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。

加载中…

高分中文技能

eval-analyzer

majiayu000's avatarfrom majiayu000★ 5

分析评估基线结果、识别故障模式并生成可行的见解。在运行评估基线后或当用户要求分析评估结果、检查基准、调查故障或了解故障原因时使用。

command-audit

majiayu000's avatarfrom majiayu000★ 5

Validates command frontmatter, delegation patterns, simplicity guidelines, and documentation proportionality. Use when reviewing, auditing, analyzing, evaluating, improving, or fixing commands, validating official frontmatter (description, argument-hint, allowed-tools, model), checking delegation clarity or standalone prompts, assessing simplicity guidelines (6-15 simple, 25-80 documented), validating argument handling, or assessing documentation appropriateness. Distinguishes official Anthropic requirements from custom best practices. Also triggers when user asks about command best practices, whether a command should be a skill instead, or needs help with command structure.

audit-coordinator

majiayu000's avatarfrom majiayu000★ 5

Orchestrates comprehensive audits across multiple specialized auditors for Claude Code customizations and provides guidance on naming, organization, best practices, and troubleshooting. Use when: (1) Auditing - wants complete evaluation, multi-faceted analysis, coordinated audit reports, thorough validation, or asks to audit multiple components; (2) Guidance - asks "what should I name...", "how should I organize...", "best practices for...", troubleshooting issues, understanding evaluation criteria, or needs pre-deployment validation. Automatically determines which auditors to invoke (agent-audit, skill-audit, hook-audit, command-audit, output-style-audit, evaluator, test-runner) based on target type and compiles unified reports with consolidated recommendations.

skill-audit

majiayu000's avatarfrom majiayu000★ 5

审核技能的可发现性和触发效果。用于分析技能描述、检查触发短语覆盖率、验证渐进式披露、审查SKILL.md结构、确保技能可发现性、测试技能触发、改进技能描述、修复未被调用的技能、调试发现问题或评估技能是否会被适当调用。同时,当用户询问技能最佳实践、希望提高技能可发现性或需要帮助技能结构时也会触发。

determinism

ingpoc's avatarfrom ingpoc★ 5

用于代码验证结果而非LLM判断,版本化提示词带哈希,或确保代理行为可重复。加载用于任何关键验证。脚本返回布尔退出码,而非主观评估。提示词使用语义版本控制与SHA256验证。

skill-description-evaluator

majiayu000's avatarfrom majiayu000★ 5

Automates multi-model skill description analysis using sequential-thinking. Evaluates invocation likelihood (Sonnet 4.5, Haiku), authority level against competing prompts, semantic clarity, user request matching. Generates 0-100 ratings with actionable recommendations. Use when evaluating skill descriptions or saying 'evaluate skill', 'test skill description', 'analyze skill effectiveness'.

agent-tuning

majiayu000's avatarfrom majiayu000★ 5

优化ElevenLabs对话式AI代理以适用于房地产应用。在创建新代理、提高对话质量、选择声音、构建系统提示、配置代理参数或分析代理性能指标时使用。包括声音选择、模型调整、提示工程和A/B测试策略。

mcp-evaluation-skill

majiayu000's avatarfrom majiayu000★ 5

Comprehensive evaluation creation for MCP servers - question generation, answer verification, and XML formatting for agent usability testing

testing-skills-with-subagents

majiayu000's avatarfrom majiayu000★ 5

Use after writing a new skill and/or when testing existing skills, creating skill evaluations, or verifying skills work under pressure - applies TDD/RED-GREEN-REFACTOR to skill documentation by running baseline tests, measuring compliance, and closing rationalization loopholes

eval-review

majiayu000's avatarfrom majiayu000★ 5

Review LLM-generated diff classifications for the diffview eval system. Use when the user invokes this skill or pastes yanked case data from evalreview (containing "# Diff Classification Review" header). Evaluates whether classifications accurately help code reviewers, provides pass/fail verdict with detailed critique.

evaluating-rag

majiayu000's avatarfrom majiayu000★ 5

Evaluate RAG systems with hit rate, MRR, faithfulness metrics and compare retrieval strategies. Use when testing retrieval quality, generating evaluation datasets, comparing embeddings or retrievers, A/B testing, or measuring production RAG performance.

agentlightning-skill

majiayu000's avatarfrom majiayu000★ 5

闪电特工를 사용하여 AI 에동으로 최적화하는 방법을 제공합니다。

output-style-audit

majiayu000's avatarfrom majiayu000★ 5

Validates output-style persona definitions, behavior specifications, and keep-coding-instructions decisions. Use when auditing, reviewing, or improving output-styles, checking persona clarity, validating behavior concreteness, or verifying scope alignment (user vs project). Triggers when user asks about output-style best practices or needs help with persona definition.

procedure-refiner

majiayu000's avatarfrom majiayu000★ 5

Iteratively refine LA-Bench experimental procedures through validation and regeneration cycles. This skill should be used when improving generated procedures by ID, validating procedure quality against LA-Bench criteria, and managing the refinement loop between procedure-checker and procedure-generator skills. Triggered by requests to refine, improve, or validate LA-Bench procedures in output JSONL files.

clig-eval-prompt

samzong's avatarfrom samzong★ 5

根据clig.onev.dev指南生成简洁的中文DevOps CLI项目评估提示,包含权重、阈值和硬门限。用于用户请求创建或存储可重用CLI审查提示、评分标准或源自CLI设计指南的评估清单。

engine-superpower-profiling

majiayu000's avatarfrom majiayu000★ 5

Profile AI engine superpowers and capability boundaries.

neutral-target-baseline

majiayu000's avatarfrom majiayu000★ 5

建立中性基准指标以进行无偏评估。

agent-coverage-check

majiayu000's avatarfrom majiayu000★ 5

检查代理配置覆盖层级和阶段。用于确保代理系统全面覆盖。

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。