web-reader

Read web pages, articles, and document links by converting URLs into Markdown text. Use the `read_url` tool directly, without bash.

Quality

78%

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 ./a_全网优秀资源/10_大模型/07_skill包/vibe_trading_skills/web-reader/SKILL.md

Quality

Content

86%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.

A tight, executable single-purpose skill: the tool call, return format, and failure modes are all concrete with essentially zero filler. The only real improvements are trimming the redundant 'Common Usage' examples and making the 451 fallback concrete.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes competence (no explanation of what URLs or Markdown are), but the 'Common Usage' section repeats the exact same read_url call three times with only the URL swapped, which is padding relative to the Usage section that already shows the call.	4 / 5
Actionability	The invocation 'read_url(url="https://tushare.pro/document/2?doc_id=27")' is copy-paste ready, the JSON response shape is documented so output handling is unambiguous, and the Notes cover concrete edge cases (8000-char truncation, HTTP 451, SPA skeleton HTML).	5 / 5
Workflow Clarity	This is a simple single-action skill and the action is unambiguous, with limitations and a fallback documented; however the fallback 'fall back to bash + requests' gives no concrete command or check on the response 'status' field, leaving a minor gap in the error-recovery path.	4 / 5
Progressive Disclosure	The skill is under 50 lines with no need for external references, and content is organized into clear sections (Purpose, Usage, Notes, Common Usage), which satisfies the simple-skill exception for a top score.	5 / 5
	Total	18 / 20 Passed

Description

61%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.

A concise, concrete description that clearly states what the skill does and names its tool, but it omits any explicit 'when to use' trigger clause, which is its main weakness and caps completeness. Trigger-term coverage is good though missing a few common synonyms.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks to read, fetch, or summarize a URL, web page, article, or online documentation.'

Broaden natural trigger synonyms to include terms like 'fetch this link', 'webpage', and 'documentation' so the skill surfaces for phrasings beyond 'web pages' and 'articles'.

State what the Markdown output enables (e.g. 'for analysis, summarization, or quoting') to sharpen the capability picture without adding length.

Dimension	Reasoning	Score
Specificity	The description names the domain (web pages, articles, document links) and one concrete action ('converting URLs into Markdown text'), but lists no other capabilities, matching the '1-2 concrete actions, not comprehensive' anchor. It is not a 4 because no second distinct action is enumerated; not a 2 because the action named is specific rather than generic.	3 / 5
Completeness	The 'what' is clear (read web content by converting URLs to Markdown), but there is no 'Use when...' clause or equivalent trigger guidance — 'Use the read_url tool directly, without bash' is invocation instruction, not a when-to-use trigger, which caps completeness at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	'web pages', 'articles', 'document links', and 'URLs' are natural phrases users would say when needing this skill, giving good coverage. Missing common variations like 'fetch this link', 'webpage', or 'documentation' keeps it below the comprehensive-synonym anchor of 5.	4 / 5
Distinctiveness Conflict Risk	Naming the read_url tool and URL-to-Markdown conversion carves a clear niche, but 'Read web pages, articles' could overlap with a generic web-fetch/search skill at the trigger-matching stage, giving minor overlap risk consistent with the 'mostly distinct' anchor.	4 / 5
	Total	14 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: charliedream1/ai_quant_trade
Path: a_全网优秀资源/10_大模型/07_skill包/vibe_trading_skills/web-reader/SKILL.md
Commit: b612402

Reviewed: 3 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.