Name: web-to-markdown
Rating: 46.400000000000006 (1 reviews)
Author: bear2u

Blog Docs Log in Get started

web-to-markdown

웹페이지 URL을 입력받아 마크다운 형태로 변환하여 저장합니다. 웹 문서를 로컬 마크다운 파일로 아카이빙하거나 정리할 때 유용합니다.

Quality

50%

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

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/web-to-markdown/SKILL.md

The canonical home for this skill is web-to-markdown in bear2u/my-skills

Quality

Content

46%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 is actionable with concrete WebFetch/Playwright guidance and a reasonable workflow, but it is heavily verbose with duplicated templates and no progressive disclosure, inlining large blocks that should live in separate reference files.

Suggestions

Extract the full AI-optimized prompt template into a reference file (e.g. references/ai-optimized-prompt.md) and reference it once instead of duplicating it verbatim in Step 4 and Dual Mode Step 3.

Move the detailed Dynamic Content Handling / Playwright fallback section into a separate references/dynamic-content.md and keep only a short decision summary in SKILL.md.

Add per-URL validation/checkpoints to the batch conversion workflow (verify each converted file is non-empty and non-trivial) to lift workflow_clarity above the batch cap.

Dimension	Reasoning	Score
Conciseness	At ~770 lines the body is noticeably verbose: the full AI-optimized prompt template is duplicated verbatim twice (~70 lines each), with repeated example dialogues, emoji output blocks, and minor over-explanation of WebFetch caching, fitting the 'noticeably verbose; several unnecessary explanations or padded sections' anchor rather than a single padded section.	2 / 5
Actionability	Provides copy-paste WebFetch prompts, Write tool examples, AskUserQuestion JSON, and Playwright scripts that are mostly executable, matching 'mostly executable guidance with minor gaps'; gaps are the placeholder content, hard-coded personal paths, and a pseudo MCP call.	4 / 5
Workflow Clarity	A clear multi-step workflow with a validation checkpoint (len < 500) and error handling exists, but batch/multi-URL conversion lacks per-item validation, and the rubric caps batch operations without validation at 3.	3 / 5
Progressive Disclosure	No bundle files exist and all content is inlined into one ~770-line SKILL.md; the duplicated prompt template and long dynamic-content/dual-mode sections clearly belong in separate reference files, matching the 'minimal structure; content that clearly belongs in separate files is inlined' anchor, lifted above 1 by present section headers.	2 / 5
	Total	11 / 20 Passed

Description

53%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 clearly communicates a focused capability (convert webpages to local markdown) with a few concrete actions, but lacks an explicit trigger clause and broad keyword coverage, leaving completeness and trigger quality at mid-level.

Suggestions

Add an explicit 'Use when ...' trigger clause listing concrete user phrasings (e.g., 'Use when the user wants to save a webpage as markdown, archive web content, or build AI-optimized context files').

Expand trigger terms with synonyms and file extensions such as .md, 웹 문서, 웹사이트, 블로그 글 to improve keyword coverage.

Reflect the AI-optimized and dual modes in the description so the capability set reads as comprehensive rather than 1-2 actions.

Dimension	Reasoning	Score
Specificity	Names the domain (webpage to markdown) with concrete actions (변환하여 저장, 아카이빙) but coverage is limited to 1-2 actions and omits the AI-optimized/dual modes described in the body, fitting the 'names domain and 1-2 concrete actions' anchor.	3 / 5
Completeness	Has a clear 'what' (변환하여 저장) but the 'when' is only a soft '유용합니다' clause with no explicit 'Use when...' trigger guidance, which per the rubric caps completeness at 3.	3 / 5
Trigger Term Quality	Includes relevant natural terms (웹페이지, URL, 마크다운, 아카이빙) but misses common synonyms and file extensions (.md, 웹 문서), matching the 'some relevant keywords but missing common variations' anchor rather than full coverage.	3 / 5
Distinctiveness Conflict Risk	The web-to-markdown niche is clearly distinct from generic document skills with only minor overlap risk, matching the 'mostly distinct; minor overlap risk' anchor and clearly above the broad 'works with document files' anchor.	4 / 5
	Total	13 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (774 lines); consider splitting into references/ and linking	Warning
relative_links	Relative link issues: 4 missing, 4 suspicious	Warning

	Total	14 / 16 Passed

Repository: bear2u/my-skills
Path: .claude/skills/web-to-markdown/SKILL.md
Commit: 8ed5784

Reviewed: 10 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.