baoyu-url-to-markdown
Fetch any URL and convert to markdown using Chrome CDP. Supports two modes - auto-capture on page load, or wait for user signal (for pages requiring login). Use when user wants to save a webpage as markdown.
Install with Tessl CLI
npx tessl i github:jimliu/baoyu-skills --skill baoyu-url-to-markdown85
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillAgent success when using this skill
Validation for skill structure
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 explains the skill's capabilities and when to use it. The two-mode explanation (auto-capture vs user signal) adds valuable specificity. The main weakness is limited trigger term coverage - users might describe this task using words like 'scrape', 'download', or 'capture' that aren't included.
Suggestions
Expand trigger terms to include common variations: 'scrape', 'download page', 'capture website', 'web page', 'save site'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists specific concrete actions: 'Fetch any URL', 'convert to markdown', 'using Chrome CDP', and describes two distinct modes (auto-capture vs wait for user signal). Also mentions specific use case of pages requiring login. | 3 / 3 |
Completeness | Clearly answers both what ('Fetch any URL and convert to markdown using Chrome CDP' with two modes explained) and when ('Use when user wants to save a webpage as markdown') with explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes some natural terms like 'URL', 'webpage', 'markdown', but misses common variations users might say such as 'web page', 'website', 'scrape', 'download page', 'capture page', or 'save website'. | 2 / 3 |
Distinctiveness Conflict Risk | Very specific niche combining URL fetching, Chrome CDP, and markdown conversion. The mention of login-required pages and two capture modes makes it highly distinctive from generic web or document skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides highly actionable, well-structured guidance for URL-to-markdown conversion with clear workflows and validation steps. However, it suffers from verbosity, particularly in the configuration/preferences section which could be more concise or split into reference files. The core functionality documentation is excellent with executable examples.
Suggestions
Move the detailed first-time setup flow and EXTEND.md configuration details to a separate reference file, keeping only a brief summary in the main skill
Condense the preferences section tables - the ASCII-art tables add visual noise without proportional value
Remove redundant explanations like 'This is a BLOCKING operation' which could be conveyed more concisely
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill contains useful information but is verbose in places, particularly the extensive EXTEND.md setup section and the detailed first-time setup flow. Some tables could be condensed, and the preferences section is overly detailed for what could be simpler configuration. | 2 / 3 |
Actionability | Provides fully executable bash and CLI commands with clear examples. The usage section has copy-paste ready commands, options are well-documented in tables, and the workflow steps are concrete and specific. | 3 / 3 |
Workflow Clarity | Multi-step processes are clearly sequenced with explicit checkpoints. The wait mode workflow, media download workflow, and first-time setup flow all have numbered steps with clear decision points and validation (checking for remote media, user confirmation before proceeding). | 3 / 3 |
Progressive Disclosure | References external file (references/config/first-time-setup.md) appropriately, but the main skill file is quite long with detailed inline content that could be split. The EXTEND.md configuration details and first-time setup could be moved to reference files. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
100%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 / 11 Passed
Validation for skill structure
No warnings or errors.
- 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.