Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Work To Skill

ASecurity

工作即技能:每次完成一项有复用价值的工作后,自动评估并封装为可复用 Skill。让团队在工作中持续进化。

92 stars
0 votes
0 copies
0 views
Added 9/22/2026
ai-agentsapi

Works with

api

Security Analysis

A100/100

Scanned 9/22/2026

Install to Claude Code

$npx -y skills add aAAaqwq/AGI-Super-Team --skill work-to-skill --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Work To Skill?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Work To Skill
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/aaaaqwq-work-to-skill-agi-super-team/badge)](https://www.skillsdirectory.com/skills/aaaaqwq-work-to-skill-agi-super-team)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: work-to-skill
description: 工作即技能:每次完成一项有复用价值的工作后,自动评估并封装为可复用 Skill。让团队在工作中持续进化。
license: MIT
metadata:
  version: 1.0.0
  domains:
  - meta
  - self-improvement
  - skill-creation
  type: automation
author: Daniel Li
---
# Work-to-Skill — 工作即技能

- Author: Daniel Li
- Copyright © Daniel Li. All rights reserved.

> **核心理念:每一次有价值的工作,都可能成为团队永久的能力。**
> 完成任务不是终点,把任务沉淀为 Skill 才是闭环。

## 什么时候触发

**每次完成一项工作后,花 30 秒问自己这 3 个问题:**

| # | 问题 | 判断标准 |
|---|------|---------|
| 1 | **这个工作以后会重复吗?** | 同类任务出现过 ≥2 次,或预期会再出现 |
| 2 | **过程中有可复用的模式吗?** | 有固定步骤、固定命令、固定判断逻辑 |
| 3 | **别的 agent 也可能需要吗?** | 不是只有自己才用得上的一次性操作 |

**满足任意 2 条 → 创建 Skill。**

## 不该做成 Skill 的

- ❌ 一次性的数据查询("帮我查下今天的天气")
- ❌ 纯主观判断、没有可复用逻辑的决策
- ❌ 已有现成 Skill 能覆盖的能力(先搜 ClawHub)
- ❌ 涉及密钥/凭据的硬编码操作

## 创建流程

### Step 1: 评估(完成任务后立即)

在任务完成的回复中,附加一段自评:

```
📦 Skill 潜力评估:
- 任务类型:[数据采集/代码开发/内容创作/运维/分析/...]
- 可复用性:[高/中/低]
- 复用场景:[简述谁在什么场景下会再用]
- 判定:[✅ 值得封装 / ❌ 一次性任务]
```

### Step 2: 提取核心模式

从刚完成的工作中提取:
1. **输入**:这个任务需要什么输入?(参数/文件/URL/...)
2. **步骤**:核心步骤是什么?(按顺序列出)
3. **输出**:产出物是什么?(文件/消息/数据/...)
4. **踩坑点**:过程中有什么容易出错的地方?

### Step 3: 写 SKILL.md

在 `skills/<skill-name>/` 下创建:

```
<skill-name>/
├── SKILL.md          # 技能文档(必需)
├── scripts/          # 脚本(如有)
│   └── main.py/.sh/.js
└── examples/         # 示例(如有)
```

**SKILL.md 模板:**

```yaml
---
name: <skill-name>
description: "<一句话:做什么 + 什么场景用>"
license: MIT
metadata:
  version: 1.0.0
  domains: [<领域标签>]
  type: automation
---

# <Skill 名称>

## 什么时候用
- 场景 1
- 场景 2

## 使用方法

### 前置条件
- 需要的 API key / 工具 / 环境

### 步骤
1. ...
2. ...
3. ...

### 示例
```(具体命令或调用方式)```

## 注意事项
- 踩坑点 1
- 踩坑点 2

## 触发词
- "关键词1"
- "关键词2"(中英双语)
```

### Step 4: 注册到对应 Agent

如果 Skill 是通用的 → 放 `skills/`(全局生效)
如果 Skill 是某个角色专用的 → 放 `skills/` 并配到对应 agent 的 `agent.json`

### Step 5: 汇报

在在团队渠道中简要汇报新 Skill:
```
📦 新 Skill 已创建:<skill-name>
- 功能:一句话描述
- 位置:路径
- 适用:哪些 agent
- 来源:从什么任务中提炼的
```

## 质量标准

一个好的 Skill 必须满足:
- [ ] **自包含**:读 SKILL.md 就能直接用,不需要问别人
- [ ] **有示例**:至少一个完整的使用示例
- [ ] **有踩坑**:写明容易出错的地方和解决方案
- [ ] **无密钥**:所有密钥通过 `pass show` 引用,绝不硬编码
- [ ] **有触发词**:中英文触发词,方便 Agent 匹配

## 进阶:Skill 迭代

使用中发现 Skill 不好用?直接更新:
1. 修改 SKILL.md
2. 更新 version 号
3. 在团队渠道中通知:`📦 Skill 更新:<name> v1.0 → v1.1,改了什么`

## 反模式(绝对不要)

| ❌ 反模式 | ✅ 正确做法 |
|----------|-----------|
| Skill 里写死 API key | `pass show api/xxx` |
| 一个 Skill 做 10 件事 | 拆成多个聚焦的 Skill |
| 写了 Skill 但没人知道 | 群里汇报 + 更新团队记忆或相关文档 |
| 把所有代码都做成 Skill | 只做有复用价值的 |
| Skill 没有使用示例 | 至少一个可运行的 example |

## 触发词

- "创建 skill"、"封装技能"、"做成 skill"
- "这个以后还会用"、"这个可以复用"
- "create skill"、"package as skill"、"make reusable"
- "工作沉淀"、"能力封装"

Attribution

aAAaqwqaAAaqwq
View sourceMore from aAAaqwq →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1066601 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

651 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →