tessl install https://github.com/softaworks/agent-toolkit --skill web-to-markdowngithub.com/softaworks/agent-toolkit
Use ONLY when the user explicitly says: 'use the skill web-to-markdown ...' (or 'use a skill web-to-markdown ...'). Converts webpage URLs to clean Markdown by calling the local web2md CLI (Puppeteer + Readability), suitable for JS-rendered pages.
Average Score
78%
Content
77%
Description
70%
Generated
Validations
Total score
13/16| Criteria | Score |
|---|---|
skill_md_line_count SKILL.md line count is 78 (<= 500) | |
frontmatter_valid YAML frontmatter is valid | |
name_field 'name' field is valid: 'web-to-markdown' | |
description_field 'description' field is valid (246 chars) | |
description_voice 'description' uses third person voice | |
description_trigger_hint Description includes an explicit trigger hint | |
compatibility_field 'compatibility' field not present (optional) | |
allowed_tools_field 'allowed-tools' field not present (optional) | |
metadata_version 'metadata.version' is present: 0.1.0 | |
metadata_field 'metadata' contains 1 entry | |
license_field 'license' field is missing | |
frontmatter_unknown_keys No unknown frontmatter keys found | |
body_present SKILL.md body is present | |
body_examples No examples detected (no code fences and no 'Example' wording) | |
body_output_format Output/return/format terms detected | |
body_steps No step-by-step structure detected (no ordered list); consider adding a simple workflow |
Content
Suggestions 2
Total score
10/12| Dimension | Score |
|---|---|
conciseness Content is mostly efficient but includes some unnecessary explanation (e.g., 'Handles JS-rendered pages (Puppeteer → user Chrome)' and browser compatibility notes that Claude would understand). The input options list is comprehensive but could be more compact. | 2/3 |
actionability Provides fully executable commands for all scenarios: single URL, batch processing, interactive mode, stdout output. Commands are copy-paste ready with clear flag explanations and concrete examples. | 3/3 |
workflow_clarity Clear 6-step workflow with explicit validation checkpoint (step 5: verify files exist and are non-empty). Includes installation verification step and specific commands for different scenarios. The interactive mode workflow includes clear human-in-the-loop instructions. | 3/3 |
progressive_disclosure Content is well-organized with clear sections, but the optional rendering controls list is lengthy and could be moved to a separate reference file. For a skill of this size (~80 lines), inline content is acceptable but borders on too much detail in one file. | 2/3 |
Suggestions
Remove explanatory phrases like 'Works best with Chromium-family browsers' and 'Extracts main content (Readability)' - Claude understands these concepts
Consider moving the full list of optional rendering controls to a separate REFERENCE.md file, keeping only the most common flags inline
Overall Assessment
This is a well-structured skill with excellent actionability and workflow clarity. The explicit trigger gate enforcement is appropriate for a specialized tool. Minor improvements could be made in conciseness by trimming explanatory text Claude doesn't need, and the extensive options list could potentially be externalized for better progressive disclosure.
Description
Suggestions 2
Total score
10/12| Dimension | Score |
|---|---|
specificity Lists specific concrete actions: 'Converts webpage URLs to clean Markdown by calling the local web2md CLI (Puppeteer + Readability), suitable for JS-rendered pages.' This describes the exact mechanism and capability. | 3/3 |
completeness Clearly answers both what ('Converts webpage URLs to clean Markdown by calling the local web2md CLI') and when ('Use ONLY when the user explicitly says: use the skill web-to-markdown'). The when clause is explicit, even if overly restrictive. | 3/3 |
trigger_term_quality The trigger terms are artificially restrictive ('explicitly says: use the skill web-to-markdown') rather than natural user language. Users would naturally say 'convert this webpage to markdown' or 'get the content from this URL', not the prescribed phrase. | 1/3 |
distinctiveness_conflict_risk Very distinct niche - specifically for converting webpages to Markdown using a particular CLI tool. The explicit trigger requirement and specific technology stack (Puppeteer + Readability) make conflicts unlikely. | 3/3 |
Suggestions
Replace the artificial trigger phrase with natural user language like 'Use when the user wants to convert a webpage to markdown, fetch URL content as text, or mentions web2md, webpage extraction, or JS-rendered pages'
Add common variations users might say: 'scrape webpage', 'get page content', 'URL to markdown', 'extract article from URL'
Overall Assessment
The description excels at specificity and completeness, clearly explaining what the skill does and providing explicit trigger guidance. However, the trigger terms are artificially restrictive, requiring users to say a specific phrase rather than using natural language like 'convert webpage to markdown' or 'fetch URL content'. This defeats the purpose of skill selection since users won't naturally use the prescribed phrase.