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.

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

Quality

Content

82%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 a well-structured, highly actionable reference: concrete tool schemas, setup configuration, and usage patterns plus a useful drift warning and untrusted-results guidance. Weaknesses are minor — slight redundancy between the Usage Patterns and Core Tools sections and a missing connectivity-verification step for the MCP setup.

Suggestions

Add a one-line validation step after the MCP setup JSON, e.g., verify the server with `claude mcp list` or confirm the Exa tools appear before first use.

Trim the Usage Patterns examples that repeat parameters already covered by the Core Tools tables, or fold them into the tool sections to remove redundancy.

If the skill grows, move the parameter tables and usage patterns into a references/ file to keep SKILL.md a lean overview.

Dimension	Reasoning	Score
Conciseness	The body assumes Claude's competence (no explanation of what web search or MCP is) and stays lean, but the Usage Patterns section reiterates tool invocations already fully documented in the Core Tools parameter tables — minor trimming possible, matching anchor 4.	4 / 5
Actionability	Fully executable guidance: copy-paste-ready MCP server config JSON with API-key placement, concrete tool invocations, parameter tables with defaults and valid ranges (e.g., tokensNum 1000-50000), and usage examples covering the common lookup, code-research, and company/people cases — matching anchor 5.	5 / 5
Workflow Clarity	The sequence (configure the MCP server, pick the right tool, apply the matching usage pattern) is clear and the skill is effectively single-purpose, but there is no checkpoint to verify the Exa server is actually connected before first use — a minor validation gap matching anchor 4.	4 / 5
Progressive Disclosure	A self-contained single-file skill (no references/, scripts/, or assets/ exist) with well-organized sections and clearly labeled related skills. At ~110 inline lines, it exceeds the under-50-line simple-skill case for a top score, and the parameter tables plus usage patterns could arguably live in a reference file — matching anchor 4.	4 / 5
	Total	17 / 20 Passed

Description

78%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.

A strong description with an explicit Use-when trigger clause and good natural keywords. Its main weakness is specificity: it conveys a single search action across several domains rather than enumerating several distinct concrete capabilities.

Suggestions

Enumerate 2-3 distinct concrete capabilities in the what-clause (e.g., 'find company funding and market intel, retrieve professional profiles, pull code examples from GitHub and Stack Overflow') instead of the single generic action 'research'.

Add a couple of common trigger synonyms users naturally say, such as 'look up' or 'find information on', to broaden natural keyword coverage.

Dimension	Reasoning	Score
Specificity	Names the mechanism ("Neural search via Exa MCP") and domains (web, code, and company research), but offers only a single action verb — search — rather than several distinct concrete operations, matching the anchor 'Names domain and 1-2 concrete actions, but not comprehensive'. Not 4 because it does not enumerate several separate specific actions.	3 / 5
Completeness	Explicitly answers 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") with concrete trigger phrases, matching anchor 5.	5 / 5
Trigger Term Quality	Natural user phrases like "web search", "code examples", "company intel", "people lookup", and "deep research" give good keyword coverage, but a few common variations (e.g., "look up", "find info on") are missing, matching anchor 4.	4 / 5
Distinctiveness Conflict Risk	"via Exa MCP" carves a clear niche, but generic "web search" triggers carry minor overlap risk with other search-oriented skills, matching anchor 4 rather than 5.	4 / 5
	Total	16 / 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
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: affaan-m/ECC
Path: skills/exa-search/SKILL.md
Commit: c70874f

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.