Live survey304 models · 14 providers · 23,592 auditsAudited implement · SAFE →What changedHow we verifyllms.txt

Agent skill · Audited from source

baoyu-url-to-markdown

skill · jimliu/baoyu-skillsMIT licenceAudited 13 Nov 2026 · source e63a35febc0c

★ 27,501pushed 6 days agoversion 1.61.0
!CAUTIONGrade B · 89/100 · 9 findings · e63a35f
27,501repo stars · whole jimliu/baoyu-skills

Is it safe? With care — CAUTION, grade B (89/100). We read this skill's source at commit e63a35febc0c and observed filesystem, network and shell access and no hard-coded secrets. The audit raised 9 findings, 0 critical or high. What it does: Fetch any URL and convert to markdown using baoyu-fetch CLI (Chrome CDP with site-specific adapters). Built-in adapters for X/Twitter, YouTube transcripts, Hacker News threads, and generic pages via Defuddle. Handles…

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “baoyu-url-to-markdown (jimliu/baoyu-skills)”. Retrieved 13 Nov 2026. https://modelsatlas.com/skills/jimliu/baoyu-url-to-markdown

Trust audit

Audit 0.4.1 · source read 13 Nov 2026

Trust score89/100!CAUTION B
0 critical0 high3 medium6 low0 info

CAUTION means the audit found things worth knowing before you trust this skill. Grade B is shared by 17,406 of 18,389 audited skills.

What the source does

  • FilesystemDeclared5 observations
  • NetworkDeclared8 observations
  • ShellDeclared2 observations
  • DependenciesNot pinnedSome versions float
  • SecretsNone foundNo keys in source

Five audit layers

LayerWhat we checkResultFindings
L0 ProvenanceRepo owner, licence, archive status, activityPASS0
L1 Static sourceSecrets, path traversal, supply chain, hidden codeWARN9
L2 InstructionsPrompt injection, authority framing, hidden directivesPASS0
L3 InventoryThe files and declarations match the sourcePASS0
L4 SandboxRun in isolation and watch behaviourSKIPPED why0

Gates applied: no behavioural pass.

Findings (9)

MEDIUMNetwork egressnet.raw_ip · scripts/lib/browser/chrome-launcher.ts:64
F-04 Network egressCWE-200 · CWE-319Layer L1
const origin = `http://127.0.0.1:${port}`;
Why
No further detail recorded for this rule.
Fix
—
MEDIUMNetwork egressnet.raw_ip · scripts/lib/browser/chrome-launcher.ts:100
F-04 Network egressCWE-200 · CWE-319Layer L1
const origin = `http://127.0.0.1:${launchedChrome.port}`;
Why
No further detail recorded for this rule.
Fix
—
MEDIUMNetwork egressnet.raw_ip · scripts/lib/browser/profile.ts:140
F-04 Network egressCWE-200 · CWE-319Layer L1
const version = await fetchJson<ChromeVersionResponse>(`http://127.0.0.1:${port}/json/version`, timeoutMs);
Why
No further detail recorded for this rule.
Fix
—
LOWFilesystem / pathfs.traversal · scripts/lib/adapters/generic/index.ts:2
F-05 Filesystem / pathCWE-22 · CWE-59Layer L1
import { detectInteractionGate } from "../../browser/interaction-gates";
Why
No further detail recorded for this rule.
Fix
—
LOWFilesystem / pathfs.traversal · scripts/lib/adapters/generic/index.ts:3
F-05 Filesystem / pathCWE-22 · CWE-59Layer L1
import { captureNormalizedPageSnapshot } from "../../browser/page-snapshot";
Why
No further detail recorded for this rule.
Fix
—
LOWFilesystem / pathfs.traversal · scripts/lib/adapters/generic/index.ts:4
F-05 Filesystem / pathCWE-22 · CWE-59Layer L1
import { convertHtmlToMarkdown } from "../../extract/html-to-markdown";
Why
No further detail recorded for this rule.
Fix
—
LOWFilesystem / pathfs.traversal · scripts/lib/adapters/hn/index.ts:5
F-05 Filesystem / pathCWE-22 · CWE-59Layer L1
import type { ExtractedDocument } from "../../extract/document";
Why
No further detail recorded for this rule.
Fix
—
LOWFilesystem / pathfs.traversal · scripts/lib/adapters/hn/index.ts:6
F-05 Filesystem / pathCWE-22 · CWE-59Layer L1
import { collectMediaFromDocument } from "../../media/markdown-media";
Why
No further detail recorded for this rule.
Fix
—
LOWSupply chainsupply.unpinned · scripts/package.json
F-08 Supply chainCWE-829 · CWE-1357Layer L1
@mozilla/readability, chrome-launcher, defuddle, jsdom, remark-gfm, remark-parse, turndown, turndown-plugin-gfm
Why
10 dependency range(s) float
Fix
pin exact versions or ship a lockfile

Audit 0.4.1 · source sha e63a35febc0c · 13 Nov 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

  • Publisherjimliu GitHub userOwner of the repository this skill is read from
  • Source folderjimliu/baoyu-skills/skills/baoyu-url-to-markdownThe exact folder we audited
  • LicenceMITAs the repository states it
  • Commit pinned for this verdicte63a35febc0cA new audit runs when the source changes
  • Repository statusNot archivedLast push 6 days ago
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: Fetch any URL and convert to markdown using baoyu-fetch CLI (Chrome CDP with site-specific adapters). Built-in adapters for X/Twitter, YouTube transcripts, Hacker News threads, and generic pages via Defuddle. Handles…

---
name: baoyu-url-to-markdown
description: Fetch any URL and convert to markdown using baoyu-fetch CLI (Chrome CDP with site-specific adapters). Built-in adapters for X/Twitter, YouTube transcripts, Hacker News threads, and generic pages via Defuddle. Handles login/CAPTCHA via interaction wait modes. Use when user wants to save a webpage as markdown.
version: 1.61.0
metadata:
  openclaw:
    homepage: https://github.com/JimLiu/baoyu-skills#baoyu-url-to-markdown
    requires:
      anyBins:
        - bun
---

# URL to 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

The CLI source is vendored in `{baseDir}/scripts/lib`; `scripts/package.json` installs only third-party runtime dependencies.

1. `{baseDir}` = this SKILL.md's directory
2. `${BUN}` = `bun` if installed; otherwise suggest installing Bun
3. If `{baseDir}/scripts/node_modules` is missing: `${BUN} install --cwd {baseDir}/scripts`
4. `${READER}` = `{baseDir}/scripts/baoyu-fetch` (substitute everywhere below)

## Preferences (EXTEND.md)

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 |

Found → read and apply. Not found → **BLOCKING** first-time setup: ask the questions in [references/config/first-time-setup.md](references/config/first-time-setup.md) (Media, Output, Save — all in one call) before any conversion, write EXTEND.md, confirm "Preferences saved to [path]", then continue. Never create EXTEND.md with silent defaults.

| Key | Default | Values | CLI mapping |
|-----|---------|--------|-------------|
| `download_media` | `ask` | `ask` (prompt each time) / `1` (always) / `0` (never) | `1` → `--download-media` (requires `--output`) |
| `default_output_dir` | empty (= `./url-to-markdown/`) | path or empty | Agent builds `--output <dir>/{domain}/{slug}.md`; not a direct flag |

Value priority: CLI arguments → EXTEND.md → skill defaults.

## Usage

```bash
${READER} <url>                                          # headless, markdown to stdout
${READER} <url> --output article.md --download-media     # save with local media
${READER} <url> --wait-for interaction --output a.md     # login/CAPTCHA: auto-detect and continue
${READER} <url> --wait-for force --output a.md           # manual: Enter to continue
${READER} <url> --format json --output a.json
${READER} <url> --adapter youtube --output transcript.md
```

## Options

| Option | Description |
|--------|-------------|
| `<url>` | URL to fetch |
| `--output <path>` | Output file path (default: stdout) |
| `--format <type>` | `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 |
| `--wait-for <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>` | Interaction poll interval (default: 1500) |
| `--download-media` | Download images/videos to local `imgs/` and `videos/`, rewrite links. Requires `--output` |
| `--media-dir <dir>` | Base directory for downloaded media (default: `--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) |

## Quality Gate

Headless capture is provisional: some sites silently return low-quality content with exit code `0`. Inspect the saved markdown after every headless run, using [references/quality-gate.md](references/quality-gate.md) for the checklist, recovery steps, and capture modes.

## Output Path

`baoyu-fetch` does not generate paths; the agent builds one and passes it to `--output`:

1. Base dir: EXTEND.md `default_output_dir` or `./url-to-markdown/`
2. Domain from URL (e.g., `example.com`)
3. Slug from URL path or page title (kebab-case, 2-6 words)
4. Path: `{base_dir}/{domain}/{slug}/{slug}.md` — one directory per URL so media stays isolated
5. On conflict: `{slug}-YYYYMMDD-HHMMSS/{slug}-YYYYMMDD-HHMMSS.md`

Downloaded media goes into subdirectories next to the markdown file.

## Adapters & Media

[references/adapters.md](references/adapters.md): adapter catalog (X, YouTube, Hacker News, generic), media download flow (`ask` / always / never), JSON output schema. Read it for adapter-specific questions or media prompts.

## Environment Variables

| Variable | Description |
|----------|-------------|
| `BAOYU_CHROME_PROFILE_DIR` | Chrome user data directory (or `--chrome-profile-dir`) |

**Troubleshooting**: Chrome not found → `--browser-path`. Timeout → raise `--timeout`. Login/CAPTCHA → `--wait-

Excerpt, first 6,000 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

Install

Pinned to the audited commit e63a35f

Download folder ↗
git clone https://github.com/jimliu/baoyu-skills
git -C baoyu-skills checkout e63a35febc0c

The author documents no install command, so this uses the repository directly. Our verdict covers commit e63a35febc0c only.

Works in which agents?

What its own text says, not a test

AgentStatusMore
OpenClawMentioned in its text, not testedSkills for OpenClaw · About OpenClaw
“Mentioned” means the skill’s text names the agent. We have not run it there.

Audit history

Every audit, every source change

  1. !CAUTION B 89 / 100

    first audit · source e63a35febc0c

README badge

For maintainers · shows the latest audit

ModelsAtlas: CAUTION BMODELSATLASCAUTION · B
[![ModelsAtlas: CAUTION B](https://modelsatlas.com/skills/jimliu/baoyu-url-to-markdown/badge.svg)](https://modelsatlas.com/skills/jimliu/baoyu-url-to-markdown/)

The badge shows our verdict and grade for this skill, and links back to this page. It changes when the audit does.

baoyu-xhs-images✓SAFE

jimliu/baoyu-skills

Generates infographic image card series with 12 visual styles, 8 layouts, and 3 color palettes. Breaks content into 1-10 cartoon-style image cards optimized for social media engagement. Use when user mentions "小红书图片",…

★ 28kGrade B
baoyu-wechat-summary✓SAFE

jimliu/baoyu-skills

Summarizes WeChat group chat highlights into a structured digest using the local wx-cli binary (https://github.com/jackwener/wx-cli). Generates a normal digest by default; a roast (毒舌) version is opt-in. Maintains…

★ 28kGrade B
baoyu-slide-deck✓SAFE

jimliu/baoyu-skills

Generates professional slide deck images from content. Creates outlines with style instructions, then generates individual slide images. Use when user asks to "create slides", "make a presentation", "generate deck",…

★ 27kGrade B
baoyu-translate✓SAFE

jimliu/baoyu-skills

This skill should be used when the user asks to "translate", "翻译", "精翻", "translate article", "translate to Chinese", "translate to English", "改成中文", "改成英文", "convert to Chinese", "localize", "本地化", "refined…

★ 27kGrade B
baoyu-post-to-weibo✓SAFE

jimliu/baoyu-skills

Posts content to Weibo (微博). Supports regular posts with text, images, and videos, and headline articles (头条文章) with Markdown input via Chrome CDP. Use when user asks to "post to Weibo", "发微博", "发布微博", "publish to…

★ 27kGrade B
baoyu-post-to-x✓SAFE

jimliu/baoyu-skills

Posts content and articles to X (Twitter). Supports regular posts with images/videos and X Articles (long-form Markdown). In Codex, honor explicit requests for the Codex Chrome plugin/@chrome by using the Chrome…

★ 27kGrade B

Add this badge to your README

[![ModelsAtlas: CAUTION B](https://modelsatlas.com/skills/jimliu/baoyu-url-to-markdown/badge.svg)](https://modelsatlas.com/skills/jimliu/baoyu-url-to-markdown/)

Questions about baoyu-url-to-markdown

Is baoyu-url-to-markdown safe to install?
With care. The audit graded it B (89/100) and found 9 things worth knowing before you trust this skill, listed below with the exact line each was found on.
What can baoyu-url-to-markdown 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 baoyu-url-to-markdown work with?
Its documentation mentions openclaw. 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 (e63a35febc0c), read on 2026-11-13. The repository is watched, and a new audit runs when it changes — this is the first audit.

Sources

Spotted something wrong? Report a correction · Methodology

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.