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.
68
85%
Does it follow best practices?
Impact
—
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 communicates what the skill does and when to use it, with good specificity about supported platforms and capabilities. The main weakness is in trigger term coverage—it leans toward technical terminology (Chrome CDP, Defuddle, baoyu-fetch) rather than natural user language, and the 'Use when' clause is somewhat narrow ('save a webpage as markdown') compared to the breadth of scenarios users might describe.
Suggestions
Expand trigger terms to include natural user phrases like 'scrape', 'download page content', 'read a website', 'grab text from a link', 'fetch article', or 'extract content from URL'.
Broaden the 'Use when' clause to cover more scenarios, e.g., 'Use when user wants to fetch, scrape, read, or save content from a URL or webpage, especially from Twitter/X, YouTube, or Hacker News.'
| 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 any URL and convert to markdown using baoyu-fetch CLI') and when ('Use when user wants to save a webpage as markdown'). The 'Use when' clause is explicit, though it could be broader to cover more trigger scenarios. | 3 / 3 |
Trigger Term Quality | Includes some natural terms like 'URL', 'webpage', 'markdown', 'YouTube transcripts', 'Hacker News', but misses common user phrasings like 'scrape', 'download page', 'read website', 'grab content from a link', or 'web page to text'. The tool name 'baoyu-fetch' and 'Chrome CDP' are technical jargon unlikely to be used by users. | 2 / 3 |
Distinctiveness Conflict Risk | Very distinct niche: URL fetching and markdown conversion via a specific CLI tool with named site-specific adapters. Unlikely to conflict with other skills due to the specific tool name, supported sites, and clear use case. | 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-structured, highly actionable skill with clear workflows, explicit validation checkpoints (quality gate, blocking first-time setup), and good progressive disclosure to reference files. Its main weakness is moderate verbosity — some sections could be tightened (User Input Tools preamble, redundant Extension Support section, some explanatory text around tables) without losing clarity. Overall it's a strong skill that effectively guides Claude through a complex CLI tool with multiple modes and configurations.
Suggestions
Remove or condense the 'User Input Tools' section — Claude can infer tool-selection priority without a 3-point rule; a single sentence like 'Use the runtime's built-in user-input tool (e.g., AskUserQuestion) or fall back to plain-text prompts' suffices.
Remove the 'Extension Support' section at the bottom as it adds no new information beyond what the Preferences section already covers.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly detailed and well-organized, but includes some redundancy (e.g., the 'Extension Support' section at the end just points back to the Preferences section, the troubleshooting line could be tighter, and the EXTEND.md/CLI mapping table partially duplicates information). The first-time setup flow is thorough but verbose for what it conveys. Some sections like 'User Input Tools' explain tool-selection logic Claude could infer. | 2 / 3 |
Actionability | The skill provides fully executable CLI commands with concrete examples, a clear setup sequence with exact paths and commands, specific option tables, and a well-defined output path generation algorithm. The first-time setup questions are precisely specified with exact wording and options. | 3 / 3 |
Workflow Clarity | Multi-step processes are clearly sequenced: CLI setup has numbered steps, first-time setup is marked as BLOCKING with explicit flow, the quality gate mandates post-run inspection with a reference to a full checklist and recovery workflow, and the output path generation has a clear algorithm with conflict resolution. The feedback loop for headless capture quality issues is explicitly called out. | 3 / 3 |
Progressive Disclosure | The skill provides a clear overview with well-signaled one-level-deep references to supporting 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 at the right level of detail while pointing to deeper content. Note: bundle files weren't provided for verification, but the structure and references are well-organized. | 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
bd5745f
- 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.