Atlas / Skills / jackyst0 / awesome-agent-skills

awesome-agent-skillsSAFE

skills/jackyst0/awesome-agent-skills

🤖 精选的 AI Agent Skills 列表,适用于 Cursor、Claude Code、GitHub Copilot 等 AI 编程工具

Verdict
SAFE
Grade
B
Trust score
89 /100
Version
—
Hosts
6 documented
License
CC0-1.0
Stars
651
01

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

🔍 Search Skills Online

Modular instruction packages that give AI coding assistants on-demand capabilities for specific tasks, working across Cursor, Claude Code, GitHub Copilot, and more.

English | 简体中文

Contents

  • Quick Start
  • What Are Agent Skills
  • Official Resources
  • Skills Collections
  • Development Tools
  • Productivity
  • DevOps
  • Data Processing
  • Writing
  • Design

Quick Start

Quick Install (Recommended)

macOS / Linux:

curl --fail --proto '=https' --tlsv1.2 -fsSLo install.sh https://raw.githubusercontent.com/JackyST0/awesome-agent-skills/v1.0.1/install.sh && AAS_REPOSITORY_REF=v1.0.1 bash install.sh

Windows (PowerShell):

Invoke-WebRequest -Uri "https://raw.githubusercontent.com/JackyST0/awesome-agent-skills/v1.0.1/install.ps1" -OutFile "install.ps1"; .\install.ps1 -RepositoryRef v1.0.1

The stable release reference is included directly in the copy-paste command, so no prior environment setup is required. For later commands, use forms such as AAS_REPOSITORY_REF=v1.0.1 bash install.sh -p cursor -a or .\install.ps1 -RepositoryRef v1.0.1 -Platform cursor -All. The installer also includes the stable release as its default; the environment variable and parameter remain available for reviewed overrides.

Verify Before Running

For environments

Read from source at commit 674fd97f42b2OBSERVED · 2026-10-13
02

Install

Commands as the repository documents them. They are shown, not run.

git clone https://github.com/JackyST0/awesome-agent-skills.git
git clone https://github.com/anthropics/skills.git ~/.cursor/skills/anthropics
git clone https://github.com/JackyST0/awesome-agent-skills.git
git clone https://github.com/anthropics/skills.git ~/.cursor/skills/anthropics
git clone https://github.com/example/my-skill.git ~/.cursor/skills/my-skill
git clone https://github.com/example/code-review-skill.git
03

Host compatibility

What the documentation claims. We have not run a compatibility test.

HostStatusNotes
claude-codementioned
codexmentioned
copilotmentioned
cursormentioned
openclawmentioned
windsurfmentioned
04

What it tells the agent

The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.

---
name: api-doc-generator
description: Generate API documentation from source code, supporting REST APIs, GraphQL, and various documentation formats.
license: CC0-1.0
---

# API Doc Generator

> 根据代码生成 API 文档,支持 REST API、GraphQL 及多种文档格式。
>
> Generate API documentation from source code, supporting REST APIs, GraphQL, and various documentation formats.

## When to Use

当用户请求以下操作时使用此 skill:
- 生成 API 文档 / Generate API documentation
- 创建接口文档 / Create interface documentation
- 编写 API 说明 / Write API descriptions
- 生成 OpenAPI/Swagger 规范 / Generate OpenAPI/Swagger specs

## Instructions

### 分析步骤 / Analysis Steps

1. **识别 API 类型** - REST、GraphQL、RPC 等
2. **提取端点信息** - URL、方法、参数
3. **分析数据结构** - 请求/响应格式
4. **识别认证方式** - API Key、OAuth、JWT 等
5. **生成文档** - 按照标准格式输出

### 文档内容 / Documentation Content

每个 API 端点应包含:
- **端点路径** - URL 和 HTTP 方法
- **描述** - 功能说明
- **参数** - 路径参数、查询参数、请求体
- **响应** - 成功和错误响应示例
- **认证** - 认证要求

### 输出格式 / Output Formats

支持以下文档格式:
- Markdown(默认)- 使用 `templates/api-doc.md` 模板
- OpenAPI 3.0 YAML
- API Blueprint

Use `templates/api-doc.md` for Markdown output format.

### 标准模板 / Standard Template

````markdown
## API 文档 / API Documentation

### 端点概览 / Endpoint Overview

| 方法 | 路径 | 描述 |
|------|------|------|
| GET | /api/resource | 获取资源列表 |

### 详细说明 / Details

#### [方法] /path

**描述**: ...

**请求参数**:
| 参数 | 类型 | 必需 | 描述 |
|------|------|------|------|

**请求示例**:
```json
{}
```

**响应示例**:
```json
{}
```
````

## Examples

### 输入 / Input

```python
from fastapi import FastAPI, HTTPException
from pydantic import BaseModel

app = FastAPI()

class User(BaseModel):
    id: int
    name: str
    email: str

@app.get("/users/{user_id}")
async def get_user(user_id: int) -> User:
    """Get a user by ID."""
    if user_id <= 0:
        raise HTTPException(status_code=404, detail="User not found")
    return User(id=user_id, name="John", email="[email protected]")

@app.post("/users")
async def create_user(user: User) -> User:
    """Create a new user."""
    return user
```

### 输出 / Output

## API 文档

### 端点概览

| 方法 | 路径 | 描述 |
|------|------|------|
| GET | /users/{user_id} | 根据 ID 获取用户信息 |
| POST | /users | 创建新用户 |

---

### GET /users/{user_id}

**描述**: 根据用户 ID 获取用户信息

**路径参数**:
| 参数 | 类型 | 必需 | 描述 |
|------|------|------|------|
| user_id | integer | ✅ | 用户唯一标识符 |

**响应 200 - 成功**:
```json
{
  "id": 1,
  "name": "John",
  "email": "[email protected]"
}
```

**响应 404 - 未找到**:
```json
{
  "detail": "User not found"
}
```

---

### POST /users

**描述**: 创建新用户

**请求体**:
| 字段 | 类型 | 必需 | 描述 |
|------|------|------|------|
| id | integer | ✅ | 用户 ID |
| name | string | ✅ | 用户姓名 |
| email | string | ✅ | 用户邮箱 |

**请求示例**:
```json
{
  "id": 1,
  "name": "John",
  "email": "[email protected]"
}
```

**响应 200 - 成功**:
```json
{
  "id": 1,
  "name": "John",
  "email": "[email protected]"
}
```
05

Trust audit

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codePASS
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
declared (1 observation(s))
Network
declared (2 observation(s))
Shell
declared (1 observation(s))
Dependencies
pinned
Secrets in source
none-found

Findings (0)

No findings outside the package's declared scope.

Gates applied: no_behavioural_pass.

Audited 2026-10-13 · audit v0.4.1 · source sha 674fd97f42b2full audit observations/trust-audit/skill/jackyst0__awesome-agent-skills.json · Report an issue / request a re-scan
06

Audit history

Every audit this skill has had.

DateSourceVerdictGradeScoreChange
2026-10-13674fd97f42b2SAFEB89first audit
07

Questions

What does the awesome-agent-skills skill do?

🤖 精选的 AI Agent Skills 列表,适用于 Cursor、Claude Code、GitHub Copilot 等 AI 编程工具

Is awesome-agent-skills safe to install?

The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.

What can awesome-agent-skills access on my machine?

The audit observed that it reaches the network, runs shell commands and reads or writes files. Each of those is consistent with what it says it does. Secrets in the source: none found.

Which assistants does awesome-agent-skills work with?

Its documentation mentions claude-code, codex, copilot, cursor, openclaw and windsurf. That is what the text claims, not a compatibility test we ran.

How current is this page?

The grade is for one exact copy of the source (674fd97f42b2), read on 2026-10-13. The repository is watched, and a new audit runs when it changes — this is the first audit.

Advertisement