Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/cn-big-cabbage/github-skill-distiller/fastapinpx skills add CN-big-cabbage/github-skill-distiller --skill fastapigit clone --depth 1 https://github.com/CN-big-cabbage/github-skill-distillerWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00014 | $0.01538 |
| Opus 5 | $0.00007 | $0.00769 |
| Sonnet 5 | $0.00003 | $0.00308 |
| Haiku 4.5 | $0.00001 | $0.00154 |
Grade A, and why
fastapi scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FastAPI 高性能 Python Web API 框架
技能概述
本技能帮助开发者使用 FastAPI 构建现代化、高性能的 Web API，支持以下场景：
- REST API 开发: 快速构建符合 OpenAPI 标准的 RESTful 接口
- 数据验证: 基于 Pydantic 的自动请求/响应数据验证
- 自动文档: 自动生成 Swagger UI 和 ReDoc 交互式 API 文档
- 异步支持: 原生支持 async/await，处理高并发场景
- 依赖注入: 强大的依赖注入系统，简化认证、数据库连接等公共逻辑
- 安全认证: 内置 OAuth2、JWT、API Key 等认证方案
技术基础: FastAPI 构建于 Starlette（Web 框架层）和 Pydantic（数据验证层）之上，性能接近 NodeJS 和 Go。
架构概览
FastAPI 应用架构
├── app/
│ ├── main.py # 应用入口，注册路由和中间件
│ ├── dependencies.py # 公共依赖（认证、数据库会话等）
│ ├── models/ # Pydantic 数据模型
│ │ ├── __init__.py
│ │ └── user.py
│ ├── routers/ # 路由模块（按业务划分）
│ │ ├── __init__.py
│ │ ├── users.py
│ │ └── items.py
│ ├── crud/ # 数据库操作层
│ │ ├── __init__.py
│ │ └── user.py
│ └── core/ # 核心配置
│ ├── config.py
│ └── security.py
核心概念
| 概念 | 说明 |
|---|---|
| 路径操作 | 使用 @app.get/post/put/delete 装饰器定义 API 端点 |
| 路径参数 | URL 中的变量，如 /items/{item_id} |
| 查询参数 | URL 查询字符串，如 /items?skip=0&limit=10 |
| 请求体 | 通过 Pydantic 模型接收 JSON 数据 |
| 依赖注入 | 通过 Depends() 注入可复用的依赖函数 |
| 中间件 | 处理每个请求/响应的通用逻辑 |
| 路由器 | APIRouter 将路由按模块组织，类似 Flask Blueprint |
使用流程
AI 助手将引导你完成以下步骤：
- 安装 FastAPI 及依赖（uvicorn、pydantic 等）
- 创建应用入口文件
main.py - 定义 Pydantic 数据模型
- 编写路径操作函数（路由处理器）
- 配置依赖注入和中间件
- 启动开发服务器并验证 API 文档
关键章节导航
AI 助手能力
当你向 AI 描述需求时，AI 会：
- 自动生成 路由处理函数和 Pydantic 数据模型
- 自动配置 依赖注入（数据库会话、用户认证）
- 自动搭建 项目骨架结构（models、routers、crud 分层）
- 自动实现 JWT 认证和 OAuth2 安全方案
- 自动集成 SQLAlchemy/SQLModel 数据库操作
- 自动编写 测试用例（pytest + httpx）
- 自动处理 CORS 配置和自定义中间件
核心功能
- ✅ 基于 Python 类型提示的自动数据验证
- ✅ 自动生成 OpenAPI/Swagger 交互式文档
- ✅ 原生 async/await 异步支持
- ✅ 强大的依赖注入系统
- ✅ 内置安全认证（OAuth2、JWT、API Key、HTTP Basic）
- ✅ 支持 WebSocket 实时通信
- ✅ 支持 GraphQL（通过 Strawberry 集成）
- ✅ 支持后台任务（BackgroundTasks）
- ✅ 支持文件上传和静态文件服务
- ✅ 支持中间件和 CORS 配置
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 167 lines · 14 tokens per session scan A b52aaf10f253
fastapi is a skill published in the GitHub repository CN-big-cabbage/github-skill-distiller (4 stars, last pushed 2mo ago), licensed MIT. It adds 14 tokens to every session and 1,538 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
inferring-a-spell-from-examples
Use when the user invokes /capture-this-chat or /build-spell --from-transcript. Reads a transcript and produces a context dictionary plus a draft SKILL.md, which hands off to building-a-spell at Stage 2.
building-a-subagent-spell
Use when the meta-builder routes to kind=subagent. Generates a spell that dispatches one or more subagents to do work in parallel or in isolation.
intuitive-interviewing
Use when conducting any interview-style flow with a user (building a spell, refining one, gathering requirements). Picks depth, filters questions by relevance, matches against known shapes, and detects mid-stream pivots.
building-a-workflow-spell
Use when the meta-builder routes to kind=workflow. Generates a workflow spell with explicit stages, checkpoints, and loop-back conditions.
chaining-spells
Use when composing multiple spells into a chain that runs end-to-end (e.g. brainstorm -> plan -> execute -> verify).
discovering-spells
Use when browsing what spells are available - bundled seeds, your personal library, or both. Filter by kind, audience, or update status.