web-search-andi

Fast, high-quality web search with intelligent ranking and instant answers

Quality

67%

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-andi/SKILL.md

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a tight, actionable API reference with executable curl examples, a complete parameter list, and a clean setup-to-search workflow. Its only real flaw is the marketing tagline repeated three times, which wastes tokens without adding information.

Dimension	Reasoning	Score
Conciseness	The parameter reference and curl examples are dense and earn their tokens, but the marketing tagline 'Fast, high-quality search with intelligent ranking, instant answers...' is repeated nearly verbatim three times (intro, Capabilities, Usage). Removing the redundant repetitions would tighten it to the top anchor.	2 / 3
Actionability	Provides a fully executable, copy-paste-ready curl call with real endpoint, auth header, and request body, plus a complete typed parameter list and executable 'Discover More' commands. Claude can act on this directly without inference.	3 / 3
Workflow Clarity	As a simple single-purpose API skill, the flow is clear and well-sequenced: read credentials (with an explicit fallback telling the user to run 'npx gooseworks login'), then call the search endpoint. The setup branch is an explicit checkpoint and no destructive/batch validation is needed.	3 / 3
Progressive Disclosure	A self-contained single file (no bundle files exist) organized into clear sections (Setup, Capabilities, Usage, Use Cases, Discover More), with the 'Discover More' block acting as a well-signaled one-level-deep pointer to full endpoint details via the live API rather than dumping everything inline.	3 / 3
	Total	11 / 12 Passed

Description

50%

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 reads as a product tagline: it conveys the core capability (web search) but leans on marketing adjectives and omits any 'Use when' trigger guidance. It answers 'what' weakly and 'when' not at all, landing at the middle anchor across all dimensions.

Suggestions

Append an explicit trigger clause, e.g. 'Use when the user asks to search the web, look something up online, or find current information with sources.'

Replace buzzword padding ('Fast, high-quality', 'intelligent ranking', 'instant answers') with concrete actions Claude performs, such as 'Search the web, return ranked results with source extracts, and filter by domain, date, or content type.'

Add natural trigger-term variations users actually say ('search the web', 'look up', 'find online', 'research') to improve trigger coverage and reduce overlap with generic research skills.

Dimension	Reasoning	Score
Specificity	Names the domain and one concrete action ('web search') but pads it with buzzword adjectives ('Fast, high-quality', 'intelligent ranking', 'instant answers') rather than listing multiple specific actions. It is more concrete than 'Helps with documents' but does not reach the multi-action coverage of the top anchor.	2 / 3
Completeness	It answers 'what does this do' (web search with ranking/answers) but provides no 'Use when...' clause or equivalent explicit trigger guidance for when Claude should invoke it. Per the rubric, a missing 'Use when' clause caps completeness at 2.	2 / 3
Trigger Term Quality	'web search' and 'answers' are natural terms a user might say, but coverage is thin and missing common variations like 'look up', 'find information', or 'research'. It has some relevant keywords but not the broad coverage of the top anchor.	2 / 3
Distinctiveness Conflict Risk	'web search' is a recognizable niche, but the generic 'search'/'answers' framing and absence of explicit triggers mean it could overlap with other search or research skills. It is somewhat specific but not clearly fenced off from similar skills.	2 / 3
	Total	8 / 12 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-andi/SKILL.md
Commit: 8866b2a

Reviewed: 1 day 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.