CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

70

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

92%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 skill body is concise, well-structured, and highly actionable, with a clear validated workflow and error-recovery retries appropriate to a single-purpose fetch skill. The only minor gap is that fetching is described in terms of the abstract built-in tool rather than a concrete invocation.

DimensionReasoningScore

Conciseness

The body is lean and well-sectioned with no padding or explanations of concepts Claude already knows — e.g., "Build a conversion URL as `https://markdown.new/<target-url>`" states only what is needed; matches the 'lean and efficient, every token earns its place' anchor and is not a 4 since there are no over-explanation instances to trim.

5 / 5

Actionability

Provides concrete, executable guidance including the exact conversion URL pattern, parameter values (`method=auto|ai|browser`, `retain_images=true|false`), and a copy-paste example URL `https://markdown.new/https://example.com?method=browser&retain_images=true`; not a 5 because the actual fetch relies on the abstract "built-in fetch tool" rather than a fully specified invocation, and not a 3 because the steps and parameters are specific and usable.

4 / 5

Workflow Clarity

The four-step workflow has explicit validation checkpoints (malformed/missing URL, query parameters, tool unavailability) and feedback loops (retry with `method=browser` on empty results, `retain_images=true` for image-rich pages), plus a Failure Policy section; matches the anchor requiring explicit validation and error-recovery loops, and the simple-skill exception supports a 5.

5 / 5

Progressive Disclosure

Content is self-contained with no need for external references and is organized into clear, well-signaled sections (Use This Skill When, Do Not Use, Workflow, Optional Parameters, Examples, Failure Policy); per the simple-skills note, a self-contained skill with well-organized sections scores 5, and there is no nested or buried reference structure to penalize it.

5 / 5

Total

19

/

20

Passed

Description

78%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 clear, third-person, and explicitly covers both what the skill does and when to use it with natural trigger phrases. Its main limitation is specificity — it describes essentially one conversion action — and a minor overlap risk with general page-fetching skills.

DimensionReasoningScore

Specificity

Names the domain and one concrete action — "Retrieve the Markdown version of a public web page from a URL ... using ... markdown.new" — but lists only a single conversion action rather than several, matching the '1-2 concrete actions, not comprehensive' anchor; not a 2 because the action is concrete rather than generic, and not a 4 because no breadth of actions is enumerated.

3 / 5

Completeness

Explicitly answers both what ("Retrieve the Markdown version of a public web page from a URL using ... markdown.new") and when ("Use when a user asks for page content in Markdown ... or URL-to-Markdown conversion") with concrete trigger phrases, matching the top anchor; a 4 would require the 'when' to be less explicit, which it is not.

5 / 5

Trigger Term Quality

Includes natural user phrases like "page content in Markdown", "cleaner extracted page content for LLM use", and "URL-to-Markdown conversion", giving good keyword coverage with synonyms; not a 5 because coverage stops short of exhaustive synonyms/extensions, and not a 3 because multiple natural terms are present rather than just one generic keyword.

4 / 5

Distinctiveness Conflict Risk

The markdown.new niche is distinct with specific triggers, but the phrase "cleaner extracted page content for LLM use" overlaps with general web-fetch/browse skills, matching 'mostly distinct; minor overlap risk'; not a 5 because of that overlap, and not a 3 because the markdown.new mechanism is clearly specific.

4 / 5

Total

16

/

20

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
ceshine/ceshine-agent-skills
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.