Claude Skills 中文技能市场——为 Claude Code、Codex 与 Cursor 精选 Agent Skills
收录 90,000+ 开源 SKILL.md 工作流,提供中文解读、安全检测与高速下载,一行命令即可装到你的 AI 编程助手里。
高分中文技能
ln-627-observability-auditor
Observability audit worker (L3). Checks structured logging, health check endpoints, metrics collection, request tracing, log levels. Returns findings with severity, location, effort, recommendations.
ln-230-story-prioritizer
RICE prioritization per Story with market research. Generates consolidated prioritization table in docs/market/[epic-slug]/prioritization.md. L2 worker called after ln-220.
ln-510-test-planner
Plans Story test task by Risk-Based Testing after manual testing. Calculates priorities, selects E2E/Integration/Unit, delegates to ln-301-task-creator. Invoked by ln-500-story-quality-gate.
ln-300-task-coordinator
Orchestrates task operations. Analyzes Story, builds optimal plan (1-6 implementation tasks), delegates to ln-301-task-creator (CREATE/ADD) or ln-302-task-replanner (REPLAN). Auto-discovers team ID.
ln-600-docs-auditor
Audit project documentation quality across 6 categories (Hierarchy, SSOT, Compactness, Requirements, Actuality, Legacy). Use when documentation needs quality review, after major doc updates, or as part of ln-100-documents-pipeline. Outputs Compliance Score X/10 per category + Findings + Recommended Actions.
ln-610-code-comments-auditor
Audit code comments and docstrings quality across 6 categories (WHY-not-WHAT, Density, Forbidden Content, Docstrings, Actuality, Legacy). Use when code needs comment review, after major refactoring, or as part of ln-100-documents-pipeline. Outputs Compliance Score X/10 per category + Findings + Recommended Actions.
ln-002-best-practices-researcher
Research best practices via MCP Ref/Context7 and create documentation (guide/manual/ADR). Single research, multiple output types.
ln-401-task-executor
Executes implementation tasks (Todo -> In Progress -> To Review). Follows KISS/YAGNI, guides, quality checks. Not for test tasks.
ln-635-test-isolation-auditor
Test Isolation + Anti-Patterns audit worker (L3). Checks isolation (APIs/DB/FS/Time/Random/Network), determinism (flaky, order-dependent), and 6 anti-patterns.
ln-625-dependencies-auditor
Dependencies and reuse audit worker (L3). Checks outdated packages, unused dependencies, reinvented wheels, custom implementations of standard library features. Returns findings with severity, location, effort, recommendations.
ln-628-concurrency-auditor
Concurrency audit worker (L3). Checks race conditions, missing async/await, resource contention, thread safety, deadlock potential. Returns findings with severity, location, effort, recommendations.
ln-221-story-creator
Creates Stories from IDEAL plan (CREATE) or appends user-requested Stories (ADD). Generates 8-section documents, validates INVEST, creates in Linear. Invoked by ln-220.
ln-301-task-creator
Creates ALL task types (implementation, refactoring, test). Generates task documents from templates, validates type rules, creates in Linear, updates kanban. Invoked by orchestrators.
ln-632-test-e2e-priority-auditor
E2E Critical Coverage audit worker (L3). Validates E2E coverage for critical paths (Money 20+, Security 20+, Data 15+). Pure risk-based - no pyramid percentages.
ln-631-test-business-logic-auditor
Business Logic Focus audit worker (L3). Detects tests that validate framework/library behavior (Prisma, Express, bcrypt, JWT, axios, React hooks) instead of OUR code. Returns findings with REMOVE decisions.
ln-501-code-quality-checker
Worker that checks DRY/KISS/YAGNI/architecture/guide compliance for Done implementation tasks. Reports issues; does not change statuses or create tasks.
ln-310-story-validator
This skill should be used to validate and auto-fix Stories/Tasks against 2025 standards. Penalty Points system (goal = 0), delegates to ln-002 for documentation, Plan Mode support. Auto-discovers team/config.
ln-001-standards-researcher
通过MCP参考研究标准/模式,为故事技术笔记子节生成标准研究。可重复使用的工人。
常见问题
什么是 Claude Skills(Agent Skills)?
Skills 是一种标准化的 SKILL.md 指令包——把「何时触发、如何执行、使用哪些工具」写成结构化工作流,装入 Claude Code、Codex、Cursor 等 AI 编程助手后,Agent 遇到对应任务会自动调用,效果远好于每次手写提示词。
装了 Skill 之后怎么使用?
安装后无需手动调用:直接在 Claude Code / Cursor 里描述你的任务(如「帮我做 PR 代码审查」),Agent 检测到匹配的技能后会自动加载对应 SKILL.md 并按其流程执行。也可以在对话中显式要求「使用 xx skill」。
国内如何高速下载安装?
本站在 Cloudflare R2 托管了全部技能 ZIP 离线包,无需直连 GitHub:在详情页点击「Download ZIP」,或用 `npx skills add <owner/repo>` 一键安装;也可以复制 curl 命令直接解压到 ~/.claude/skills 目录。