agentsclimarketplace
Sign in

Shelves Data & backend

APIs & services

1,766 rows from 452 repositories

Building the endpoint rather than designing it.

What APIs & services skills agree on

449 skill files read, by 448 of the 471 authors on this shelf whose files we hold, 2026-09-06

The middle one of the 73 measured here is ~1.7k tokens long, counted with cl100k_base

Counted by distinct author, so one author publishing three of these counts once. Where a claim sits in fewer files than authors, that is said: a claim held by forty authors across three files is one file people copied, not forty people who agreed. Near-identical wordings are grouped and the other wordings are shown, so the grouping is yours to check.

What they tell the agent to do

  1. Use HTTP status codes semantically25 of 448 in 11 filesalso worded as Return semantic HTTP status codes; use standard HTTP status codes
  2. Return 201 with a Location header on create24 of 448 in 9 filesalso worded as Return 201 with Location header on create; Return 201 with Location header for created resources
  3. Name resources plural, lowercase, kebab-case23 of 448 in 9 filesalso worded as Name resources as plural kebab-case nouns; Name resources plural, lowercase, kebab-case without verbs
  4. Configure rate limiting with limit headers22 of 448 in 8 filesalso worded as Configure rate limiting with X-RateLimit headers; Configure rate limiting with standard headers
  5. Paginate list endpoints with cursor or offset21 of 448 in 10 filesalso worded as Paginate all list endpoints; Use cursor-based pagination instead of offset
  6. Version APIs in the URL path21 of 448 in 11 filesalso worded as Version APIs in URL path starting at v1; Use URL path versioning for public APIs
  7. Validate request input with a schema21 of 448 in 7 filesalso worded as Validate input with a schema; Generate request validation schema
  8. Add pagination to all list endpoints18 of 448 in 15 filesalso worded as Paginate every list endpoint; Implement pagination on all list endpoints
  9. Match HTTP method to the operation12 of 448 in 6 filesalso worded as match HTTP methods to operation semantics; Use correct HTTP method per operation
  10. Limit query depth and complexity12 of 448 in 7 filesalso worded as Add query complexity and depth limits; Configure query depth and complexity limits
  11. Name resources with plural nouns11 of 448also worded as name resources as plural nouns; Identify resources with plural nouns in URLs
  12. Return errors with machine-readable codes10 of 448 in 5 filesalso worded as Return one consistent error shape with machine-readable codes; Return machine-readable error codes, not messages
  13. Require authentication on every endpoint10 of 448 in 6 filesalso worded as require authentication or mark endpoints public; Require authentication or explicitly mark endpoints public
  14. Create DataLoader loaders per request10 of 448 in 7 filesalso worded as Create new DataLoader instances per request; Create DataLoaders per request, not globally
  15. Retry on 429 using the Retry-After header10 of 448also worded as Honor Retry-After on 429; Surface 429 with Retry-After

What they tell it not to do

  1. Don't put verbs in resource URLs38 of 448 in 24 filesalso worded as Never use verbs in URLs; Never use verbs in resource URLs
  2. Don't return 200 for error cases37 of 448 in 23 filesalso worded as Never return 200 for errors or created resources; Don't return 200 for every response
  3. Don't expose internal error details26 of 448 in 13 filesalso worded as Never expose stack traces, SQL errors, or internal details; Never expose internal details in error responses
  4. Don't maintain more than two active versions15 of 448 in 4 filesalso worded as keep more than two active API versions; Do not maintain multiple versions simultaneously
  5. Never skip validation11 of 448 in 6 filesalso worded as Never skip validation; Do not skip validation before activation
  6. Never hardcode credentials11 of 448 in 7 filesalso worded as never hardcode credentials; Do not hardcode credentials in parameters
  7. Never expose internal details in responses10 of 448 in 8 filesalso worded as Never expose internal details in responses; Do not expose internal details
  8. Never use wildcard CORS origins in production10 of 448 in 9 filesalso worded as do not allow wildcard CORS origins together with credentials; Never use wildcard CORS in production
  9. Don't return 500 for validation errors9 of 448 in 5 filesalso worded as Never return 500 for validation errors; return 500 for validation errors
  10. Never use blocking calls in async routes9 of 448 in 6 filesalso worded as Never use blocking calls in async routes; Do not call requests in an async route

What they expect to be installed

  1. curl62 of 448
  2. Pydantic35 of 448 in 20 files
  3. Zod32 of 448 in 18 files
  4. pytest30 of 448 in 29 files
  5. DataLoader27 of 448 in 22 files
  6. FastAPI27 of 448 in 26 files
  7. grep23 of 448 in 22 files
  8. jq23 of 448 in 21 files
  9. OpenAPI/Swagger21 of 448 in 7 files
  10. httpx20 of 448 in 19 files

What they ask it to produce

  1. Updated OpenAPI/Swagger specification22 of 448 in 8 filesalso worded as Updated OpenAPI/Swagger spec; OpenAPI/Swagger documentation
  2. OpenAPI specification12 of 448also worded as OpenAPI 3.1 specification; OpenAPI spec
  3. Typed GraphQL schema10 of 448 in 8 filesalso worded as GraphQL schema; GraphQL schema file
  4. Pydantic request and response schemas9 of 448 in 8 filesalso worded as Separate Pydantic create, update, and response schemas; Pydantic request and response models
  5. API documentation8 of 448also worded as API documentation comment; OpenAPI documentation
  6. Standardized error response bodies7 of 448 in 2 files
  7. Per-request DataLoader loaders7 of 448 in 4 filesalso worded as Per-request DataLoader instances in context; Per-request DataLoader middleware
  8. Webhook receiver endpoint with signature verification7 of 448also worded as Webhook receiver endpoint implementation; signature-verifying webhook receiver

When APIs & services authors say to reach for one

The situations these authors wrote into their own files, counted out of the same 448 authors, with the skills that name each one

How APIs & services skills are built

1,570 skill directories by 421 authors, read from their repositories’ own file trees 2026-08-05

The middle bundle among those shipping files is 3 files, 19.4 KB beside SKILL.md

Counted by distinct author, same as above, so one author publishing forty template copies counts once. SKILL.md itself is not counted as a file, so a single-file skill is one where that file is the whole skill.

The shape

  1. SKILL.md is the whole skill166 of 421 authors, 849 of 1,570 skills
  2. files ship beside it255 of 421 authors, 721 of 1,570 skills
  3. executable scripts ship inside79 of 421 authors, 211 of 1,570 skills

The folders they converge on

  1. references/180 of 421 authors, 400 of 1,570 skills
  2. scripts/65 of 421 authors, 184 of 1,570 skills
  3. assets/36 of 421 authors, 75 of 1,570 skills
  4. evals/28 of 421 authors, 50 of 1,570 skills
  5. agents/22 of 421 authors, 40 of 1,570 skills
  6. examples/17 of 421 authors, 39 of 1,570 skills

  • Mcp server trello

    delorenj/mcp-server-trello/io.github.delorenj/mcp-server-trello MCP server

    432★ repo

    MCP server for Trello boards with rate limiting, type safety, and comprehensive API integration.

  • mockd

    getmockd/mockd/io.mockd/mockd MCP server

    141★ repo

    Multi-protocol API mock server: HTTP, GraphQL, gRPC, WebSocket, MQTT, SSE, SOAP.

  • Add backend

    ahpxex/open-dashboard/.claude/skills/add-backend Skill

    119★ repo

    A skill catalogue of 36 copy-ready admin UI shapes an AI agent installs and composes into a real back-office. Built on TanStack Start, Drizzle + better-auth, shadcn + Tailwind v4.

  • Goframe v2

    gogf/skills/skills/goframe-v2 Skill

    no license78★ repo

    GoFrame Agent Skills empowering AI to deeply understand GoFrame conventions and best practices, generating high-quality, production-ready code.

  • Api design

    proyecto26/system-design-skills/skills/api-design Skill

    46★ repo

    A divide-and-conquer wiki of system-design skills for Claude Code — reason about scalable systems, don't memorize architectures.

  • Crawl apis

    ea-toolkit/architecture-catalog/.claude/skills/crawl-apis Skill

    38★ repo

    Git-native architecture catalog — Markdown registry, schema-driven UI, AI-ready

  • Symfony api response

    aligundogdu/symfony-hexagonal-skill/skills/symfony-api-response Skill

    no license32★ repo

    Claude Code plugin that enforces hexagonal architecture (ports & adapters) in Symfony projects — with 10 auto-triggered skills, 2 review agents, and progressive refactoring support for existing codebases.

  • Bitrix24 agent

    vrtalex/bitrix24-skill/skills/bitrix24-agent Skill

    24★ repo

    Bitrix24 AI Agent skill: webhook/OAuth, events, retries, safety guardrails, and ops patterns

  • Api breaker

    Orizon-eu/claude-code-pentest/api-breaker Skill

    22★ repo

    6 Claude Code skills that automate the entire pentest lifecycle. From recon to exploit chains to bug bounty reports — just give it a domain. 43 scripts, zero dependencies, pure Python.

  • Authentication failures

    scholarly360/owasp-top10-web-skills/skills/authentication-failures Skill

    20★ repo

    Agent Skills for OWASP Top 10 Application Security Risks (https://owasp.org/Top10/2025/)

  • Paymob integration

    PaymobAccept/Paymob-AI-Integration-Skill/skills/paymob-integration Skill

    19★ repo

    Official Paymob payment integration skill for Claude Code — Intention API, HMAC, mobile wallets, BNPLs, Apple Pay across Node.js, Python, PHP, Flutter and more

  • Api security

    ShieldNet-360/secure-vibe/dist/agent-skills/.agents/skills/api-security Skill

    15★ repo

    SecureVibe — prevention-first security for AI-written code. Signed SKILL.md knowledge that makes AI coding assistants write secure code at generation time, plus a deterministic CI gate. Offline · keyless · Ed25519-signed. By ShieldNet360.

  • Fastapi address review

    steph-dove/klaussy-agents/examples/fastapi/.agents/skills/fastapi-address-review Skill

    13★ repo

    A multi-agent context, rules, and hooks boilerplate generator. With a single command, it scaffolds conventions, namespaced skills, stack-appropriate settings, and interactive guardrails for seven major AI coding environments, matching each agent's native file formats and capability profiles.

  • Sota api design

    martinholovsky/SOTA-skills/skills/sota-api-design Skill

    12★ repo

    State-of-the-Art (2026) AI/LLM engineering skills/agents for building and auditing software — 40+ domain & language skills, BUILD/AUDIT modes, audit checklists.

  • 302AI API Integration Skill

    302ai/302AI-API-Integration-Skill Skill

    10★

    Instantly integrate 1400+ AI APIs into your code - The ultimate Claude Code skill for seamless 302.AI API integration

  • Graphql federation

    wundergraph/graphql-federation-skill/skills/graphql-federation Skill

    7★ repo

    Agentic Coding Skill for GraphQL Federation / Apollo Federation

  • Microtech graphql

    microtech-gmbh/microtech-skills/microtech-graphql Skill

    6★ repo

    KI Skills für das microtech ERP-System. GraphQL-Queries, Vorgangsverwaltung und mehr - optimiert für die Nutzung mit GraphQL MCP-Servern

  • Add Admin API Endpoint

    HK-hub/AgentSkills/Add Admin API Endpoint Skill

    6★ repo

    精选 Claude Code , Open Code等Agent Skills 合集，覆盖 Agent/Skill 工程化、后端架构、事件驱动、CI/CD、前端设计、文档办公自动化与可视化创作

  • Fastapi

    DongDuong2001/pudo-code-system/skills/backend/fastapi Skill

    5★ repo

    Modular, scalable, automated development intelligence.

  • Api

    teamtinvio/jaz-ai/.agents/skills/api Skill

    5★ repo

    Complete agent stack for Jaz. Plugins, Skills, MCP tools, and CLI for Claude Code, Cowork, Codex, Copilot, Cursor, and more.

  • Nuclear bug fix

    ajaydata-vision/nuclear-bug-fix- Skill

    no license4★

    Single shot Bug Fixing Skill for AI Agents

  • Setup backend stack

    WESTsyre21/setup-backend-stack Skill

    4★

    This skill bootstraps a local Node.js backend development stack with Docker, PostgreSQL, and an ORM (Prisma or Sequelize). It is designed to help the next user quickly install, configure, and run the skill in a Claude-compatible skill directory.

  • Universal connector mcp

    TeodorMCP/universal-connector-mcp/io.github.TeodorMCP/universal-connector-mcp MCP server

    4★ repo

    Security-first MCP server that connects any OpenAPI, GraphQL, gRPC or SOAP API to AI agents.

  • Yield xyz agentkit builder

    stakekit/agentkit/plugins/yield-xyz-agentkit-builder/skills/yield-xyz-agentkit-builder Skill

    3★ repo

    The official tooling for Yield.xyz AgentKit — a Claude Code plugin, standalone skills, and connection guides for the Yield.xyz AgentKit MCP Server.

  • Api design

    iwritec0de/app-dev/skills/api-design Skill

    3★ repo

    Full-stack Next.js development plugin for Claude Code

  • Api designer

    FutureJJ/claude-skills/skills/api-designer Skill

    3★ repo

    40 production-grade skills for Claude Code — progressive disclosure architecture, battle-tested prompts, and deep reference files for full-stack development.

  • Api review

    MuhammedZohaib/patchman/plugins/patchman/skills/api-review Skill

    2★ repo

    Defensive AI security audit skill for Claude and Codex. Reviews codebases and web apps for OWASP Top 10, auth and authorization flaws, business logic bugs, tenant isolation gaps, insecure defaults, secret leaks, and ORM or N+1 query issues, then produces clear remediation guidance.

  • Api security

    Rootx202/appsec-skills/api-security Skill

    no license2★ repo

    AppSec Skills — 15 plug-and-play Claude Code security skills that audit, harden, and fix any website or app before you ship it. OWASP Top 10, auth, API, database, frontend, backend, cloud, dependencies, secrets, and pentest-style checks — all defensive, all evidence-based.

  • Api sculptor

    mturac/hermes-supercode-skills/skills/api-sculptor Skill

    2★ repo

    ⚡ 13 production-grade skills for Claude Code · db-whisperer, auth-architect, obs-guardian + 10 more · Zero config · MIT

  • Dsc endpoint help

    j-256/claude-code-skills/skills/dsc-endpoint-help Skill

    2★ repo

    Some useful Claude Code Skills

  • Asc api

    raydeveloperF/App-Store-Connect-release-kit/skills/asc-api Skill

    2★ repo

    A Claude Code and Codex plugin with Agent Skills for localized App Store Connect release workflows

  • Action1

    wyre-technology/action1-mcp/io.github.wyre-technology/action1-mcp MCP server

    2★ repo

    Action1 MCP server — endpoint inventory, patch visibility, and policy automation via REST API.

  • Api design review

    Noorkhalel/saas-ai-skills/skills/api-design-review Skill

    1★ repo

    Open-source AI Skills library for building, improving, and scaling modern SaaS applications.

  • Tokenlab api integration

    hedging8563/tokenlab-skills/skills/tokenlab-api-integration Skill

    1★ repo

    Agent skills for TokenLab API integration, model picking, native endpoints, cost routing, and OpenAI-compatible migration

  • Formcarry

    hicay/claude-code-skills/formcarry Skill

    no license1★ repo

    Public repository for Claude Code Agent Skills

  • Api design

    SkillMedev/full-stack-web-dev/skills/api-design Skill

    1★ repo

    Next.js to Postgres — build and ship a modern web app end to end.

  • Fastbound api

    FastBound/skills/skills/fastbound-api Skill

    no license1★ repo

    Official FastBound Agent Skills for AI coding assistants — integrate with FastBound's products and APIs.

  • Api design

    simanam/theaiteam/team/skills/architecture/api-design Skill

    no license1★ repo

    Reusable, provider-agnostic AI team. Drop a project brief, get end-to-end delivery. 12 role agents + 112 skills + orchestrator + self-improvement. Works with Claude Code, Codex, or Gemini.

  • Dianpo

    jyuwaaw/dianpo-skill/skills/dianpo Skill

    1★ repo

    Claude Code skill that explains the mental model behind any technical mechanism — who issues the token, who verifies whom, and why it's designed that way. 点破技术机制背后的信任拓扑。

  • Api design

    SkillMedev/technical-writing-studio/skills/api-design Skill

    1★ repo

    Docs people actually read — READMEs, guides, changelogs, and specs.

  • Integrate hookmyapp

    hookmyapp/agent-skills/skills/integrate-hookmyapp Skill

    1★ repo

    Agent skills for WhatsApp integration with HookMyApp. Install: npx skills add hookmyapp/agent-skills

  • Api integration

    choutos/agent-skills-spec/examples/api-integration Skill

    1★ repo

    Open specification for packaging procedural knowledge for AI agents. Framework-agnostic SKILL.md format.

  • Fastapi clean

    fulit103/fastapi-clean Skill

    1★

    FastAPI clean architecture pragmatic skill — multi-agent (Cursor, Claude Code, Codex, OpenCode, Continue, Aider, Cline, Windsurf). Use cases + repositories + Celery 5.4 + PyMongo async + Clerk JWT + API keys SHA-256.

  • Sharp api design

    zhouhuijia/sharp-skills/skills/sharp-api-design Skill

    no license1★ repo

    AI Agent 品控规则合集。Stop AI slop — 六个模块，七平台兼容，一行命令安装。

  • Expect the unexpected

    008993368-yaz/expect-the-unexpected Skill

    1★

    Scenario-driven failure-mode analysis skill for AI coding agents (Cursor, Claude Code, Copilot, Codex)

  • Wolverine skill

    zetroot/wolverine-skill Skill

    1★

    AI-agent skill for building applications with WolverineFX framework

  • Skill

    mohamedzhioua/proofguard/deferred/api-contract-guard/skill Skill

    1★ repo

    Kill-tested guard skills for AI coding agents , self-invoking quality gates that catch AI failure modes in security, tests, docs, dependencies, and diffs before the agent says "done." Works with Claude Code, Codex, and Cursor.

  • Fastapi best practices

    dkmqflx/fastapi-best-practices-plugin/plugins/fastapi-best-practices/skills/fastapi-best-practices Skill

    1★ repo

    Claude Code plugin: FastAPI best practices (41 rules, 13 categories) grounded in the official FastAPI docs

  • Hookwarden — Webhook Integrity

    Hookwarden/hookwarden/io.github.Hookwarden/mcp MCP server

    1★ repo

    Webhook signature-verification audit. Stripe, GitHub, Shopify, Twilio +17. Local. Deterministic.

  • Grpc invoke mcp

    grulex/grpc-invoke-mcp/io.github.grulex/grpc-invoke-mcp MCP server

    1★ repo

    MCP server for describing and invoking gRPC methods

  • Tableau graphql mcp

    tdries/tableau-graphQL-mcp/io.github.tdries/tableau-graphql-mcp MCP server

    1★ repo

    Ask any Tableau lineage question, in any MCP client, through the Tableau Metadata API.

  • Fastapi app

    aneebbaig/app-starter-skills/plugins/app-starter/skills/fastapi-app Skill

    0★ repo

    Bootstrap skills for Next.js, Flutter, and FastAPI apps. Current packages, no deprecated APIs, consistent structure. Claude Code plugin + AGENTS.md.

  • Spring boot microservices

    gauravs19/spring-boot-microservices-skill/spring-boot-microservices Skill

    0★ repo

    Claude Code skill to design, scaffold, and review modern Java Spring Boot microservices (Spring Boot 4.x / Java 25 LTS). Installable as a plugin marketplace.

  • Smart API Skills

    jill6125/Smart-API-Skills Skill

    no license0★

    Complete integration reference for SmartAPI (Angel One's REST API for algorithmic trading). Use this skill whenever the user is building, debugging, or asking about Angel One SmartAPI integrations

  • Codex

    vivian254338489/agent-skills-openai-compatible-pack/skills/codex Skill

    0★ repo

    Original Claude skills, Codex skills, Cursor rules, Gemini instructions, and prompts for OpenAI-compatible base_url setup.

  • Api testing

    Marcdaou/claude-qa-suite/qa-suite/skills/api-testing Skill

    0★ repo

    Claude Code plugin marketplace: qa-suite — end-to-end QA (API, E2E, SEO, security, payments) for Next.js + Supabase + Stripe apps

  • Api design

    BTN101/claude-skill-pack/skills/engineering/api-design Skill

    0★ repo

    Claude skills organized into domain layers — engineering, product, founder/GTM, design, and documents

  • Spike first

    AllenShi100/spike-first Skill

    no license0★

    Spike First | 先打靶再造枪 - 抓取/集成任务的强制可行性闸门 Agent Skill：开工前 5 分钟探针验证最大未知点，连跑 3-5 次测成功率，不通过当场喊停

  • Nestjs

    iamursky/nestjs-skill/skills/nestjs Skill

    0★ repo

    Reference skill for NestJS — the progressive, TypeScript-first Node.js framework.

  • Api contract

    digitaldreams/tuhin/skills/api-contract Skill

    0★ repo

    My dev identity as a Claude Code plugin — a full Laravel team in a box: SDLC pipeline, task board, coding agents, and audit skills.

All 1,766 in the catalog