CtrlK
BlogDocsLog inGet started
Tessl Logo

web-search-tavily

AI-powered web search, crawling, extraction, and deep research

55

Quality

62%

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 ./skills/research-tools/capabilities/web-search-tavily/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

50%

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 well-organized but monolithic API reference with concrete curl examples, two of which are malformed and non-executable. It lacks validation checkpoints and keeps all detail inline with no progressive disclosure into reference files.

Suggestions

Fix the malformed JSON in the Tavily Search and Tavily Crawl curl examples so they are copy-paste executable (wrap parameters in a "body":{…} object inside the `-d` string).

Move the verbose per-parameter reference into a separate references/ file (e.g. REFERENCE.md) and keep SKILL.md as a concise overview with one-level-deep links.

Tighten the long parameter descriptions (search_depth, auto_parameters, chunks_per_source) to the essential choices and tradeoffs, dropping redundant prose.

DimensionReasoningScore

Conciseness

The body is a dense, verbose inline API reference — e.g. the multi-paragraph search_depth and auto_parameters descriptions — that could be tightened or moved to a reference file. It does not explain concepts Claude already knows, so it stays above 1, but the padding keeps it from a lean level-3.

2 / 3

Actionability

Each endpoint ships a concrete curl command, but the Tavily Search and Tavily Crawl examples contain malformed JSON (fields like "query"/"url" sit outside the `-d '…'` string), so they are not copy-paste executable. That incompleteness matches the level-2 anchor rather than the fully-executable level-3 anchor.

2 / 3

Workflow Clarity

Setup is sequenced (read credentials, or tell the user to run `npx gooseworks login`), but the API-call steps lack validation checkpoints or error-recovery guidance. The sequence is present but checkpoints are missing, matching level 2 rather than the validate-and-retry level-3 anchor.

2 / 3

Progressive Disclosure

No bundle files exist and the entire ~190-line API reference lives inline in SKILL.md, matching the level-2 example of "200 lines of API reference that could be in a separate file". It is well-headed per endpoint, so it clears level 1, but nothing is split out to reach level 3.

2 / 3

Total

8

/

12

Passed

Description

75%

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 concrete, natural-sounding capabilities but omits any explicit "Use when…" trigger guidance, which caps completeness and weakens distinctiveness. It reads as a capability list rather than an activation-oriented description.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks to search the web, crawl or extract content from URLs, or run deep research on a topic."

Drop the "AI-powered" buzzword prefix to reduce fluff and sharpen distinctiveness.

Include common user phrasings (e.g. "search the internet", "scrape a site", "research a topic") to broaden trigger-term coverage.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "web search, crawling, extraction, and deep research" — rather than vague language, matching the "lists multiple specific concrete actions" anchor. The "AI-powered" prefix is mild buzzword fluff but the named actions are concrete, so it clears the bar for 3 rather than dropping to 2.

3 / 3

Completeness

It clearly answers "what" (search, crawl, extract, research) but provides no "Use when…" clause or equivalent explicit trigger guidance. Per the judging guideline, a missing "Use when…" clause caps completeness at 2, so it cannot reach 3.

2 / 3

Trigger Term Quality

Terms like "web search", "crawling", "extraction", and "deep research" are natural phrases a user would say when needing this skill, giving good coverage. It is not dropped to 2 because the keywords are common user-facing terms rather than internal jargon.

3 / 3

Distinctiveness Conflict Risk

"AI-powered web search" is fairly generic and could overlap with general browsing/fetch skills, and the missing "when" clause gives no sharpening triggers. It is somewhat specific (the crawl/extract/research combo is a niche) but could still conflict, matching the level-2 anchor rather than the clearly-distinct level-3 anchor.

2 / 3

Total

10

/

12

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Repository
gooseworks-ai/goose-skills
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.