Name: tavily-web
Rating: 56.8 (1 reviews)
Author: administrakt0r

tavily-web

Web search, content extraction, crawling, and research capabilities using Tavily API. Use when you need to search the web for current information, extracting content from URLs, or crawling websites.

Quality

65%

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 ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/tavily-web/SKILL.md

The canonical home for this skill is tavily-web in administrakt0r/AI-Agents-Safe-Coding-Skills

Quality

Content

47%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 well-structured and token-efficient but substantively thin: it provides almost no executable guidance on actually using the Tavily API and defers most useful content to an external repository. The workflow sequence is cursory and lacks configuration detail.

Suggestions

Add a concrete code example showing an actual Tavily API call (e.g., a curl or SDK snippet with the endpoint, required parameters, and expected response) so the skill is actionable without leaving SKILL.md.

Replace 'Configure Tavily API key' with specifics: the exact environment variable name, where to obtain the key, and how the skill reads it.

Move the deferred examples/troubleshooting into local bundle files under references/ (e.g., references/examples.md) so the skill is self-contained rather than pointing off-repo.

Dimension	Reasoning	Score
Conciseness	The body is short and does not over-explain concepts Claude already knows, but several lines are near-empty pointers ('See the GitHub repository…') that earn their place only marginally; efficient but not maximally lean, so a 4 rather than 5.	4 / 5
Actionability	Only the install command ('npx skills add -g BenedictKing/tavily-web') is concrete and executable; 'Configure Tavily API key' and 'Use naturally in Claude Code conversations' are high-level hints with no specifics, and there is no example of actually calling the Tavily API — minimal concrete guidance, so a 2.	2 / 5
Workflow Clarity	A rough three-step sequence is present (install, configure key, use naturally) but with major gaps — no indication of how to configure the key, no checkpoint or validation — so it fits the 'rough sequence, many gaps, validation absent' anchor at 2.	2 / 5
Progressive Disclosure	Sections are well-organized (Overview, When to Use, Installation, Step-by-Step Guide, etc.) and references are clearly signaled, but essential content (examples, troubleshooting, API usage) is offloaded to an external GitHub repo rather than local bundle files, a minor organization gap that caps it at 4.	4 / 5
	Total	12 / 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.

The description is strong: it concisely states capabilities and provides an explicit 'Use when…' clause with concrete triggers. Its main weakness is overlap risk with other web-search/extraction skills and a few missing natural synonyms.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'Web search, content extraction, crawling, and research capabilities' — naming the domain and multiple specific operations; just short of comprehensive coverage (e.g., no mention of filtering, batching, or result formatting), so a 4 rather than 5.	4 / 5
Completeness	Explicitly answers both 'what' ('Web search, content extraction, crawling, and research capabilities using Tavily API') and 'when' with concrete trigger phrases ('Use when you need to search the web for current information, extracting content from URLs, or crawling websites'), matching the level-5 anchor.	5 / 5
Trigger Term Quality	Includes natural user phrases like 'search the web', 'extracting content from URLs', and 'crawling websites', but misses common synonyms users might say ('scrape', 'fetch a URL', 'web research'), so not a 5.	4 / 5
Distinctiveness Conflict Risk	Naming 'Tavily API' gives a clear niche and distinct trigger, but the generic web-search/extraction phrasing overlaps with sibling skills (exa-search, firecrawl-scraper are listed as related), so minor overlap risk keeps it at 4 rather than 5.	4 / 5
	Total	17 / 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: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills-claude/skills/tavily-web/SKILL.md
Commit: debb2ec

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.