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.

Quality

84%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

86%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable and well-structured, with executable commands, a complete options table, and clean progressive disclosure to three verified reference files. It could tighten the User Input Tools section and surface the quality-gate recovery loop inline to lift conciseness and workflow clarity to the top anchor.

Suggestions

Tighten the User Input Tools section by collapsing the three numbered priority rules and the runtime-substitution note into one or two lines, since most agents only need the prefer-built-in-then-fallback rule.

Add a brief inline validate→recover loop (e.g., "if the markdown looks thin or empty, switch capture mode or re-run with --wait-for interaction") instead of deferring the entire recovery workflow to references/quality-gate.md.

Drop or compress the EXTEND.md "supported keys" duplication between the First-Time Setup Q&A and the Supported Keys table to reduce repeated content.

Dimension	Reasoning	Score
Conciseness	The body is largely lean, relying on tables and concrete commands without explaining concepts Claude already knows, but the User Input Tools priority list and runtime-substitution notes are minor over-explanation that could be trimmed, matching the efficient-but-slightly-trimmable score-4 anchor rather than the fully lean score-5.	4 / 5
Actionability	It provides copy-paste-ready ${READER} commands covering default, save, media, interaction-wait, JSON, and forced-adapter cases, a full options table with concrete defaults, and a numbered output-path algorithm with conflict resolution, matching the fully executable score-5 anchor.	5 / 5
Workflow Clarity	Numbered CLI setup, a priority-ordered EXTEND.md lookup, a blocking first-time setup, and a post-run quality-gate checkpoint give a clear sequenced workflow, but the full validate→fix→retry recovery loop is delegated to references/quality-gate.md rather than stated inline, a minor gap that fits score 4 instead of 5.	4 / 5
Progressive Disclosure	SKILL.md is a clear overview with three one-level-deep, well-signaled references (first-time-setup.md, quality-gate.md, adapters.md) that each exist as real files and are introduced with explicit read-when context, matching the clear-overview score-5 anchor; it is not a 4 because content is appropriately split and navigation is easy.	5 / 5
	Total	18 / 20 Passed

Description

83%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific, distinctive, and clearly answers both what the skill does and when to use it, with concrete adapter and login/CAPTCHA capabilities. Its main limitation is a single, slightly generic trigger phrase and missing common synonyms, which keeps trigger-term quality and completeness just below the top anchor.

Dimension	Reasoning	Score
Specificity	"Fetch any URL and convert to markdown", "Built-in adapters for X/Twitter, YouTube transcripts, Hacker News threads, and generic pages via Defuddle", and "Handles login/CAPTCHA via interaction wait modes" list multiple specific concrete actions with comprehensive coverage, matching the score-5 anchor; it is not a 4 because coverage is broad rather than having minor gaps.	5 / 5
Completeness	It has a detailed explicit "what" and an explicit "when" ("Use when user wants to save a webpage as markdown"), but the trigger is a single generic clause rather than the multiple concrete trigger phrases in the score-5 anchor, placing it at 4.	4 / 5
Trigger Term Quality	Natural terms like "save a webpage as markdown", "URL", "markdown", and "fetch" give good keyword coverage, but common synonyms such as scrape, article, or HTML-to-markdown are absent, so it falls below the comprehensive score-5 anchor and aligns with score 4.	4 / 5
Distinctiveness Conflict Risk	The Chrome CDP + site-specific adapter niche with named adapters (X/Twitter, YouTube, HN) and the baoyu-fetch CLI form a clear, distinct trigger set with minimal conflict risk, matching the score-5 anchor; it is not a 4 because overlap risk is negligible.	5 / 5
	Total	18 / 20 Passed

Validation

68%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 11 / 16 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
relative_links	Relative link issues: 1 deeper-than-1-level	Warning
referenced_paths_exist	Referenced path issues: 2 deeper-than-1-level	Warning

	Total	11 / 16 Passed

Repository: JimLiu/baoyu-skills
Path: skills/baoyu-url-to-markdown/SKILL.md
Commit: 1567581

Reviewed: 13 days ago

Table of Contents

Discovery Implementation Validation

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.