-design --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/cosmicstack-labs/mercury-agent-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/categories/backend/api-design .cursor/skills/api-design && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "api-design" agent skill from https://github.com/cosmicstack-labs/mercury-agent-skills/tree/main/categories/backend/api-design into .cursor/skills/api-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "api-design", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/cosmicstack-labs/mercury-agent-skills.git --path categories/backend/api-design

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add cosmicstack-labs/mercury-agent-skills --skill api-design -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install cosmicstack-labs/mercury-agent-skills api-design --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/cosmicstack-labs/mercury-agent-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/categories/backend/api-design .gemini/skills/api-design && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "api-design" agent skill from https://github.com/cosmicstack-labs/mercury-agent-skills/tree/main/categories/backend/api-design into .gemini/skills/api-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "api-design", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install cosmicstack-labs/mercury-agent-skills api-design

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add cosmicstack-labs/mercury-agent-skills --skill api-design -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/cosmicstack-labs/mercury-agent-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/categories/backend/api-design .github/skills/api-design && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "api-design" agent skill from https://github.com/cosmicstack-labs/mercury-agent-skills/tree/main/categories/backend/api-design into .github/skills/api-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "api-design", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add cosmicstack-labs/mercury-agent-skills --skill api-design -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install cosmicstack-labs/mercury-agent-skills api-design --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/cosmicstack-labs/mercury-agent-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/categories/backend/api-design .opencode/skills/api-design && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "api-design" agent skill from https://github.com/cosmicstack-labs/mercury-agent-skills/tree/main/categories/backend/api-design into .opencode/skills/api-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "api-design", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: api-design
GitHub stars: 476
Token cost: ~1.9k tokens
SKILL.md length: 580 words
Files: 1
Skills in repo: 12
Repo updated: Aug 25, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

REST and GraphQL API design principles, versioning, error handling, and documentation patterns

Works in 4 steps: Consistency Over Cleverness → Resources, Not Actions → Developer Experience First → …
Tasks that involve API design
SKILL.md covers Core Principles, API Quality Scorecard, Actionable Guidance and Common Mistakes
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

API Design is an agent skill from cosmicstack-labs/mercury-agent-skills. REST and GraphQL API design principles, versioning, error handling, and documentation patterns

Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Backend & APIs, covering API design and GraphQL. It works with GraphQL. The repository describes itself as: A curated registry of reusable Mercury Agent, Open Claw or Hermes Agent skills designed for real developer workflows, persistent memory, and token-efficient execution. The licence is MIT.

When your agent uses it

Tasks that involve API design
Tasks that involve GraphQL

Example prompts

“/api-design”

Workflow steps

4 steps, taken from the step headings in SKILL.md.

Consistency Over Cleverness
Resources, Not Actions
Developer Experience First
Backward Compatibility

What it can do on your machine

Read from SKILL.md and the folder at commit 30392fb. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are json, graphql and yaml).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

API Design loads about 1.9k tokens when it runs. Until then it costs about 26 tokens; SKILL.md has 580 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~26
When it runs · the whole SKILL.md, loaded when a task matches: ~1.9k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from cosmicstack-labs/mercury-agent-skills at commit 30392fb, republished under its MIT licence (© cosmicstack-labs). 580 words, ~1,914 tokens.

Download SKILL.mdSave it as .claude/skills/api-design/SKILL.md (or your agent's skills folder).

name: api-design
description: REST and GraphQL API design principles, versioning, error handling, and documentation patterns
metadata.author: cosmicstack-labs
metadata.version: 1.0.0
metadata.category: backend
metadata.tags: api, rest, graphql, design, documentation, error-handling

API Design

Design APIs that are intuitive, consistent, and a joy to integrate with.

Core Principles

1. Consistency Over Cleverness

Your API should be predictable. If one resource uses POST /users, another shouldn't use POST /createUser. Patterns should be uniform across the entire surface.

2. Resources, Not Actions

URLs name resources. HTTP verbs name actions. /users is a resource. POST /users creates one. DELETE /users/123 removes one.

3. Developer Experience First

Your API's consumers are developers. Good DX means clear errors, thorough documentation, predictable responses, and sensible defaults.

4. Backward Compatibility

Once a field or endpoint is public, removing it breaks consumers. Version carefully. Add fields, don't remove them. Deprecate before deleting.

API Quality Scorecard

Dimension	Poor	Good	Excellent
URL structure	`/getUsers`, `/create_user`	`/users`, `POST /users`	`/users`, `/users/:id`, with HATEOAS links
HTTP methods	All POST	CRUD mapped properly	Proper status codes, idempotency
Error format	HTML or plain text	JSON with message	RFC 7807 Problem Details
Pagination	None or offset	Cursor-based	Cursor + metadata + total hints
Versioning	None	URL prefix `/v1/`	Header or content negotiation
Documentation	None	Swagger/OpenAPI	Interactive docs with examples
Rate limiting	None	`X-RateLimit-*` headers	Granular per-endpoint limits

Target: Good for internal APIs. Excellent for public APIs.

Actionable Guidance

RESTful URL Design

Pattern: /{version}/{resource}[/{resource-id}][/{sub-resource}]

# Good
GET    /v1/users                    # List users
POST   /v1/users                    # Create user
GET    /v1/users/{id}               # Get user by ID
PATCH  /v1/users/{id}               # Partial update user
DELETE /v1/users/{id}               # Delete user
GET    /v1/users/{id}/orders        # List user's orders
GET    /v1/users/{id}/orders/{oid}  # Get specific order

# Bad
GET    /v1/getUserInfo              # Verb in URL
POST   /v1/createNewUser            # Verb, camelCase
PUT    /v1/updateUser               # Verb, vague
GET    /v1/users_list               # Underscore, not a resource
POST   /v1/delete_user/123          # POST for deletion, imperative style

Naming conventions:

Plural nouns: /users, /orders, /products
Lowercase with hyphens: /order-items, not /orderItems or /order_items
No file extensions: /users/123, not /users/123.json
No verbs in URLs: Use HTTP verbs for actions

HTTP Methods and Status Codes

Method	Action	Success Code	Body Contains
`GET`	Retrieve	200 OK	Resource(s)
`POST`	Create	201 Created	Created resource
`PUT`	Full replace	200 OK	Replaced resource
`PATCH`	Partial update	200 OK	Updated resource
`DELETE`	Remove	204 No Content	(empty)

Common status codes:

Code	Meaning	When
200	OK	Successful GET, PUT, PATCH
201	Created	Successful POST
204	No Content	Successful DELETE
400	Bad Request	Malformed input, validation failure
401	Unauthorized	Missing/invalid auth token
403	Forbidden	Valid auth but insufficient permissions
404	Not Found	Resource doesn't exist
409	Conflict	Duplicate resource, version conflict
422	Unprocessable	Semantic validation failure
429	Too Many Requests	Rate limit exceeded
500	Internal Server Error	Unhandled server error

Show full SKILL.md (233 more words)Show less

Error Response Format

Use RFC 7807 (Problem Details):

json

HTTP/1.1 422 Unprocessable Content
Content-Type: application/problem+json

{
  "type": "https://api.example.com/errors/validation-error",
  "title": "Validation Error",
  "status": 422,
  "detail": "The request body contains invalid fields.",
  "instance": "/v1/users",
  "errors": [
    {
      "field": "email",
      "message": "Must be a valid email address",
      "code": "INVALID_FORMAT"
    },
    {
      "field": "age",
      "message": "Must be a positive integer",
      "code": "OUT_OF_RANGE"
    }
  ]
}

Pagination

Cursor-based pagination (recommended for most APIs):

json

GET /v1/users?cursor=eyJpZCI6MTB9&limit=20

{
  "data": [...],
  "pagination": {
    "next_cursor": "eyJpZCI6MzB9",
    "has_more": true
  }
}

Offset-based (acceptable for small, stable datasets):

json

GET /v1/users?page=2&per_page=20

{
  "data": [...],
  "pagination": {
    "page": 2,
    "per_page": 20,
    "total": 154,
    "total_pages": 8
  }
}

Versioning

Strategy: URL prefix versioning (most common, clearest)

/v1/users
/v2/users

When to bump version:

Removing a field or endpoint
Changing response structure (e.g., renaming fields)
Changing request/response semantics
Changing authentication requirements

When NOT to bump version:

Adding new fields (consumers should ignore unknown fields)
Adding new endpoints
Bug fixes that don't change API contract

GraphQL Considerations

N+1 problem: Use DataLoader for batching
Auth at resolver level: Never in field-level middleware
Max query depth: Prevent runaway queries with depth limiting
Persisted queries: Use for production to reduce overhead
Nullable by default: Make fields nullable unless you're certain

graphql

type Query {
  user(id: ID!): User
}

type User {
  id: ID!
  name: String!
  email: String  # Nullable — might be hidden for privacy
  orders: [Order!]!  # Non-null list, but could be empty
}

API Documentation

OpenAPI 3.0 example:

yaml

openapi: "3.0.0"
paths:
  /v1/users:
    get:
      summary: List users
      parameters:
        - name: cursor
          in: query
          schema: { type: string }
        - name: limit
          in: query
          schema: { type: integer, minimum: 1, maximum: 100, default: 20 }
      responses:
        "200":
          description: Paginated list of users
          content:
            application/json:
              schema:
                type: object
                properties:
                  data:
                    type: array
                    items: { $ref: "#/components/schemas/User" }
                  pagination:
                    $ref: "#/components/schemas/Pagination"

Common Mistakes

Inconsistent error responses: Different endpoints returning different error shapes. Standardize on one format.
Exposing internal IDs: Use opaque public IDs (UUIDs) instead of auto-increment integers.
No pagination on list endpoints: Returning all records is a performance and reliability risk.
PUT for partial updates: Use PATCH. PUT should replace the entire resource.
Nesting too deep: /v1/users/{id}/orders/{oid}/items/{iid} — keep nesting to 2-3 levels max.
Returning 500 for validation errors: Validation failures are client errors — use 400/422.
No rate limiting headers: Tell clients their limits with headers. Don't just drop connections.
Synchronous long operations: If an operation takes >5 seconds, use 202 Accepted with a status URL.

Files

Just SKILL.md in categories/backend/api-design of cosmicstack-labs/mercury-agent-skills.

Open the folder on GitHubat commit 30392fb

Compare with similar skills

API Design next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

API Design compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
API Design this skillcosmicstack-labs/mercury-agent-skills	476	—	~1.9k	Automated safety check: Pass	MIT	1 mo ago
API DesignerJeffallan/claude-skills	12k	2 repos	~2k	Automated safety check: Pass	MIT	4 days ago
Nodejs Backend Patternsever-works/ever-works	158	18 repos	~4k	Automated safety check: Pass	AGPL-3.0	2 days ago
API Design Principlesjh941213/my-cc-harness	126	20 repos	~3.4k	Automated safety check: Pass	None	2 mo ago
API And Interface Designdzhalaevd/Donatello	135	9 repos	~2.6k	Automated safety check: Pass	Apache-2.0	4 days ago
Designing APIsCloudAI-X/claude-workflow-v2	1.4k	2 repos	~1.2k	Automated safety check: Pass	MIT	yesterday

Similar skills

API Designer
Jeffallan/claude-skills
Designs REST and GraphQL APIs from resource modeling to an OpenAPI 3.1 contract, with versioning, pagination and RFC 7807 error handling.
12k GitHub starsUsed in 2 repos~2k tokens
Backend & APIsAuto-check passed
Nodejs Backend Patterns
ever-works/ever-works
Build production-ready Node.js backend services with Express/Fastify, implementing middleware patterns, error handling, authentication, database integration, and API design best practices.
158 GitHub starsUsed in 18 repos~4k tokens
Backend & APIsAuto-check passed
API Design Principles
jh941213/my-cc-harness
REST 및 GraphQL API 설계 원칙 가이드. An agent skill from jh941213/my-cc-harness.
126 GitHub starsUsed in 20 repos~3.4k tokens
Backend & APIsAuto-check passed
API And Interface Design
dzhalaevd/Donatello
Guides stable API and interface design. An agent skill from dzhalaevd/Donatello.
135 GitHub starsUsed in 9 repos~2.6k tokens
Backend & APIsAuto-check passed
Designing APIs
CloudAI-X/claude-workflow-v2
Designs REST and GraphQL APIs including endpoints, error handling, versioning, and documentation.
1.4k GitHub starsUsed in 2 repos~1.2k tokens
Backend & APIsAuto-check passed
GraphQL Architect
Jeffallan/claude-skills
Designs GraphQL schemas and Apollo Federation graphs, with DataLoader resolvers, subscriptions, query complexity limits and caching.
12k GitHub starsUsed in 1 repo~1.3k tokens
Backend & APIsAuto-check passed

More from cosmicstack-labs/mercury-agent-skills

All 12 skills in this repo

Before You Build
cosmicstack-labs/mercury-agent-skills
Use this before implementing a product, feature, SaaS, AI app, or side project to score product risk and choose the smallest validation step.
476 GitHub stars~2.2k tokensUpdated 1 mo ago
Auto-check passed
Hyperframes CLI
cosmicstack-labs/mercury-agent-skills
HyperFrames CLI dev loop — project scaffolding, validation (lint/inspect), browser preview with live reload, MP4/WebM rendering, and environment troubleshooting (doctor, browser, info, upgrade).
476 GitHub stars~1.4k tokensUpdated 1 mo ago
Auto-check passed
Hyperframes Media
cosmicstack-labs/mercury-agent-skills
Asset preprocessing for HyperFrames compositions — local text-to-speech narration (Kokoro-82M, no API key), audio/video transcription (Whisper), and background removal for transparent overlays…
476 GitHub stars~1.7k tokensUpdated 1 mo ago
Auto-check passed
Agent Handoff Protocols
cosmicstack-labs/mercury-agent-skills
Design and implement agent-to-agent handoff protocols for multi-agent systems.
476 GitHub stars~4.1k tokensUpdated 1 mo ago
Auto-check passed
Agent Health Monitoring
cosmicstack-labs/mercury-agent-skills
Monitor AI agent health, detect anomalies, set up alerting, and maintain observability dashboards for production multi-agent systems.
476 GitHub stars~2.7k tokensUpdated 1 mo ago
Auto-check passed
Agent Task Delegation
cosmicstack-labs/mercury-agent-skills
Design and operate task delegation systems for multi-agent fleets.
476 GitHub stars~3.4k tokensUpdated 1 mo ago
Auto-check passed

Works with

GraphQL

Questions about API Design

What does API Design do?

REST and GraphQL API design principles, versioning, error handling, and documentation patterns. API Design is an agent skill from cosmicstack-labs/mercury-agent-skills.

When should I use API Design?

API Design fits situations like: tasks that involve API design; tasks that involve GraphQL.

How do I install API Design in Claude Code?

Run `npx skills add cosmicstack-labs/mercury-agent-skills --skill api-design -a claude-code`. Or copy the skill folder (categories/backend/api-design in cosmicstack-labs/mercury-agent-skills) into .claude/skills/api-design in your project. Claude Code loads it when a task matches its description.

How do I install API Design in Codex?

Run `npx skills add cosmicstack-labs/mercury-agent-skills --skill api-design -a codex`. Or copy the skill folder (categories/backend/api-design in cosmicstack-labs/mercury-agent-skills) into .agents/skills/api-design in your project. Codex loads it when a task matches its description.

Can I use API Design in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add cosmicstack-labs/mercury-agent-skills --skill api-design -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/api-design, .gemini/skills/api-design, .github/skills/api-design and .opencode/skills/api-design in your project.

What does API Design need to run?

SKILL.md names no scripts, command-line tools or credentials: API Design is instructions for the agent only.

Does API Design access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is API Design safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does API Design use?

API Design is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does API Design use?

About 1.9k tokens (SKILL.md is roughly 7.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to API Design?

Skills that share tags, products or a category with API Design: API Designer (Jeffallan/claude-skills, 12k stars), Nodejs Backend Patterns (ever-works/ever-works, 158 stars), API Design Principles (jh941213/my-cc-harness, 126 stars) and API And Interface Design (dzhalaevd/Donatello, 135 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains API Design?

cosmicstack-labs (a GitHub organization) maintains it in cosmicstack-labs/mercury-agent-skills, which has 476 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on August 25, 2026.

Source: cosmicstack-labs/mercury-agent-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install API Design

Facts

At a glance

What it does

When your agent uses it

Example prompts

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

API Design

Core Principles

1. Consistency Over Cleverness

2. Resources, Not Actions

3. Developer Experience First

4. Backward Compatibility

API Quality Scorecard

Actionable Guidance

RESTful URL Design

HTTP Methods and Status Codes

Error Response Format

Pagination

Versioning

GraphQL Considerations

API Documentation

Common Mistakes

Files

Compare with similar skills

Similar skills

More from cosmicstack-labs/mercury-agent-skills

Related

Questions about API Design