exa-web-search-free

Free AI search via Exa MCP. Web search for news/info, code search for docs/examples from GitHub/StackOverflow, company research for business intel. No API key needed.

Quality

80%

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 ./configs/microservice/bff-service/configs/agent-skills/clawhub/exa-web-search-free/SKILL.md

Quality

Content

100%

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 lean, fully actionable reference: executable mcporter commands with real parameters, a verify-then-proceed setup loop, and a well-signaled one-level reference to examples.md. It assumes Claude's competence and earns a top score across all content dimensions.

Dimension	Reasoning	Score
Conciseness	The body is lean executable mcporter commands with terse parameter tables and no explanations of what Exa/MCP/search are; it assumes Claude's competence and every token earns its place.	3 / 3
Actionability	Every tool ships a copy-paste-ready command with real parameter values (e.g. mcporter call 'exa.web_search_exa(query: "latest AI news 2026", numResults: 5)') plus a setup/verify command, fully executable rather than pseudocode.	3 / 3
Workflow Clarity	Setup includes an explicit verify-then-proceed checkpoint ('mcporter list exa' with an 'If not listed:' fallback), and the core usage is simple single-call actions, which the rubric's simple-skills note allows to score 3.	3 / 3
Progressive Disclosure	SKILL.md is a concise overview with Advanced Tools summarized and a clearly signaled one-level-deep reference to references/examples.md (verified to exist), with content appropriately split between overview and examples.	3 / 3
	Total	12 / 12 Passed

Description

60%

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 specific and names three concrete search capabilities in third person, but it omits explicit 'Use when...' trigger guidance and relies on somewhat generic trigger terms, capping completeness and trigger-term quality at 2.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks to search the web for current news/info, find code examples or docs, or research a company.'

Broaden trigger terms with natural variations users say, such as 'search the internet', 'look up', 'find documentation', and 'look into a company'.

Sharpen distinctiveness by leading with the Exa-specific angle (neural/AI search) rather than generic 'web search' / 'code search' phrasing.

Dimension	Reasoning	Score
Specificity	Enumerates multiple concrete actions across three distinct modes ('web search for news/info', 'code search for docs/examples from GitHub/StackOverflow', 'company research for business intel'), matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Clearly states what the skill does across three modes but lacks any 'Use when...' clause or explicit trigger guidance; the rubric caps completeness at 2 when 'when' is only implied.	2 / 3
Trigger Term Quality	Contains relevant natural terms ('web search', 'code search', 'company research', 'news/info') but misses common variations users might say ('search the internet', 'look up', 'find documentation'), so it is not the full coverage of anchor 3.	2 / 3
Distinctiveness Conflict Risk	The 'via Exa MCP' framing and three-mode specialization carve a niche, but the bare terms 'web search' and 'code search' are generic enough to overlap with other search skills, so it does not reach the clearly-distinct anchor 3.	2 / 3
	Total	9 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	14 / 16 Passed

Repository: UnicomAI/wanwu
Path: configs/microservice/bff-service/configs/agent-skills/clawhub/exa-web-search-free/SKILL.md
Commit: f618458

Reviewed: about 14 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.