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.
85
85%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
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 the tool, its capabilities, and supported platforms. The specificity and distinctiveness are excellent, with concrete actions and named adapters. The main weakness is the trigger term coverage—the 'Use when' clause is somewhat narrow and doesn't capture the variety of ways users might request webpage content fetching or scraping.
Suggestions
Expand the 'Use when...' clause to include more natural trigger phrases like 'scrape a website', 'read a URL', 'get content from a page', 'fetch an article', or 'download webpage content'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: fetch URLs, convert to markdown, handle X/Twitter, YouTube transcripts, Hacker News threads, generic pages via Defuddle, and handle login/CAPTCHA via interaction wait modes. | 3 / 3 |
Completeness | Clearly answers both 'what' (fetch URLs, convert to markdown, site-specific adapters for various platforms, handle login/CAPTCHA) and 'when' (explicit 'Use when user wants to save a webpage as markdown'). | 3 / 3 |
Trigger Term Quality | Includes some good natural terms like 'URL', 'markdown', 'webpage', 'YouTube transcripts', 'Hacker News', and 'X/Twitter', but the 'Use when' clause is narrow ('save a webpage as markdown') and misses common user phrasings like 'scrape', 'read this page', 'get content from', 'fetch article', or 'download page'. | 2 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with specific tool name (baoyu-fetch CLI), specific technology (Chrome CDP), and a clear niche of URL-to-markdown conversion with named site adapters. Unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-crafted skill with strong actionability, clear workflow sequencing with validation checkpoints, and excellent progressive disclosure through well-organized reference files. The main weakness is moderate verbosity — the User Input Tools section, the detailed first-time setup flow, and some redundant sections (Extension Support repeating Preferences) add tokens without proportional value. Overall it's a high-quality skill that could benefit from trimming.
Suggestions
Remove or significantly condense the 'User Input Tools' section — Claude can handle tool selection without 3 priority rules and examples of tool names.
Remove the redundant 'Extension Support' section at the bottom since it just points back to the Preferences section already covered in detail.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly well-structured but includes some redundancy — the EXTEND.md section is quite verbose with the first-time setup flow, the 'Extension Support' section at the end is redundant, and the CLI mapping tables could be tighter. Some sections like 'User Input Tools' explain things Claude likely already knows how to handle. | 2 / 3 |
Actionability | Provides fully executable CLI commands with concrete examples, specific flags, and clear option tables. The setup instructions are step-by-step with exact paths and commands. The output path generation algorithm is specific and implementable. | 3 / 3 |
Workflow Clarity | The workflow is well-sequenced: setup CLI → check/create EXTEND.md → run fetch → quality gate inspection → handle failures. The quality gate after headless runs is an explicit validation checkpoint, and the first-time setup is clearly marked as BLOCKING. Recovery paths are referenced for suspicious results. | 3 / 3 |
Progressive Disclosure | Excellent use of progressive disclosure with clear one-level-deep references to separate files: references/quality-gate.md for the quality checklist, references/adapters.md for adapter details, and references/config/first-time-setup.md for the setup template. The main SKILL.md stays as an overview with well-signaled links. | 3 / 3 |
Total | 11 / 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
505a7e1
- 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.