exa-search

Neural search via Exa MCP for web, code, and company research. Use when the user needs web search, code examples, company intel, people lookup, or AI-powered deep research with Exa's neural search engine.

7.00x

Quality

86%

Does it follow best practices?

Impact

98%

7.00x

Average score across 2 eval scenarios

Securityby

Low

Low-risk findings worth noting

Quality

Content

72%

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

A well-organized, highly actionable MCP tool catalog with executable calls and parameter tables. Its weak spots are mild redundancy between Core Tools and Usage Patterns, and an async deep-research workflow whose retry/checkpoint behavior is left implicit.

Suggestions

Trim the 'Usage Patterns' section or fold it into the Core Tools examples so each tool is demonstrated once, removing the redundant re-demonstrations of web_search_exa and get_code_context_exa.

Add explicit checkpoint guidance to the deep_researcher workflow: how to interpret a pending vs complete result, a recommended wait/retry interval, and what to do on failure.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and avoids explaining Exa/MCP concepts Claude already knows, but the 'Usage Patterns' section re-demonstrates tools already shown with full parameter tables in 'Core Tools' (e.g. web_search_exa and get_code_context_exa recur with only different query strings), which is mild padding that could be tightened.	2 / 3
Actionability	Each tool is shown with an executable, copy-paste-ready call (e.g. 'web_search_exa(query: "...", numResults: 5)') backed by parameter tables giving type, default, and notes, matching the 'fully executable code/commands; copy-paste ready' anchor.	3 / 3
Workflow Clarity	The deep_researcher flow is sequenced (start then check) and single-tool usage is unambiguous, but the async research workflow lacks explicit checkpoints such as what a pending vs complete result looks like, how long to wait, or retry guidance, fitting the score-2 'sequence present but checkpoints missing or implicit' anchor.	2 / 3
Progressive Disclosure	No bundle files exist and the skill is a self-contained, well-sectioned overview (When to Activate, MCP Requirement, Core Tools, Usage Patterns, Tips, Related Skills) with only one-level-deep pointers to sibling skills, so navigation is clear and there is no monolithic wall of text or nested references.	3 / 3
	Total	10 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description: third person, concrete multi-action capabilities, an explicit 'Use when' trigger clause, and clear Exa-specific distinctiveness. It answers what, when, and how it differs from generic skills in one tight sentence.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions across Exa's tool surface ('web search, code examples, company intel, people lookup, or AI-powered deep research') in third person voice, matching the 'lists multiple specific concrete actions' anchor rather than the partial score-2 anchor.	3 / 3
Completeness	It explicitly answers both what ('Neural search via Exa MCP for web, code, and company research') and when ('Use when the user needs web search, code examples, company intel, people lookup, or AI-powered deep research'), matching the score-3 anchor with an explicit 'Use when' trigger clause.	3 / 3
Trigger Term Quality	It includes natural terms users would say ('web search', 'code examples', 'company intel', 'people lookup', 'deep research'), giving good coverage of capability keywords, which fits the score-3 anchor better than the sparse score-2 example ('Works with PDF files').	3 / 3
Distinctiveness Conflict Risk	Exa-specific branding ('Neural search via Exa MCP', 'Exa's neural search engine') plus distinct research categories give it a clear niche unlikely to trigger for unrelated skills, matching the score-3 anchor.	3 / 3
	Total	12 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: affaan-m/ECC
Path: .agents/skills/exa-search/SKILL.md
Commit: 754b8dd

Reviewed: 2 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.