16,568 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

Composite Most Downloads Most Likes Most Comments Newest
AIPMAndy AIPMAndy
from GitHub Tools & Productivity
memory evolve.py python3

dna-memory

DNA 记忆系统 - 让 AI Agent 像人脑一样学习和成长。 三层记忆架构（工作/短期/长期）+ 主动遗忘 + 自动归纳 + 反思循环 + 记忆关联。 激活场景：用户提到"记忆"、"学习"、"进化"、"成长"、"记住"、"回顾"、"反思"。 --- # DNA Memory - DNA 记忆系统 > 让 Agent 不只是记住，而是真正学会。 ## 核心理念 人脑不是硬盘，不会无差别存储所有信息。人脑会： - **遗忘**不重要的 - **强化**反复出现的 - **归纳**零散信息为模式 - **反思**过去的成功和失败 DNA Memory 模拟这个过程，让 Agent 真正"进化"。 --- ## 三层记忆架构 ``` ┌─────────────────────────────────────────────────┐ │ 工作记忆 (Working Memory) │ │ - 当前会话的临时信息 │ │ - 会话结束后自动筛选 │ │ - 文件：memory/working.json │ └─────────────────────────────────────────────────┘ ↓ 筛选 ┌─────────────────────────────────────────────────┐ │ 短期记忆 (Short-term Memory) │ │ - 近7天的重要信息 │ │ - 带衰减权重，不访问会逐渐遗忘 │ │ - 文件：memory/short_term.json │ └─────────────────────────────────────────────────┘ ↓ 巩固 ┌─────────────────────────────────────────────────┐ │ 长期记忆 (Long-term Memory) │ │ - 经过验证的持久知识 │ │ - 归纳后的认知模式 │ │ - 文件：memory/long_term.json + patterns.md │ └─────────────────────────────────────────────────┘ ``` --- ## 记忆类型 | 类型 | 说明 | 示例 | |------|------|------| | `fact` | 事实信息 | "Andy 的微信是 AIPMAndy" | | `preference` | 用户偏好 | "Andy 喜欢简洁直接的回复" | | `skill` | 学到的技能 | "飞书 API 限流时要分段请求" | | `error` | 犯过的错误 | "不要用 rm，用 trash" | | `pattern` | 归纳的模式 | "推送 GitHub 前先检查网络" | | `insight` | 深层洞察 | "Andy 更看重效率而非完美" | --- ## 核心操作 ### 1. 记录 (Remember) ```bash python3 scripts/evolve.py remember \ --type fact \ --content "Andy 的 GitHub 账号是 AIPMAndy" \ --source "用户告知" \ --importance 0.8 ``` ### 2. 回忆 (Recall) ```bash python3 scripts/evolve.py recall "GitHub 账号" ``` 返回相关记忆，按相关度和重要性排序。 ### 3. 反思 (Reflect) ```bash python3 scripts/evolve.py reflect ``` 触发反思循环： 1. 回顾近期记忆 2. 识别重复模式 3. 归纳成认知模式 4. 更新长期记忆 ### 4. 遗忘 (Forget) ```bash python3 scripts/evolve.py decay ``` 执行遗忘机制： - 7天未访问的短期记忆权重衰减 - 权重低于阈值的记忆被清理 - 重要记忆不会被遗忘

⬇0 ❤26 15 days ago · Uploaded Detail →
Fozu-lzwpattern Fozu-lzwpattern
from GitHub Content & Multimedia
phase project_state.py python3

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