markdown-dot-new
Retrieve the Markdown version of a public web page from a URL using the agent's built-in URL fetch capability and markdown.new. Use when a user asks for page content in Markdown, cleaner extracted page content for LLM use, or URL-to-Markdown conversion.
88
85%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
100%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 skill description that clearly communicates what the skill does (converts public web pages to Markdown via URL fetch and markdown.new), when to use it (explicit 'Use when' clause with multiple trigger scenarios), and uses natural language terms users would employ. It is concise, specific, and distinctive enough to avoid conflicts with related skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description lists concrete actions: 'Retrieve the Markdown version of a public web page from a URL' and specifies the tools used ('built-in URL fetch capability and markdown.new'). These are specific, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (retrieve Markdown version of a public web page using URL fetch and markdown.new) and 'when' (explicit 'Use when' clause covering page content in Markdown, cleaner extracted content for LLM use, or URL-to-Markdown conversion). | 3 / 3 |
Trigger Term Quality | Includes natural trigger terms users would say: 'Markdown', 'URL', 'page content', 'URL-to-Markdown conversion', 'extracted page content', 'web page'. These cover common variations of how users would phrase such requests. | 3 / 3 |
Distinctiveness Conflict Risk | The description carves out a clear niche: URL-to-Markdown conversion specifically. The mention of 'markdown.new' and the specific use case of converting web pages to Markdown makes it unlikely to conflict with general web scraping or generic Markdown editing skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
70%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 skill with clear workflow sequencing and good error handling guidance. Its main weakness is that it leans toward descriptive instructions rather than concrete, executable examples—the actionability could be improved with actual tool call examples. Some sections could be tightened to reduce token usage without losing clarity.
Suggestions
Add a concrete example showing the exact fetch tool invocation (e.g., the actual tool call with the constructed URL) rather than just describing the steps.
Trim the 'Use This Skill When' / 'Do Not Use This Skill When' sections—Claude can infer most of these conditions from the workflow itself; keep only non-obvious constraints like the query parameter limitation.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient but includes some unnecessary content. The 'Use This Skill When' and 'Do Not Use This Skill When' sections add moderate value but are somewhat verbose. The examples section listing user prompts doesn't add much actionable information. Some explanations like 'URLs with query strings would conflict with markdown.new's own query parameters' over-explain for Claude. | 2 / 3 |
Actionability | The workflow provides clear steps and the URL construction pattern is concrete (`https://markdown.new/<target-url>`), but there's no executable code—just descriptive instructions. The parameter example is helpful but the skill lacks a complete, copy-paste-ready fetch invocation. It describes what to do rather than showing exact tool calls. | 2 / 3 |
Workflow Clarity | The workflow is clearly sequenced with four numbered steps, each with explicit validation checkpoints (check URL validity, check tool availability, handle errors). Retry logic is well-specified with conditions for when to use `method=browser` or `retain_images=true`. The failure policy section provides a clear checklist of stop conditions. | 3 / 3 |
Progressive Disclosure | For a standalone skill with no bundle files, the content is well-organized into logical sections (when to use, when not to use, workflow, parameters, examples, failure policy). The structure is clean and navigable without being monolithic. No external references are needed for this simple, single-purpose skill. | 3 / 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.
- Repository
- ceshine/ceshine-agent-skills
- Commit
348c2c1
- 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.