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

git-safety-guard

terraphim's avatarfrom terraphim

在执行前阻止破坏性的 git 和文件系统命令。防止 git checkout --、git reset --hard、rm -rf 和类似的破坏性操作意外丢失未提交的工作。作为具有故障打开语义的 Claude Code PreToolUse 挂钩。

writing-rules

erikpr1994's avatarfrom erikpr1994

Use when creating or updating rules in CLAUDE.md, settings, or rule files. Covers confidence thresholds and false positive prevention.

oe-security-prompt-injection

shami-ah's avatarfrom shami-ah

Maintain and extend prompt-injection defenses. Use when adding new user-input surfaces, changing prompt templates, or when a new injection pattern is observed; run the security regression suite and add a minimal new test case.

worktree-policy

ekson73's avatarfrom ekson73

Enforce mandatory git worktree usage for multi-agent file modifications

workflow-enforcement

chkim-su's avatarfrom chkim-su

Protocol-based workflow enforcement with validation dependencies and anti-bypass protection

skill-resiliency

m31uk3's avatarfrom m31uk3

This skill should be used when the user asks to "add resiliency to a skill", "make this skill more robust", "improve error handling", "add validation mechanisms", "create self-correcting behavior", or discusses determinism, robustness, error correction, or homeostatic patterns in Agent Skills. Applies biological resiliency principles from Michael Levin's work to Agent Skill design.

amp-permissions

thurstonsand's avatarfrom thurstonsand

配置Amp权限 -- 允许、拒绝或请求在Amp中使用工具。通过短语如“拒绝使用此工具”、“我想修改工具权限”或“更改Amp权限”激活。

hook-development

cityfish91159's avatarfrom cityfish91159

当用户请求“创建钩子”、“添加PreToolUse/PostToolUse/Stop钩子”、“验证工具使用”、“实现基于提示的钩子”、“使用${CLAUDE_PLUGIN_ROOT}”、“设置事件驱动自动化”、“阻止危险命令”或提及钩子事件(PreToolUse、PostToolUse、Stop、SubagentStop、SessionStart、SessionEnd、UserPromptSubmit、PreCompact、Notification)时使用此技能。提供创建和实现Claude代码插件钩子的全面指导,重点在于高级基于提示的钩子API。

readathon-database-safety

stevensouza's avatarfrom stevensouza

Warn and protect against dangerous database operations on production database in the readathon project

approval-gate

takemo101's avatarfrom takemo101

ワークフローの重要なフェーズ移行前にユーザーの明示的な承認を必要とする承認ゲートの共通フォーマットとパターンを定義

git-safety-guard

stars-end's avatarfrom stars-end

为Claude Code安装Git安全钩子,防止破坏性的Git和文件系统命令。阻止由'git checkout --'、'git reset --hard'、'git clean -f'、'git push --force'和'rm -rf'等命令导致的意外数据丢失。使用此技能为新或现有仓库或全局代理设置安全轨道。

constitution

acornsoft's avatarfrom acornsoft

Load and confirm core principles, guardrails, and project context for MacroFlow sessions.

defense-in-depth

ChunkyTortoise's avatarfrom ChunkyTortoise

This skill should be used when implementing "multi-layer validation", "comprehensive error handling", "input sanitization", "security testing", "data validation layers", "fault tolerance", or when building robust systems with multiple validation checkpoints.

approval-workflow

maneeshanif's avatarfrom maneeshanif

Manages Human-in-the-Loop (HITL) approval workflows for sensitive actions. Use when creating approval requests, processing approved items, or implementing safety controls for autonomous actions.

ai-output-validation

Youngger9765's avatarfrom Youngger9765

Ensures all AI-generated output fields have proper validation.Auto-activates on "AI 輸出", "LLM", "Gemini", "GPT", "truncate", "截斷" keywords.Lesson learned: 2026-01-08 Quick Feedback, Report, Deep Analyze truncation bugs.

following-plans

tobyhede's avatarfrom tobyhede

算法决策树,用于确定何时严格遵循计划与何时报告“已停止” - 防止范围蔓延和未经授权的偏差。

hook-development

Kabilan108's avatarfrom Kabilan108

This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.

fpf-skillverification-verify-behavior

venikman's avatarfrom venikman

Verifies that an execution trace complies with the FPF Behavioral Specification.

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。