2,076 个开源Skills

免费获取 · 一键下载即用

✅ AI语义搜索 & 关键词搜索
✅ 在线讨论 & 社区互动
✅ 版本更新 & 多维排序
✅ SKILL.md 开放标准

导入技能

Linfee Linfee
from GitHub 工具与效率
  • 📄 SKILL.md
  • 📄 validate_release_post.py

release-post-verify

在临时目录中用 uvx 或 uv tool run 安装 specify-cn 的 main 分支最新提交,对源码声明支持的 agent 执行 init,并校验版本、中文化、模板完整性、agent 文件落点与 ai-skills 安装结果。用于本地发布后验收。

0 521 1天前 · 上传 详情页 →
getsentry getsentry
from GitHub 文档与知识管理
  • 📄 SKILL.md

agents-md

This skill should be used when the user asks to "create AGENTS.md", "update AGENTS.md", "maintain agent docs", "set up CLAUDE.md", or needs to keep agent instructions concise. Enforces research-backed best practices for minimal, high-signal agent documentation.

0 365 2天前 · 上传 详情页 →
DAAF-Contribution-Community DAAF-Contribution-Community
from GitHub 工具与效率
  • 📁 references/
  • 📄 SKILL.md

agent-authoring

Guide for creating new DAAF agent definition files with full ecosystem integration. Use when adding a new specialized agent, revising agent structure, or verifying agent integration completeness across documentation. --- # Agent Authoring Create new DAAF agents that conform to the canonical template and are fully wired into the system documentation for discoverability and usability. ## What This Skill Does - Guides creation of agent `.md` files conforming to `agent_reference/AGENT_TEMPLATE.md` (12 mandatory sections) - Ensures cross-agent consistency (standardized confidence model, Learning Signal, STOP format, etc.) - Provides a **complete integration checklist** covering every file that references agents across the codebase to ensure it is discoverable and its invocation patterns are well-understood by the system agents - Complements `skill-authoring`: this skill handles the behavioral protocol file; if the new agent also needs a companion skill, invoke `skill-authoring` separately ## Decision Tree: What Do You Need? ``` What are you doing? │ ├─ Creating a brand-new agent │ └─ Follow "New Agent Workflow" below │ ├─ Revising an existing agent to match the template │ └─ Read: references/template-walkthrough.md │ + agent_reference/AGENT_TEMPLATE.md (the canonical blueprint) │ ├─ Checking if an agent is fully integrated into the ecosystem │ └─ Read: references/integration-checklist.md │ ├─ Understanding what must be identical across all agents │ └─ Read: references/cross-agent-standards.md │ └─ Understanding the current agent landscape before adding to it └─ Read: agents/README.md (Agent Index + "Commonly Confused Pairs") ``` ## New Agent Workflow ### Phase 1: Design (before writing) Before beginning, you MUST have a clear, coherent, and compelling answer to each of the following questions: 1. **Define the role** in one sentence — what does this agent do and why does it exist? 2. **Identify pipeline stage(s)** — which stage(s) does it operate in, or i

0 140 19小时前 · 上传 详情页 →
kenneth-liao kenneth-liao
from GitHub 工具与效率
  • 📁 references/
  • 📄 SKILL.md

analyze-team-session

Use when reviewing an agent team session export for quality, when asked to "analyze this team session", "review my agent team run", "what went wrong with this session", "how can I improve my agent team usage", or when provided a markdown team session transcript and asked for feedback on agent teams effectiveness.

0 118 2天前 · 上传 详情页 →
yaleh yaleh
from GitHub 数据与AI
  • 📁 examples/
  • 📁 reference/
  • 📁 templates/
  • 📄 SKILL.md

Agent Prompt Evolution

Track and optimize agent specialization during methodology development. Use when agent specialization emerges (generic agents show >5x performance gap), multi-experiment comparison needed, or methodology transferability analysis required. Captures agent set evolution (Aₙ tracking), meta-agent evolution (Mₙ tracking), specialization decisions (when/why to create specialized agents), and reusability assessment (universal vs domain-specific vs task-specific). Enables systematic cross-experiment learning and optimized M₀ evolution. 2-3 hours overhead per experiment.

0 16 4小时前 · 上传 详情页 →
AlexAtmtit AlexAtmtit
from GitHub 开发与编程
  • 📁 references/
  • 📁 scripts/
  • 📄 SKILL.md

claude-agent-sdk

Reference for Claude Agent SDK (@anthropic-ai/claude-agent-sdk). MUST use when working with Claude Agent SDK, claude-agent-sdk package, or code that imports from @anthropic-ai/claude-agent-sdk. Covers the SDK's query API, tool configuration, hooks, subagents, MCP integration, and structured output. Do NOT use for generic agent development or other agent frameworks.

0 12 23小时前 · 上传 详情页 →
mindroom-ai mindroom-ai
from GitHub 工具与效率
  • 📄 examples.md
  • 📄 SKILL.md

agent-cli-dev

Spawns AI coding agents in isolated git worktrees. Use when the user asks to spawn or launch an agent, delegate a task to a separate agent, work in a separate worktree, or parallelize development across features.

0 12 2天前 · 上传 详情页 →
jnPiyush jnPiyush
from GitHub 工具与效率
  • 📁 references/
  • 📁 scripts/
  • 📄 SKILL.md

ai-agent-development

Build production-ready AI agents with Microsoft Foundry and Agent Framework. Use when creating AI agents, selecting LLM models, implementing agent orchestration, adding tracing/observability, or evaluating agent quality. Covers agent architecture, model selection, multi-agent workflows, and production deployment.

0 9 2天前 · 上传 详情页 →
sanity-io sanity-io
from GitHub 工具与效率
  • 📁 references/
  • 📄 SKILL.md

create-agent-with-sanity-context

Build AI agents with structured access to Sanity content via Agent Context. Use when setting up a Sanity-powered chatbot, connecting an AI assistant to Sanity content, or adding client-side tools to an agent. Covers Studio setup, agent implementation, and advanced patterns. Always use this skill when users mention building a chatbot with Sanity, creating an AI assistant for their content, setting up Agent Context MCP, integrating Sanity with Claude/GPT/any LLM, making content searchable by AI, implementing semantic search over Sanity data, or connecting their CMS to an AI agent.

0 4 1小时前 · 上传 详情页 →
Wh1isper Wh1isper
from GitHub 工具与效率
  • 📁 .github/
  • 📁 .vscode/
  • 📁 docs/
  • 📄 .env.example
  • 📄 .gitattributes
  • 📄 .gitignore

agent-builder

Build AI agents using ya-agent-sdk with Pydantic AI. Covers agent creation via create_agent(), toolset configuration, session persistence with ResumableState, subagent hierarchies, and browser automation. Use when creating agent applications, configuring custom tools, managing multi-turn sessions, setting up hierarchical agents, or implementing HITL approval flows.

0 4 16小时前 · 上传 详情页 →

Skills文件组织结构基本样例(仅作参考)

skill-sample/
├─ SKILL.md              ⭐ 必备:技能说明入口:用途 / 安装 / 用法 / 示例 / 依赖
├─ manifest.sample.json  ⭐ 推荐:机器可读元信息:用于索引 / 校验 / 自动填表
├─ LICENSE.sample        ⭐ 推荐:授权与使用范围:开源 / 限制 / 商用说明
├─ scripts/
│  └─ example-run.py     ✅ 可运行示例脚本:让用户导入后立刻验证“能用”
├─ assets/
│  ├─ example-formatting-guide.md  🧩 输出规范:统一排版 / 结构 / 风格
│  └─ example-template.tex         🧩 模板资源:报告/文档模板,快速生成标准产物
└─ references/           🧩 参考资料库:方法论 / 结构指南 / 最佳实践
   ├─ example-ref-structure.md     🧩 结构参考:章节框架 / 目录组织
   ├─ example-ref-analysis.md      🧩 分析参考:常用套路 / 指标口径
   └─ example-ref-visuals.md       🧩 视觉参考:图表规范 / 可视化建议

更多 Agent Skills 规范 详见Anthropic官方文档:https://agentskills.io/home

SKILL.md 内容要求

├─ ⭐ 必备:YAML Frontmatter(必须存在,放在文件最顶部)
│  ├─ ⭐ name                 :技能唯一名;须符合命名规则,并建议与目录名一致
│  └─ ⭐ description          :技能描述;建议包含触发关键词(便于检索/匹配)
│
├─ ✅ 可选:Frontmatter 扩展字段(规范允许,但非强制)
│  ├─ ✅ license              :许可证标识(也可配合单独 LICENSE 文件)
│  ├─ ✅ compatibility        :兼容性/运行环境要求(仅在确实有限制时写)
│  ├─ ✅ metadata             :任意键值对(如 author/version/source_url 等)
│  └─ 🧩 allowed-tools        :允许工具白名单(规范标注为 experimental)
│
└─ ✅ 推荐:Markdown 正文(自由格式,但建议按“渐进式披露”组织)
   ├─ ✅ Overview / Purpose   :一句话说明目标 + 不做什么(边界)
   ├─ ✅ When to use          :触发条件/适用场景(让模型/用户知道何时调用)
   ├─ ✅ Step-by-step         :步骤化流程(最好 3–6 步,保证可复现)
   ├─ ✅ Inputs / Outputs     :输入格式、输出格式、产物位置(文件/文本/JSON等)
   ├─ ✅ Examples             :至少 1 个可复制示例(越“能跑”越好)
   ├─ 🧩 Files & References   :引用assets/、references/、scripts/(相对路径)
   ├─ 🧩 Edge cases           :边界情况/限制(大文件、速率限制、失败回退)
   ├─ 🧩 Troubleshooting      :常见错误与解决(依赖缺失、路径不对、权限问题)
   └─ 🧩 Safety notes         :涉及联网/写文件/执行命令时给出提醒(建议写)

为什么选择 SkillWink?

在 GitHub 和各类社区里,技能文件分散、难检索、也难判断是否可靠。SkillWink 把开源技能集中整理成可搜索、可筛选、可直接下载使用的技能库,让你更快找到“正好能用”的那一个。并且支持在SkillWink上直接上传skills。

我们提供 AI 语义搜索 + 关键字检索,支持 版本更新与多维排序(下载/点赞/评论/更新),并为每个技能提供 SKILL.md 开放标准与来源信息。你还可以在详情页直接 评论讨论、交流用法与改进建议。

AI 语义搜索 关键词检索 版本更新 多维排序 开放标准 评论交流

快速上手:

支持下载与导入 skills(.zip/.skill),本地放置后即可生效:

~/.claude/skills/(Claude Code)

~/.codex/skills/(Codex CLI)

~/.gemini/skills/(Gemini CLI)

同一份 SKILL.md 跨平台通用。

常见问题解答(FAQ)

你需要了解的:技能是什么、怎么运行的、怎么找、怎么导入、怎么判断可信、怎么参与共建。

1,什么是Agent Skills?

这里的“skills(技能)”是一种可复用的任务能力包,通常包含 SKILL.md 说明(用途、输入输出、使用方法)以及可选的脚本/模板/示例文件。

你可以把它理解为:给 AI 助手或工具链用的“插件说明书 + 资源包”,可被反复安装与分享。

2,Skills是怎么运行的?

技能系统采用“渐进式披露”策略,高效管理上下文信息,具体流程如下:

发现阶段:系统启动时,智能体仅加载各技能的名称与简要描述——信息精简,足以判断其适用场景,避免冗余加载。

激活阶段:当任务需求与某技能描述匹配时,智能体才将对应的完整 SKILL.md 说明文档动态载入上下文。

执行阶段:智能体严格遵循文档指引执行操作,并按需调用关联文件或运行内置代码模块。

核心优势:该设计使智能体始终保持轻量高效,同时具备“按需扩展上下文”的能力,既保障响应速度,又确保复杂任务拥有充分执行依据。

3,我该怎么快速找到想要的技能?

推荐 3 种方式组合使用:

  • 语义搜索:用一句自然语言描述你想解决的问题;
  • 多维筛选:按分类/标签/作者/语言/许可证过滤;
  • 排序对比:按下载、点赞、评论、最近更新等维度排序,快速筛出“更可能好用”的技能。

4,SkillWink 支持哪些导入方式?

  • 上传归档文件导入:.zip / .skill 一键导入(推荐)
  • 上传skills文件夹
  • 从GitHub仓库导入

注:以上导入方式文件大小控制在10M之内。

5,在Claude / Codex 等系统中如何是使用?

常见路径如下(不同系统略有差异,以你本机为准):

  • Claude Code:~/.claude/skills/
  • Codex CLI:~/.codex/skills/

同一份 SKILL.md 通常可以跨工具复用。你在 SkillWink 导入后,也可以查看“放置指引/安装说明”。

6,一个技能能不能被多个工具一起用?

可以。很多技能本质是标准化说明 + 资源,只要目标工具支持读取该格式,就能共享使用。

比如:检索类技能 + 写作类技能 + 自动化脚本,形成“发现 → 处理 → 输出”的工作流。

7,这些skills使用安全吗?

一部分skills来源于公开的 GitHub 仓库。我们会筛掉低质量仓库(至少 2 星),并扫描基本质量指标,还有一部分是SkillWink平台的创作者独立上传的。作为使用者,在安装前应始终审查代码,对安全问题负责。

8,为什么我导入后“没有生效”?

最常见原因是这几类:

  • 放错目录(路径不对、层级多了一层)
  • SKILL.md 缺字段或格式不规范(名称/入口/依赖不完整)
  • 依赖未安装(Python/Node/CLI 工具缺失)
  • 工具未重新加载技能(某些环境需要重启/刷新)

9,SkillWink 会不会收录重复或低质量技能?

我们会尽量避免。你可以用 排序 + 评论 让“好用的”更靠前:

  • 重复技能:看差异点(更快/更稳定/更强主题能力)
  • 低质量技能:我们会定期清理低质量skills