web-search-andi

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

Quality

64%

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

67%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 body is a solid, actionable API reference: executable setup and search commands, complete parameter documentation, and a sensible discovery path for more details. Its main weaknesses are repeated marketing taglines and a broken 'Discover More' example, plus the absence of any response-format guidance.

Suggestions

Remove the duplicated taglines (after Setup, in Capabilities, and under Usage) and fold the one-bullet Capabilities section into the intro or delete it.

Fix the first Discover More curl: the trailing 'List all endpoints' text sits inside the code fence and breaks the command; move it to a comment or outside the block.

Add a short example response (result fields, answer/extract shape) so Claude knows how to interpret and present search results.

Dimension	Reasoning	Score
Conciseness	The parameter documentation is dense and assumes Claude's competence, but the tagline 'Fast, high-quality search with intelligent ranking, instant answers...' is repeated three times (after Setup, in Capabilities, and under Usage), and the single-bullet Capabilities section adds nothing. This matches 'mostly efficient but could be tightened' rather than anchor 4's 'minor instances'.	3 / 5
Actionability	Setup exports, the credential-failure path, the search curl example, and the full parameter list are concrete and mostly copy-paste ready. It falls short of anchor 5 because the first 'Discover More' curl has trailing prose ('List all endpoints') inside the code fence that breaks execution, and no example response shape is shown.	4 / 5
Workflow Clarity	This is a simple single-action skill: setup -> auth -> search is unambiguous, with an explicit checkpoint for missing credentials ('If ~/.gooseworks/credentials.json does not exist, tell the user to run: npx gooseworks login'). It is not 5 because there is no guidance on interpreting or validating the API response.	4 / 5
Progressive Disclosure	No bundle files exist and the body (~76 lines) is organized into clear sections (Setup, Usage, Use Cases, Discover More) with a discovery mechanism for further endpoint details. It is not 5 because the body exceeds 50 lines with a full inline parameter reference that could live in a separate file, and the duplicated tagline sections blur the structure.	4 / 5
	Total	15 / 20 Passed

Description

45%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 names the web-search domain but is padded with buzzwords and lacks any explicit 'when to use' trigger guidance. It would likely fire for generic search requests while giving Claude little concrete information about what the skill actually does.

Suggestions

Add an explicit trigger clause, e.g., 'Use when the user asks to search the web, look up current information, or find sources on a topic'.

Replace buzzwords ('intelligent ranking', 'instant answers') with concrete capabilities such as 'returns ranked web results with extracts, filters by date range, domain, and search intent (news, images, video)'.

State the what and when in third person with distinct trigger phrases (web search, online lookup, find sources) to reduce overlap with other search skills.

Dimension	Reasoning	Score
Specificity	The description names the domain ("web search") but relies on marketing buzzwords — "intelligent ranking", "instant answers", "high-quality" — rather than concrete actions, matching the 'names the domain but actions are minimal or generic' anchor. It falls short of anchor 3 because no genuinely concrete capability (e.g., returns ranked results, extracts, filters by date/domain) is stated.	2 / 5
Completeness	A 'what' is present (search with ranking and instant answers) but the 'when' is entirely absent — there is no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3. It is not 2 because the 'what' is stated rather than missing, though it is vague.	3 / 5
Trigger Term Quality	"web search" is the one natural keyword a user would say, but there are no variations or synonyms such as 'search the web', 'look up', or 'find sources', matching 'some relevant keywords but missing common variations'. It is above anchor 2 because 'web search' is a specific, natural trigger phrase rather than generic filler.	3 / 5
Distinctiveness Conflict Risk	The search domain is somewhat specific, but nothing distinguishes this skill from any other web-search skill a user might have installed, matching 'somewhat specific but could still overlap with similar skills'. It is not 4 because the description offers no distinct triggers or differentiators.	3 / 5
	Total	11 / 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-andi/SKILL.md
Commit: cc3e518

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.