baoyu-url-to-markdown
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.
76
73%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/baoyu-url-to-markdown/SKILL.mdQuality
Discovery
85%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong description that clearly identifies what the skill does (fetch URLs and convert to markdown with site-specific adapters) and when to use it. The specificity of naming concrete platforms and the explicit 'Use when' clause are excellent. The main weakness is that trigger terms could better cover natural user language like 'scrape', 'download page', or 'read website' instead of relying on technical terms like 'Chrome CDP' and 'Defuddle'.
Suggestions
Add more natural user-facing trigger terms such as 'scrape', 'download page', 'read website content', 'grab article', 'extract web content' to improve discoverability when users phrase requests colloquially.
Expand the 'Use when' clause to cover more trigger scenarios, e.g., 'Use when user wants to save a webpage as markdown, scrape a website, read a URL, download an article, or get a YouTube transcript.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: fetch URLs, convert to markdown, handle login/CAPTCHA, and names specific adapters for X/Twitter, YouTube transcripts, Hacker News threads. Also mentions the specific tool (baoyu-fetch CLI) and underlying technology (Chrome CDP). | 3 / 3 |
Completeness | Clearly answers both 'what' (fetch URLs, convert to markdown, handle login/CAPTCHA, site-specific adapters) and 'when' with an explicit trigger clause: 'Use when user wants to save a webpage as markdown.' | 3 / 3 |
Trigger Term Quality | Includes some good natural terms like 'URL', 'markdown', 'webpage', 'X/Twitter', 'YouTube transcripts', 'Hacker News'. However, it's missing common user phrasings like 'scrape', 'download page', 'read website', 'web content', 'fetch article', or 'save page'. The 'Chrome CDP' and 'Defuddle' terms are technical jargon users wouldn't naturally say. | 2 / 3 |
Distinctiveness Conflict Risk | Very distinct niche: fetching web pages and converting to markdown via a specific CLI tool. The mention of specific site adapters (X/Twitter, YouTube, Hacker News) and the specific tool name (baoyu-fetch) make it highly unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill is highly actionable with excellent workflow clarity, including quality gates and recovery flows that are well-structured. However, it is significantly too verbose for a SKILL.md — it reads more like comprehensive documentation than a concise skill file. Much of the content (adapter-specific notes, detailed option tables, output format schemas, configuration details) should be moved to reference files with clear links from the main skill.
Suggestions
Move the detailed Options table, Capture Modes table, Output Format details, and adapter-specific notes (YouTube, X/Twitter, HN) into separate reference files (e.g., references/options.md, references/adapters.md) and link to them from the main skill.
Condense the Preferences/EXTEND.md section significantly — move the full first-time setup flow and PowerShell/bash detection scripts to the already-referenced references/config/first-time-setup.md file.
Remove the Features bullet list entirely — it duplicates information already conveyed by the usage examples and options table.
Trim the Media Download Workflow section to just the decision table and a brief note about the ask-each-time flow, moving detailed steps to a reference file.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~300+ lines. It includes extensive detail about EXTEND.md configuration, first-time setup flows, media download workflows, environment variables, and adapter-specific notes that could be split into reference files. Many sections explain things Claude can infer (e.g., what each adapter does, basic troubleshooting tips). | 1 / 3 |
Actionability | The skill provides fully executable CLI commands, concrete examples for every mode, detailed option tables, and specific workflows with exact flags. The setup instructions, quality gate checks, and recovery workflows are all concrete and actionable. | 3 / 3 |
Workflow Clarity | Multi-step workflows are clearly sequenced with explicit validation checkpoints. The Agent Quality Gate section has a clear recovery workflow (headless → inspect → retry with interaction mode). The first-time setup is marked as BLOCKING with clear steps. The media download ask-each-time flow has numbered steps with decision points. | 3 / 3 |
Progressive Disclosure | There is one reference to an external file (references/config/first-time-setup.md), but the vast majority of content is inline in the SKILL.md. The detailed options table, adapter notes, capture modes, output format details, and media download workflow could all be split into reference files, keeping the main skill lean. The structure exists but content that should be separate is inline. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
72%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 8 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
metadata_field | 'metadata' should map string keys to string values | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 8 / 11 Passed | |
- Repository
- jimliu/baoyu-skills
- Commit
9eb032a
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.