16,559 Open Skills

Free to get · One-click to use

✅ Keyword search & category filters
✅ Discussions & community interaction
✅ Version updates & multi-metric ranking
✅ Open SKILL.md standard

Import Skills

doubleuuser doubleuuser
from GitHub Tools & Productivity

rlm-workflow

Orchestrates the RLM repo workflow end-to-end with phase gates, locked artifacts, addenda, traceability, and automatic bootstrap/upsert of AGENTS/PLANS scaffolding. Trigger phrases: "Implement requirement <run-id>", "Run RLM Phase <N>", "resume requirement", "lock Phase <N>", "verify locks".

0 27 5 days ago · Uploaded Detail →
mjhoffmeister mjhoffmeister
from GitHub Tools & Productivity

demo

Bootstrap and navigate the spec-kit demo environment. Use this when asked to set up the demo, bootstrap the demo, jump to a phase, go to a phase, switch phases, or clean up a demo.

0 16 2 days ago · Uploaded Detail →
myrtlepn myrtlepn
from GitHub Tools & Productivity

accept

완료된 결과물을 최종 수락합니다 (Phase 3 → Phase 5). Worktree를 main에 머지하고 정리합니다. 사용자가 '수락', '머지', '최종 수락'을 말하거나 /mst:accept를 호출할 때 사용. 기본적으로 /mst:approve에서 자동 호출되며, workflow.auto_accept_result=false 시 수동 사용.

0 19 14 days ago · Uploaded Detail →
Larkin0302 Larkin0302
from GitHub Tools & Productivity

feishu-bitable

飞书多维表格的完整生命周期管理:从零搭建 + 日常 CRUD 操作。 **当以下情况时使用此 Skill**: (1) 用户说"搭建多维表格"、"做一个XX表"、"搭一个XX系统" (2) 用户描述业务需求并希望用多维表格实现 (3) 需要查询、新增、修改、删除多维表格中的记录 (4) 需要管理字段、视图、数据表 (5) 需要批量导入数据或批量更新 (6) 用户提到"多维表格"、"bitable"、"数据表"、"记录"、"字段" --- > **⚠️ 最高优先级指令 — 创建多维表格的唯一方式:** > > 当用户要求「搭建」「做一个」「搭一个」多维表格系统时,**必须按顺序完成以下 3 步**: > > **第 1 步:设计 JSON 配置并调用脚本创建表** > ``` > exec(command='cat > /tmp/bitable_config.json << ...') > exec(command='python3 ~/.openclaw/skills/feishu-bitable/scripts/create_bitable_template.py --config /tmp/bitable_config.json') > ``` > > **第 2 步:用脚本生成的 Markdown 创建配置文档(禁止跳过!禁止自己写内容!)** > ``` > exec(command='cat /tmp/bitable_config_doc.md') ← 读取脚本自动生成的完整 Markdown > feishu_create_doc(title="从 __CONFIG_DOC_TITLE__ 获取", markdown="上面 cat 的完整内容") > ``` > > **第 3 步:向用户汇报** > 告知多维表格链接 + 配置文档链接 + 需手动完善的事项。 > > **禁止使用 feishu_bitable_app 工具创建!禁止让用户手动创建!禁止跳过配置文档!禁止自己编写配置文档内容!** # 飞书多维表格技能 你是一个多维表格专家。覆盖**从零搭建**到**日常操作**的完整生命周期。 ## 架构 - **从零搭建** → 调用 Python 脚本(Phase 1-4,确定性执行,无默认字段/空行问题) - **日常操作** → 用飞书插件的 `feishu_bitable_*` 工具(查询、新增、修改、删除、批量操作) - **凭据** → 脚本自动从 OpenClaw 配置读取,与飞书插件共用同一应用 **判断用哪个路径:** - 用户要"搭建"/"做一个"/"搭一个" → Phase 1-4(脚本搭建) - 用户要"查记录"/"加一行"/"改字段"/"导入数据" → 日常 CRUD 操作 --- # 一、从零搭建(Phase 1-4) **⚠️ 禁止手动调用 feishu_bitable_* 工具创建表!必须用脚本!** 飞书 API 创建表时会自动附带默认字段(多行文本、单选、日期、附件)和空行,只有脚本能从源头避免。 ## Phase 1: 需求分析(内部思考,禁止向用户提问) > **⚠️ 铁律:禁止向用户提问!禁止问澄清问题!直接读模式库 → 设计 JSON → 搭建!** > > 用户说"搭建XX系统"时,你必须**立刻开始搭建**,不要问"你需要哪些模块"、"你的业务是什么"等问题。 > 用户可以在搭建完成后通过配置文档的「修改意见区」提出修改。 **内部分析(不输出给用户)**,用六问法快速拆解: | | 问题 | 决定 | |--|------|------| | Q1 | 涉及几类数据? | 建几张表 | | Q2 | 关联关系?(1:N / N:N) | 单向/双向关联 | | Q3 | 核心指标? | 公式/汇总 | | Q4 | 数据从哪来? | 录入方式 | | Q5 | 数据到哪去? | 输出方式 | | Q6 | 谁在哪个节点消费? | 视图和权限 | 读取实战模式库(详见 [references/system-patterns.md](references/system-patterns.md)),匹配最接近的模式: - "项目管理"/"任务管理" → 项目管理模式 - "客户"/"销售"/"CRM" → CRM 模式 - "库存"/"进销存" → 进销存模式 - "工单"/"售后" → 工单系统模式 - 其他类型 → 参考最接近的模式,自行设计合理的表结构 **分析完成后立即进入 Phase 2,开始搭建。** --- ## Phase 2: 设计 JSON + 调用脚本搭建 ### 2.1 设计 JSON 配置 ```json { "app_name": "系

0 13 10 days ago · Uploaded Detail →
AhmedHabiba AhmedHabiba
from GitHub Tools & Productivity

architecture-methodology

Enforces a 4-phase architecture design workflow by reading `.arch/state.json` on every request to gate responses by phase. Phase 1 extracts and validates requirements from PRDs; Phase 2 selects architecture patterns and establishes high-level structure; Phase 3 designs and accepts components sequentially; Phase 4 finalises and documents the solution. Use when discussing system design, solution architecture, PRD analysis, component design, technology selection, or architecture patterns — distinct from general coding help by its strict phase-gating, anti-pattern detection, and state-tracked component acceptance.

0 4 13 days ago · Uploaded Detail →
Fozu-lzwpattern Fozu-lzwpattern
from GitHub Content & Multimedia

agent-orchestration-20260309-lzw

One-Person Company (OPC) 编排技能 — 复杂任务的多 Agent 协作指挥中枢。 【优先触发条件 — 满足任意一条即应调用 OPC】 ① 任务需要多个步骤且步骤之间有依赖关系(如 策划→搭建→发布) ② 任务预计超过 50K tokens 或 10 分钟 ③ 任务涉及多个领域(调研+创作+开发+发布 等两个以上领域并存) ④ 任务需要多个专业角色分工(研究员、工程师、设计师等) ⑤ 任务明确包含"并行执行""多路线""团队协作"等关键词 ⑥ 用户提到"全链路""从头到尾""完整流程""做一个完整的X" 核心能力:Context Intake(用户模型读取+背景摄入)、任务分解、多角色编排、状态持久化、断点续传、用户模型自更新。 触发词(任意匹配): OPC、一人公司、多agent、编排、全链路、复杂项目、帮我做完整的、 需要多个步骤、并行执行、团队协作、策划+搭建+发布、研究项目、内容流水线 --- # OPC — One-Person Company 编排技能 v5.2 > 用户是老板,OpenClaw 是 CEO,Sub-agents 是专业员工。 > 用户只说"我要做 X",CEO 负责拆活儿、招人、盯进度、**亲自验收**、交结果。 --- ## 30 秒上手 ``` 1. 触发 OPC → Phase 0: Context Intake(理解背景目标,给出方案,等确认) 2. 确认后 → Phase 1: init 项目 + 任务分解 3. spawn Sub-agents → Phase 2: 注入角色卡 + 注册状态 4. 监控执行 → Phase 3: 主动检查 + trigger-evaluate + 汇报进度 5. 交付汇总 → Phase 4: cost 报告 + close 项目 ``` --- ## Phase 0:Context Intake(最重要,不可跳过) OPC 被触发后,**第一步必须理解背景,给出方案,征询确认**。 ### 必须明确的四个维度 ``` 【背景】业务场景是什么?有什么前置条件?新建还是继续? 【目标】交付物是什么?怎么判断"完成"? 【约束】截止时间?token 预算?平台限制? 【范围】从哪里开始到哪里结束?什么不在本次范围? ``` ### 方案输出格式(等用户确认才开始) ```markdown ## 📋 OPC 项目方案 **背景理解**:{一句话概括} **目标**:{交付物 + 成功标准} **约束**:{时间/预算/限制} **推进方案**: - 角色配置:{N 个角色,名称 + 主要职责} - 协作模式:{串行/并行/混合} - 预估总预算:~{N}K tokens - 预计耗时:~{N} 分钟 **确认后开始执行,是否有需要调整的地方?** ``` ### 确认轮次 | 复杂度 | 判断标准 | 轮次 | |--------|---------|------| | 简单 | ≤2 角色,单流水线 | **1 轮**(Phase 0+1 合并)| | 中等 | 3-5 角色,有并行 | **1 轮**(Phase 0+1 合并)| | 复杂 | >5 角色,>200K 预算 | **2 轮**(理解→方案分开)| 详细决策逻辑 → brain/core-flow.md --- ## 核心执行命令速查 ```bash # Phase 1 — 项目初始化 python3 engine/project_state.py init "项目名" python3 engine/project_state.py update-phase <pid> phase_1_planning # Phase 2 — agent 注册 python3 engine/project_state.py agent-start <pid> <label> '{"role":"角色名"}' # Phase 3 — 监控 python3 engine/project_state.py agent-complete <pid> <label> '{"output":"..."}' <tokens> python3 engine/project_state.py agent-fail <pid> <label> '{"error":"原因"}' python3 engine/project_state.py trigger-evaluate <pid> # 每轮循环必须调用 # 断点续传 python3 engine/project_state.py checkpoint <pid> <label> '{"completedSteps":[...],"nextStep

0 2 3 days ago · Uploaded Detail →

Skill File Structure Sample (Reference)

skill-sample/
├─ SKILL.md              ⭐ Required: skill entry doc (purpose / usage / examples / deps)
├─ manifest.sample.json  ⭐ Recommended: machine-readable metadata (index / validation / autofill)
├─ LICENSE.sample        ⭐ Recommended: license & scope (open source / restriction / commercial)
├─ scripts/
│  └─ example-run.py     ✅ Runnable example script for quick verification
├─ assets/
│  ├─ example-formatting-guide.md  🧩 Output conventions: layout / structure / style
│  └─ example-template.tex         🧩 Templates: quickly generate standardized output
└─ references/           🧩 Knowledge base: methods / guides / best practices
   ├─ example-ref-structure.md     🧩 Structure reference
   ├─ example-ref-analysis.md      🧩 Analysis reference
   └─ example-ref-visuals.md       🧩 Visual reference

More Agent Skills specs Anthropic docs: https://agentskills.io/home

SKILL.md Requirements

├─ ⭐ Required: YAML Frontmatter (must be at top)
│  ├─ ⭐ name                 : unique skill name, follow naming convention
│  └─ ⭐ description          : include trigger keywords for matching
│
├─ ✅ Optional: Frontmatter extension fields
│  ├─ ✅ license              : license identifier
│  ├─ ✅ compatibility        : runtime constraints when needed
│  ├─ ✅ metadata             : key-value fields (author/version/source_url...)
│  └─ 🧩 allowed-tools        : tool whitelist (experimental)
│
└─ ✅ Recommended: Markdown body (progressive disclosure)
   ├─ ✅ Overview / Purpose
   ├─ ✅ When to use
   ├─ ✅ Step-by-step
   ├─ ✅ Inputs / Outputs
   ├─ ✅ Examples
   ├─ 🧩 Files & References
   ├─ 🧩 Edge cases
   ├─ 🧩 Troubleshooting
   └─ 🧩 Safety notes

Why SkillWink?

Skill files are scattered across GitHub and communities, difficult to search, and hard to evaluate. SkillWink organizes open-source skills into a searchable, filterable library you can directly download and use.

We provide keyword search, version updates, multi-metric ranking (downloads / likes / comments / updates), and open SKILL.md standards. You can also discuss usage and improvements on skill detail pages.

Keyword Search Version Updates Multi-Metric Ranking Open Standard Discussion

Quick Start:

Import/download skills (.zip/.skill), then place locally:

~/.claude/skills/ (Claude Code)

~/.codex/skills/ (Codex CLI)

One SKILL.md can be reused across tools.

FAQ

Everything you need to know: what skills are, how they work, how to find/import them, and how to contribute.

1. What are Agent Skills?

A skill is a reusable capability package, usually including SKILL.md (purpose/IO/how-to) and optional scripts/templates/examples.

Think of it as a plugin playbook + resource bundle for AI assistants/toolchains.

2. How do Skills work?

Skills use progressive disclosure: load brief metadata first, load full docs only when needed, then execute by guidance.

This keeps agents lightweight while preserving enough context for complex tasks.

3. How can I quickly find the right skill?

Use these three together:

  • Semantic search: describe your goal in natural language.
  • Multi-filtering: category/tag/author/language/license.
  • Sort by downloads/likes/comments/updated to find higher-quality skills.

4. Which import methods are supported?

  • Upload archive: .zip / .skill (recommended)
  • Upload skills folder
  • Import from GitHub repository

Note: file size for all methods should be within 10MB.

5. How to use in Claude / Codex?

Typical paths (may vary by local setup):

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

One SKILL.md can usually be reused across tools.

6. Can one skill be shared across tools?

Yes. Most skills are standardized docs + assets, so they can be reused where format is supported.

Example: retrieval + writing + automation scripts as one workflow.

7. Are these skills safe to use?

Some skills come from public GitHub repositories and some are uploaded by SkillWink creators. Always review code before installing and own your security decisions.

8. Why does it not work after import?

Most common reasons:

  • Wrong folder path or nested one level too deep
  • Invalid/incomplete SKILL.md fields or format
  • Dependencies missing (Python/Node/CLI)
  • Tool has not reloaded skills yet

9. Does SkillWink include duplicates/low-quality skills?

We try to avoid that. Use ranking + comments to surface better skills:

  • Duplicate skills: compare differences (speed/stability/focus)
  • Low quality skills: regularly cleaned up