API 开发
API 设计、REST 与 GraphQL
data-client-rest-setup
reactive
Set up @data-client/rest for REST APIs. Creates custom RestEndpoint base class with common behaviors (auth, urlPrefix, error handling). Use after data-client-setup detects REST patterns.
data-client-graphql-setup
reactive
Set up @data-client/graphql for GraphQL APIs. Configures GQLEndpoint with auth and custom options. Use after data-client-setup detects GraphQL patterns.
parallel-execution
CloudAI-X
Patterns for parallel subagent execution using Task tool with run_in_background. Use when coordinating multiple independent tasks, spawning dynamic subagents, or implementing features that can be parallelized.
codebase-context-extractor
lofcz
This skill provides a comprehensive context extraction system for large codebases. It intelligently analyzes code structure, dependencies, and relationships to extract relevant context for understanding, debugging, or modifying code.
atlassian-reader
bitwarden
Reads Jira issues, epics, stories, sprints, boards, and Confluence pages from Atlassian Cloud into context via READ-ONLY scoped API tokens and curl commands. Use when the user mentions a Jira ticket (e.g. PROJ-123), references a Confluence page or URL, asks about sprint status, needs epic child stories, or wants to review linked documents for a Jira issue.
multi-tenant-platform-architecture
mblode
Provides architecture guidance for multi-tenant platforms on Cloudflare or Vercel. Use when defining domain strategy, tenant identification, isolation, routing, custom domains, and plan/limit mapping.
autonomous-skill
feiskyer
'Use when user wants to execute long-running tasks that require multiple sessions to complete. This skill manages task decomposition, progress tracking, and autonomous execution using Claude Code headless mode with auto-continuation. Trigger phrases: "autonomous", "long-running task", "multi-session", "自主执行", "长时任务", "autonomous skill".'
SKILL.md — Agent Guide for tool-eval-bench
SeraphimSerapis
Use --dry-run to preview — before committing to a long run, check which scenarios would execute.
langfuse
langfuse
Interact with Langfuse and access its documentation. Use when needing to (1) query or modify Langfuse data programmatically via the CLI — traces, prompts, datasets, scores, sessions, and any other API resource, (2) look up Langfuse documentation, concepts, integration guides, or SDK usage, or (3) understand how any Langfuse feature works. This skill covers CLI-based API access (via npx) and multiple documentation retrieval methods.
designing-architecture
CloudAI-X
Designs software architecture and selects appropriate patterns for projects. Use when designing systems, choosing architecture patterns, structuring projects, making technical decisions, or when asked about microservices, monoliths, or architectural approaches.
github-pr-inline-reply
Azure-Samples
Reply to inline PR review comments on GitHub pull requests using the GitHub API. Use this skill when you need to respond to individual review comments on a PR, acknowledge feedback, or mark comments as resolved by posting direct replies to comment threads.
baoyu-imagine
JimLiu
AI image generation with OpenAI GPT Image 2, Azure OpenAI, Google, OpenRouter, DashScope, Z.AI GLM-Image, MiniMax, Jimeng, Seedream and Replicate APIs. Supports text-to-image, reference images, aspect ratios, and batch generation from saved prompt files. Sequential by default; use batch parallel generation when the user already has multiple prompts or wants stable multi-image throughput. Use when user asks to generate, create, or draw images.
arrow-typed-errors
alexandru
Kotlin + Arrow typed error handling using Raise DSL and wrapper types (Either/Option/Ior/Result/nullable), including validation with accumulation, interop with exceptions, and custom error wrappers. Use for designing or refactoring error modeling, converting exception-based flows, building smart constructors, accumulating validation errors, or integrating Outcome/Progress-style wrappers with Arrow.
erpnext-syntax-whitelisted
OpenAEC-Foundation
"Deterministic syntax for Frappe Whitelisted Methods (Python API endpoints) for v14/v15/v16. Use when Claude needs to generate code for API functions, REST endpoints, @frappe.whitelist() decorator, frappe.call() or frm.call() invocations, permission checks in APIs, error handling patterns, or when questions concern API structure, response formats, or client-server communication. Triggers: whitelisted, API endpoint, frappe.call, frm.call, REST API, @frappe.whitelist, allow_guest, API method."
brainstorm
boshu2
'Separate WHAT from HOW before planning. Clarify goals, explore approaches, capture structured design decisions. Triggers: brainstorm, explore idea, clarify goal, idea phase.'
openai-docs
boshu2
"Use when the user asks how to build with OpenAI products or APIs and needs up-to-date official documentation with citations (for example: Codex, Responses API, Chat Completions, Apps SDK, Agents SDK, Realtime, model capabilities or limits); prioritize OpenAI docs MCP tools and restrict any fallback browsing to official OpenAI domains."
vue-router-best-practices
antfu
"Vue Router 4 patterns, navigation guards, route params, and route-component lifecycle interactions."
unbrowse
unbrowse-ai
API-native agent browser powered by Kuri (Zig-native CDP, 464KB, ~3ms cold start). Unbrowse is the intelligence layer — learns internal APIs (shadow APIs) from real browsing traffic and progressively replaces browser calls with cached API routes (<200ms). Three paths: skill cache, shared route graph, or Kuri browser fallback. 3.6x mean speedup over Playwright across 94 domains. Full Kuri API surface exposed (snapshots, ref-based actions, HAR, cookies, DOM, screenshots). Free to capture and index; agents earn from mining routes for other agents.
django-tdd
xu-xiang
使用 pytest-django、测试驱动开发（TDD）方法论、factory_boy、Mock 模拟、覆盖率统计以及 Django REST Framework API 测试的 Django 测试策略。
golang-testing
xu-xiang
Go 测试模式，包括表格驱动测试、子测试、基准测试、模糊测试和测试覆盖率。遵循测试驱动开发（TDD）方法论及地道的 Go 语言实践。
项目指南技能（Project Guidelines Skill，示例）
xu-xiang
tdd-workflow/ - æµè¯é©±å¨å¼å (TDD) æ¹æ³è®º
springboot-patterns
xu-xiang
Spring Boot 架构模式、REST API 设计、分层服务、数据访问、缓存、异步处理和日志记录。适用于 Java Spring Boot 后端开发工作。
coding-standards
xu-xiang
适用于 TypeScript、JavaScript、React 和 Node.js 开发的通用编码标准、最佳实践和模式。
tdd-workflow
xu-xiang
Use this skill when writing new features, fixing bugs, or refactoring code. Enforces test-driven development with 80%+ coverage including unit, integration, and E2E tests.