浏览器规划
- 作者仓库星标 0
- 作者更新于 2026年7月4日 01:22
- 作者仓库 baoyu-skills
- 领域
- 文档
- 作者声明的智能体
- 未找到明确声明;不据此推断已兼容或已测试
- 静态检查
- 92 / 100 · 启发式扫描,不代表运行安全
- 运行环境证据
- 未执行;当前没有隔离运行测试证据
- 作者 / 版本 / 许可证
- @JimLiu · v1.61.0 · 未声明许可证
- 上下文用量评级
- 低消耗
- 接入复杂程度
- 需简单配置
- 是否需要外部接口密钥
- 不需要
- 兼容的系统
- macOS · Linux · Windows
- 运行环境要求
- Bun
- 检测到的文件与系统行为
-
- 只读
- 允许写入 / 修改
- 命令执行
- 读取环境变量
- 网络行为
- 允许外网请求
- 安装命令数
- 无(仅作为资料)
需要注意: 未声明工具权限范围;实际权限由运行环境决定。
# URL to Markdown
Fetches any URL via `baoyu-fetch` CLI (Chrome CDP + site-specific adapters) and converts it to clean markdown.
## User Input Tools
When this skill prompts the user, follow this tool-selection rule (priority order):
1. **Prefer built-in user-input tools** exposed by the current agent runtime — e.g., `AskUserQuestion`, `request_user_input`, `clarify`, `ask_user`, or any equivalent.
2. **Fallback**: if no such tool exists, emit a numbered plain-text message and ask the user to reply with the chosen number/answer for each question.
3. **Batching**: if the tool supports multiple questions per call, combine all applicable questions into a single call; if only single-question, ask them one at a time in priority order.
Concrete `AskUserQuestion` references below are examples — substitute the local equivalent in other runtimes.
## CLI Setup
**Important**: The CLI source is vendored in `{baseDir}/scripts/lib`. `scripts/package.json` installs only third-party runtime dependencies.
**Agent Execution Instructions**:
1. Determine this SKILL.md file's directory path as `{baseDir}`
2. Resolve `${BUN}` runtime: if `bun` installed → `bun`; else suggest installing Bun
3. If `{baseDir}/scripts/node_modules` does not exist, run `${BUN} install --cwd {baseDir}/scripts`
4. `${READER}` = `{baseDir}/scripts/baoyu-fetch`
5. Replace all `${READER}` in this document with the resolved value
## Preferences (EXTEND.md)
Check EXTEND.md in priority order — the first one found wins:
| Priority | Path | Scope |
|----------|------|-------|
| 1 | `.baoyu-skills/baoyu-url-to-markdown/EXTEND.md` | Project |
| 2 | `${XDG_CONFIG_HOME:-$HOME/.config}/baoyu-skills/baoyu-url-to-markdown/EXTEND.md` | XDG |
| 3 | `$HOME/.baoyu-skills/baoyu-url-to-markdown/EXTEND.md` | User home |
| Result | Action |
|--------|--------|
| Found | Read, parse, apply settings |
| Not found | **MUST** run first-time setup (see below) — do NOT silently create defaults |
**EXTEND.md supports**: download media by default, default output directory.
### First-Time Setup ⛔ BLOCKING
When EXTEND.md is not found, you **MUST** use `AskUserQuestion` to gather preferences before creating EXTEND.md. **NEVER** create EXTEND.md with silent defaults. Generation is BLOCKED until setup completes. Batch all three questions into a single call:
- **Q1 — Media** (header "Media"): "How to handle images and videos in pages?"
- "Ask each time (Recommended)" — Prompt after each save
- "Always download" — Download to local `imgs/` and `videos/`
- "Never download" — Keep remote URLs
- **Q2 — Output** (header "Output"): "Default output directory?"
- "url-to-markdown (Recommended)" — Save to `./url-to-markdown/{domain}/{slug}.md`
- User may pick "Other" and type a custom path
- **Q3 — Save** (header "Save"): "Where to save preferences?"
- "User (Recommended)" — `~/.baoyu-skills/` (all projects)
- "Project" — `.baoyu-skills/` (this project only)
After answers, write EXTEND.md, confirm "Preferences saved to [path]", then continue.
Full template: [references/config/first-time-setup.md](references/config/first-time-setup.md).
### Supported Keys
| Key | Default | Values | Description |
|-----|---------|--------|-------------|
| `download_media` | `ask` | `ask` / `1` / `0` | `ask` = prompt each time, `1` = always, `0` = never |
| `default_output_dir` | empty | path or empty | Default output directory (empty = `./url-to-markdown/`) |
**EXTEND.md → CLI mapping**:
| EXTEND.md key | CLI argument | Notes |
|---------------|-------------|-------|
| `download_media: 1` | `--download-media` | Requires `--output` to be set |
| `default_output_dir: ./posts/` | Agent constructs `--output ./posts/{domain}/{slug}.md` | Agent generates path, not a direct flag |
**Value priority**: CLI arguments → EXTEND.md → skill defaults.
## Usage
```bash
# Default: headless capture, markdown to stdout
${READER} <url>
# Save to file
${READER} <url> --output article.md
# Save with media download
${READER} <url> --output article.md --download-media
# Wait for interaction (login/CAPTCHA) — auto-detect and continue
${READER} <url> --wait-for interaction --output article.md
# Wait for interaction — manual control (Enter to continue)
${READER} <url> --wait-for force --output article.md
# JSON output
${READER} <url> --format json --output article.json
# Force specific adapter
${READER} <url> --adapter youtube --output transcript.md
```
## Options
| Option | Description |
|--------|-------------|
| `<url>` | URL to fetch |
| `--output <path>` | Output file path (default: stdout) |
| `--format <type>` | Output format: `markdown` (default) or `json` |
| `--json` | Shorthand for `--format json` |
| `--adapter <name>` | Force adapter: `x`, `youtube`, `hn`, or `generic` (default: auto-detect) |
| `--headless` | Force headless Chrome (no visible window) |
| `--wait-for <mode>` | Interaction wait mode: `none` (default), `interaction`, or `force` |
| `--wait-for-interaction` | Alias for `--wait-for interaction` |
| `--wait-for-login` | Alias for `--wait-for interaction` |
| `--timeout <ms>` | Page load timeout (default: 30000) |
| `--interaction-timeout <ms>` | Login/CAPTCHA wait timeout (default: 600000 = 10 min) |
| `--interaction-poll-interval <ms>` | Poll interval for interaction checks (default: 1500) |
| `--download-media` | Download images/videos to local `imgs/` and `videos/`, rewrite markdown links. Requires `--output` |
| `--media-dir <dir>` | Base directory for downloaded media (default: same as `--output` directory) |
| `--cdp-url <url>` | Reuse existing Chrome DevTools Protocol endpoint |
| `--browser-path <path>` | Custom Chrome/Chromium binary path |
| `--chrome-profile-dir <path>` | Chrome user data directory (default: `BAOYU_CHROME_PROFILE_DIR` env or `./baoyu-skills/chrome-profile`) |
| `--debug-dir <dir>` | Write debug artifacts (document.json, markdown.md, page.html, network.json) |
## Agent Quality Gate
**CRITICAL**: treat default headless capture as provisional. Some sites render differently in headless mode and can silently return low-quality content without failing the CLI.
After every headless run, inspect the saved markdown. See [references/quality-gate.md](references/quality-gate.md) for the full checklist, recovery workflow, and capture-mode table. Read it whenever a run looks suspicious or the user asks about login/CAPTCHA handling.
## Output Path Generation
The agent must construct the output file path — `baoyu-fetch` does not auto-generate paths.
**Algorithm**:
1. Determine base directory from EXTEND.md `default_output_dir` or default `./url-to-markdown/`
2. Extract domain from URL (e.g., `example.com`)
3. Generate slug from URL path or page title (kebab-case, 2-6 words)
4. Construct: `{base_dir}/{domain}/{slug}/{slug}.md` — each URL gets its own directory so media files stay isolated
5. Conflict resolution: append timestamp `{slug}-YYYYMMDD-HHMMSS/{slug}-YYYYMMDD-HHMMSS.md`
Pass the constructed path to `--output`. Media files (`--download-media`) are saved into subdirectories next to the markdown file, keeping each URL's assets self-contained.
## Adapters & Media
See [references/adapters.md](references/adapters.md) for the adapter catalog (X, YouTube, Hacker News, generic), per-adapter notes, the media download flow (`ask` / always / never), and the JSON output schema. Read it before answering adapter-specific questions or handling media prompts.
## Environment Variables
| Variable | Description |
|----------|-------------|
| `BAOYU_CHROME_PROFILE_DIR` | Chrome user data directory (can also use `--chrome-profile-dir`) |
**Troubleshooting**: Chrome not found → use `--browser-path`. Timeout → increase `--timeout`. Login/CAPTCHA → `--wait-for interaction`. Debug → `--debug-dir` to inspect captured HTML and network logs.
## Extension Support
Custom configurations via EXTEND.md. See **Preferences** section above for paths and supported keys.
章节与文件索引
按说明文件中的顺序排列。
用户输入工具
CLI 设置
首选项(EXTEND.md)
首次设置 ⛔ 阻止
支持的按键
文件/命令 -> baoyu-fetch · AskUserQuestion · request_user_input · clarify · ask_user · {baseDir}/scripts/lib · scripts/package.json · {baseDir}
内容校验值 -> aee2388de394
baoyu-url-to-markdown 给一个 URL,把网页正文抓回来转成干净的 Markdown——重点是「干净」:去广告、去导航、去推荐位,只留正文。
设计思路
作者发现通用型抓取工具(Mercury、Readability)对中文站点支持不太好,特定站点(X、YouTube、Hacker News、知乎、微信)又有自己的反爬和结构。所以技能用了「baoyu-fetch CLI + 站点专用 adapters」的双层设计——通用站点走 Defuddle 走清洗,特殊站点走 site-specific adapter。
内置 adapters
SKILL.md 列出 built-in adapters:
未来可加更多 adapter,框架已留好扩展点。
工作流
按 Workflow:① 读 URL;② 自动判断走哪个 adapter;③ 通过 baoyu-fetch CLI(封装了 Chrome CDP)打开页面;④ Agent Quality Gate:抓回来后检查正文是否完整、是否有明显污染(导航、推荐);⑤ Output Path Generation 自动起文件名(基于标题 + 日期);⑥ Adapters & Media 处理图、视频、附件。
CLI Setup
启用前需装
baoyu-fetchCLI——SKILL.md 顶部 CLI Setup 章节给了详细的安装步骤。装好后通过 Environment Variables 控制 Chrome 路径、超时、缓存。适合谁
不适合
配套
baoyu-format-markdown:把抓回来的 Markdown 进一步格式化baoyu-translate:英文文章抓回来后翻译baoyu-post-to-wechat:抓 → 翻 → 发布的链路obsidian-vault:把抓回来的文件归档到 Obsidian