CtrlK
BlogDocsLog inGet started
Tessl Logo

web-content-fetcher

网页内容获取工具 | 当常规爬虫被过滤时,使用替代服务获取网页内容。支持:1) r.jina.ai - 最稳定 2) markdown.new - Cloudflare 专用 3) defuddle.md - 备用方案。触发词:获取网页内容、网页转markdown、内容抓取、fetch webpage、bypass cloudflare

64

Quality

77%

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

Fix and improve this skill with Tessl

tessl review fix ./configs/microservice/bff-service/configs/agent-skills/clawhub/web-content-fetcher/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

71%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 concise, mostly actionable body with a clear fallback workflow and well-organized sections. Its main weakness is a broken reference to a fetch.sh script that does not exist in the bundle, and an undefined fetch_webpage API form that is not executable.

Suggestions

Either include the referenced fetch.sh under scripts/ or remove the '工具脚本' and 'API 格式' sections so every mentioned artifact actually exists.

Reconcile the two invocation styles: pick one concrete interface (the curl commands or the fetch.sh script) and drop the undefined 'fetch_webpage <url> --method ...' pseudocode.

Spell out the inter-service fallback as explicit steps (if r.jina.ai fails or returns empty, try markdown.new, then defuddle.md) so the priority table becomes an executable workflow.

DimensionReasoningScore

Conciseness

Mostly lean with a table and executable curl snippets and no padding about concepts Claude already knows; the curl examples partially duplicate the usage column of the services table, which is a minor instance of content that could be trimmed, keeping it below 5.

4 / 5

Actionability

Provides concrete, copy-paste-ready curl commands and fetch.sh invocations covering the common cases; the 'API 格式' section's fetch_webpage <url> --method ... form is not tied to a defined executable, a minor gap that prevents a 5.

4 / 5

Workflow Clarity

Gives a clear two-step sequence (try web_fetch first, fall back to this tool when filtered) plus a priority-ordered service table; this is a read-only skill so the destructive/batch validation cap does not apply, but the inter-service fallback (try jina, then markdown, then defuddle) is implied rather than spelled out as steps, so it is not a 5.

4 / 5

Progressive Disclosure

The body is well organized into clear sections, but it references a 'fetch.sh' script ('本目录包含 fetch.sh 脚本') that is not present in the bundle — a dangling reference rather than the clear, backed navigation expected at anchor 4.

3 / 5

Total

15

/

20

Passed

Description

83%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 strong description that names a distinct niche, lists three concrete fallback services with their scenarios, and supplies explicit bilingual trigger words. Both the 'what' and 'when' are clearly and concretely answered.

DimensionReasoningScore

Specificity

Lists several concrete items — three named fallback services (r.jina.ai, markdown.new, defuddle.md) each with a specific use case (most stable, Cloudflare-specific, backup) — matching the 'lists several specific actions; minor gaps' anchor; not a 5 because all three are variations of one fetch action rather than distinct capabilities.

4 / 5

Completeness

Explicitly answers both what ('使用替代服务获取网页内容' plus three named services) and when ('当常规爬虫被过滤时' plus a concrete trigger-word clause), matching the anchor for clearly and explicitly answering both with concrete trigger phrases.

5 / 5

Trigger Term Quality

Provides an explicit trigger-word list covering both Chinese and English synonyms ('获取网页内容、网页转markdown、内容抓取、fetch webpage、bypass cloudflare') for good keyword coverage; not a 5 because a few natural variations (e.g. 'scrape webpage', 'extract web content') are absent.

4 / 5

Distinctiveness Conflict Risk

Has a clear niche — a fallback fetcher used only when regular crawlers are filtered, with distinct triggers like 'bypass cloudflare' — but carries minor overlap risk with a general web-fetch skill, so it sits below the minimal-conflict anchor of 5.

4 / 5

Total

17

/

20

Passed

Validation

81%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

13

/

16

Passed

Repository
UnicomAI/wanwu
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.