github-stars-analyzer

AI Community

Repo stars 0
Author repo skills-registry

Interpretation is structured for decision-making; original keeps the upstream SKILL.md unchanged.

Decide Fit First

Core job: 通过 GitHub 公开 API 抓取用户所有 starred 仓库，按大类自动分组，生成标准化中文 Markdown 报告文件。 github-stars-analyzer/ ├── SKILL.md ← 本文件 │ └── fetch_stars.py…
Best fit: Use it when the task has reusable inputs, steps, and validation criteria rather than a one-off answer.
Avoid forcing it: If the source lacks commands, platform support, or external-service evidence, keep those fields unknown instead of guessing.

Design Intent

Structure: The skill is organized around “技能概述”, “文件结构”, “执行流程”, “第一步：解析用户名”, showing how the author expects the agent to judge fit, collect context, and produce verifiable output.
Trigger evidence: Prioritize the author’s wording around when to use it, what context to collect, and what output shape to produce.
Evidence boundary: Author text states facts, repository files prove commands and paths, and Fluxly only adds fit, limits, and usage judgment.

How To Use It

Inputs: Provide target material, scope, expected result, forbidden changes, and validation method.
Invocation: Name github-stars-analyzer directly; if the source includes slash commands, start with the command and then add task context.
Validation: Start small and check whether the result follows “技能概述 / 文件结构 / 执行流程” before expanding.

Boundaries And Review

Dependencies: Prepare Vendor-specific API keys before running a full task.
Permissions: Declared permissions include read; ask the agent to state file, command, and rollback boundaries before acting.
Quality bar: A useful result names the deliverable, evidence, and next action. Generic prose means the task needs tighter context.

GitHub Stars 分析器技能

技能概述

通过 GitHub 公开 API 抓取用户所有 starred 仓库，按大类自动分组，生成标准化中文 Markdown 报告文件。

文件结构

github-stars-analyzer/
├── SKILL.md                  ← 本文件
├── scripts/
│   └── fetch_stars.py        ← 抓取 + 报告生成脚本
└── assets/
    └── template.md           ← 标准化报告模板（说明格式规范）

执行流程

第一步：解析用户名

从用户消息中提取 GitHub 用户名，支持以下格式：

https://github.com/USERNAME?tab=stars
https://github.com/USERNAME
@USERNAME
裸用户名

第二步：运行脚本

将脚本复制到工作目录后执行：

cp /path/to/skill/scripts/fetch_stars.py /home/claude/fetch_stars.py
python3 /home/claude/fetch_stars.py USERNAME --output /home/claude/USERNAME_github_stars.md

可选参数：

--token <PAT>：GitHub Personal Access Token，将 API 限额从 60次/小时提升至 5000次/小时
--output <路径>：指定输出文件路径，默认为 <username>_github_stars.md

第三步：交付文件

cp /home/claude/USERNAME_github_stars.md /mnt/user-data/outputs/USERNAME_github_stars.md

然后使用 present_files 工具将文件提供给用户。

报告大类分类规则

脚本按仓库 topics 和语言自动划分以下大类（优先级从上到下匹配）：

大类	匹配关键词（topics / 语言）
🤖 人工智能与机器学习	ai, ml, machine-learning, deep-learning, llm, nlp, neural-network, gpt, pytorch, tensorflow
🛠️ 开发工具与效率	cli, tool, productivity, devtools, vscode, vim, ide, automation, workflow
🌐 前端与界面	frontend, react, vue, angular, css, html, ui, design, javascript, typescript
⚙️ 后端与框架	backend, api, rest, graphql, microservice, server, django, flask, fastapi, go, rust
📦 基础设施与运维	devops, docker, kubernetes, ci-cd, cloud, aws, infra, terraform, nginx
🗄️ 数据库与数据	database, sql, nosql, redis, postgres, mongodb, data, analytics, etl
🔒 安全与隐私	security, hacking, pentest, crypto, privacy, auth, vulnerability
📚 学习资源与文档	awesome, tutorial, learning, course, book, guide, roadmap, cheatsheet
🎮 游戏与创意	game, graphics, animation, art, creative, shader
🐍 Python 生态	语言为 Python 且未命中以上类别
其他	未匹配任何类别的仓库

报告模板规范

详见 assets/template.md，生成报告时严格遵循该模板的结构和中文命名规范。

错误处理

HTTP 404：提示用户名不存在，终止
HTTP 403：提示 API 超限，显示剩余等待秒数，建议添加 --token
网络不通：提示检查网络连接（Claude 服务器无外网出口，脚本需在用户本地运行）

向用户说明

完成后告知用户：

文件已生成，可直接下载
如需在本地重新运行：python3 fetch_stars.py <用户名>
如遇 API 限速，在 GitHub 设置页生成一个免费 Token（无需任何权限勾选）后加上 --token 参数

Source: AgentWorkers/skills — distributed by TomeVault.

Fluxly profile Author and license come from source; runtime, permissions, and network are Fluxly detections or estimates

Fluxly category: AI
Author-declared agents: No explicit declaration found; this is not inferred or tested compatibility
Static check: 88 / 100 · heuristic scan, not runtime safety proof
Author / version / license: @tomevault-io · no license declared
Fluxly token estimate: Lean
Fluxly setup estimate: Manual integration
External API key: Required · Vendor-specific
Detected OS requirements: Docker
Runtime requirements: Python · Docker
Detected file/system behavior: Read-only
Detected network behavior: External requests
Install commands: None (reference only)

Profile is derived at build time from SKILL.md and install vectors. Subject to drift from author intent.

Heads up: 未限定 allowed-tools，默认拥有全部工具权限。

Output preview github-stars-analyzer.preview

The current SKILL.md does not define a fixed output example.

SKILL.md SKILL.md

# GitHub Stars 分析器技能

## 技能概述

通过 GitHub 公开 API 抓取用户所有 starred 仓库，按大类自动分组，生成标准化中文 Markdown 报告文件。

## 文件结构

```
github-stars-analyzer/
├── SKILL.md                  ← 本文件
├── scripts/
│   └── fetch_stars.py        ← 抓取 + 报告生成脚本
└── assets/
    └── template.md           ← 标准化报告模板（说明格式规范）
```

## 执行流程

### 第一步：解析用户名

从用户消息中提取 GitHub 用户名，支持以下格式：
- `https://github.com/USERNAME?tab=stars`
- `https://github.com/USERNAME`
- `@USERNAME`
- 裸用户名

### 第二步：运行脚本

将脚本复制到工作目录后执行：

```bash
cp /path/to/skill/scripts/fetch_stars.py /home/claude/fetch_stars.py
python3 /home/claude/fetch_stars.py USERNAME --output /home/claude/USERNAME_github_stars.md
```

可选参数：
- `--token <PAT>`：GitHub Personal Access Token，将 API 限额从 60次/小时 提升至 5000次/小时
- `--output <路径>`：指定输出文件路径，默认为 `<username>_github_stars.md`

### 第三步：交付文件

```bash
cp /home/claude/USERNAME_github_stars.md /mnt/user-data/outputs/USERNAME_github_stars.md
```

然后使用 `present_files` 工具将文件提供给用户。

## 报告大类分类规则

脚本按仓库 topics 和语言自动划分以下大类（优先级从上到下匹配）：

| 大类 | 匹配关键词（topics / 语言） |
|------|--------------------------|
| 🤖 人工智能与机器学习 | ai, ml, machine-learning, deep-learning, llm, nlp, neural-network, gpt, pytorch, tensorflow |
| 🛠️ 开发工具与效率 | cli, tool, productivity, devtools, vscode, vim, ide, automation, workflow |
| 🌐 前端与界面 | frontend, react, vue, angular, css, html, ui, design, javascript, typescript |
| ⚙️ 后端与框架 | backend, api, rest, graphql, microservice, server, django, flask, fastapi, go, rust |
| 📦 基础设施与运维 | devops, docker, kubernetes, ci-cd, cloud, aws, infra, terraform, nginx |
| 🗄️ 数据库与数据 | database, sql, nosql, redis, postgres, mongodb, data, analytics, etl |
| 🔒 安全与隐私 | security, hacking, pentest, crypto, privacy, auth, vulnerability |
| 📚 学习资源与文档 | awesome, tutorial, learning, course, book, guide, roadmap, cheatsheet |

…

Evidence boundary and execution chain

Author text anchors workflow facts; Fluxly only indexes current sections, terms, files, and commands.

sections -> 技能概述 → 文件结构 → 执行流程 → 第一步：解析用户名 → 第二步：运行脚本 → 第三步：交付文件
terms    -> HTTP 404 · HTTP 403 · 网络不通 · 通过 GitHub 公开 API 抓取用户所有 starred 仓库，按大类自动分组，生成标准化中文 Markdown 报告文件。 · 然后使用 presentfiles 工具将文件提供给用户。 · 详见 assets/template.md，生成报告时严格遵循该模板的结构和中文命名规范。 · 完成后告知用户： 1. · --- > Source: [AgentWorkers/skills](https://github.com/AgentWorkers/skills) — distributed by [TomeVault](https://tomevault.io).
files/cmd -> https://github.com/USERNAME?tab=stars · https://github.com/USERNAME · @USERNAME · --token <PAT> · --output <路径> · <username>githubstars.md · presentfiles · assets/template.md
body sha256 -> 8bcafc8d150c