Name: tavily-web
Rating: 49.6 (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

54%

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/skills/tavily-web/SKILL.md

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

Quality

Content

25%Scale 1-5

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

This skill is essentially a placeholder with no actionable content. It provides an installation command but completely lacks concrete usage examples, API patterns, tool invocation syntax, or any substantive guidance on how to perform web searches, extract content, or crawl websites using Tavily. All meaningful content is deferred to an external GitHub repository that Claude cannot access during use.

Suggestions

Add concrete, executable examples showing how to invoke Tavily search, extract, and crawl operations (e.g., actual tool calls or API usage patterns with sample inputs and expected outputs).

Provide specific instructions for configuring the Tavily API key (e.g., exact environment variable name and how to set it).

Include at least one complete workflow example showing a search query, processing the results, and verifying the output.

Replace external GitHub references with inline content or bundled files that Claude can actually access during conversations.

Dimension	Reasoning	Score
Conciseness	The content is relatively short but includes unnecessary sections like 'When to Use' that merely repeat the description, and 'Best Practices' with a single trivial bullet. Some sections are filler rather than substantive.	3 / 5
Actionability	There is no concrete guidance on how to actually use the Tavily API—no code examples, no commands beyond installation, no API usage patterns, no tool invocation syntax. Everything is vague ('Use naturally in Claude Code conversations') or deferred to an external repository.	1 / 5
Workflow Clarity	The 'Step-by-Step Guide' lists three steps but they are extremely vague: 'Configure Tavily API key' gives no specifics on how, and 'Use naturally' is not a real step. No validation or verification is mentioned.	2 / 5
Progressive Disclosure	References point to an external GitHub repository rather than bundled files, providing no actual content at the reference targets. There are no bundle files to support the skill, and the references are essentially dead ends for Claude's context.	2 / 5
	Total	8 / 20 Passed

Description

83%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.

This is a solid skill description that clearly communicates both what the skill does and when to use it, with the explicit 'Use when' clause providing good trigger guidance. The mention of Tavily API adds distinctiveness. Minor improvements could include adding more natural synonym trigger terms and being slightly more specific about the types of research or content extraction supported.

Dimension	Reasoning	Score
Specificity	Lists several specific actions: 'web search', 'content extraction', 'crawling', and 'research capabilities'. These are concrete but could be more detailed (e.g., what kind of research, what format of extracted content).	4 / 5
Completeness	Clearly answers both 'what' (web search, content extraction, crawling, research via Tavily API) and 'when' ('Use when you need to search the web for current information, extracting content from URLs, or crawling websites') with explicit trigger phrases.	5 / 5
Trigger Term Quality	Includes good natural keywords like 'search the web', 'current information', 'extracting content from URLs', 'crawling websites', and 'Tavily API'. Missing some synonyms users might say like 'look up', 'find online', 'scrape', 'browse', or 'web scraping'.	4 / 5
Distinctiveness Conflict Risk	Mentioning 'Tavily API' specifically helps distinguish it from other potential web search or research skills. However, 'research capabilities' is broad and could overlap with other research-oriented skills. The specific tool mention (Tavily) reduces conflict risk significantly.	4 / 5
	Total	17 / 20 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills/skills/tavily-web/SKILL.md
Commit: debb2ec

Reviewed: 20 hours 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.