web-search-linkup

Web search and content fetching - search the web or extract content from URLs

Quality

55%

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 ./skills/research-tools/capabilities/web-search-linkup/SKILL.md

Quality

Content

60%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 content is a clean, sectioned API skill with executable setup and a working fetch example, but the primary search example is malformed and there is some duplicated phrasing. Adding validation guidance and fixing the example would raise quality.

Suggestions

Fix the /search curl example so the JSON body is valid and executable (move q/depth/outputType inside the body object and close it correctly).

Remove the duplicated '/search endpoint allows you to retrieve web content' line and the redundant capabilities sentence to tighten conciseness.

Add a brief validation/error-handling step after API calls (e.g. check HTTP status, surface error messages) to lift workflow clarity toward 5.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with necessary parameter reference, but 'The /search endpoint allows you to retrieve web content' is duplicated (Capabilities and Usage) and line 23 repeats it, adding padding that fits anchor 3 over 4.	3 / 5
Actionability	Concrete curl commands are provided, but the /search example JSON is malformed (the object closes after "path":"/search" then leaves q/depth/outputType as loose lines before a trailing }'), so the primary example is not executable as written, matching anchor 3.	3 / 5
Workflow Clarity	A clear sequence is present (read credentials, set auth header, call endpoint) with a fallback instruction ('npx gooseworks login'), fitting anchor 4; not 5 because there are no explicit validation or error-handling checkpoints after API calls.	4 / 5
Progressive Disclosure	Single-file skill with well-organized sections (Setup, Capabilities, Usage, Use Cases, Discover More) and a dynamic 'Discover More' mechanism for deeper detail, fitting anchor 4; not 5 because the full inline parameter reference could be split out and there are no signaled one-level references.	4 / 5
	Total	14 / 20 Passed

Description

50%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 states the skill's purpose and two concrete actions but lacks any explicit trigger guidance and relies on only a couple of natural keywords. It is adequate but not exemplary.

Suggestions

Add a 'Use when...' clause naming concrete triggers, e.g. 'Use when the user asks to search the web, look up current information, or fetch/extract content from a URL.'

Broaden trigger terms with synonyms and extensions users actually say (look up, scrape, fetch URL, .html pages) to improve distinctiveness.

Specify a few more concrete actions (e.g. retrieve sourced answers, filter by date or domain) to lift specificity toward anchor 4-5.

Dimension	Reasoning	Score
Specificity	Quotes 'Web search and content fetching' and 'search the web or extract content from URLs' name the domain plus two concrete actions, matching anchor 3; not 4 because it does not list several specific actions.	3 / 5
Completeness	It gives a clear 'what' (web search and content fetching) but no 'Use when...' trigger guidance, so per the cap it cannot exceed 3; anchor 3 is the best fit.	3 / 5
Trigger Term Quality	Phrases 'search the web' and 'extract content from URLs' are natural, but common synonyms like 'look up', 'scrape', 'Google', or 'fetch URL' are missing, fitting anchor 3 rather than 4.	3 / 5
Distinctiveness Conflict Risk	'Web search and content fetching' is a recognizable niche but overlaps with other generic web-search/fetch skills, matching anchor 3 rather than the more distinct anchor 4.	3 / 5
	Total	12 / 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: gooseworks-ai/goose-skills
Path: skills/research-tools/capabilities/web-search-linkup/SKILL.md
Commit: 2523432

Reviewed: 7 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.