Name: exa-search
Rating: 74.67 (1 reviews)
Author: affaan-m

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

73%

Does it follow best practices?

Impact

98%

7.00x

Average score across 2 eval scenarios

Securityby

Failed to scan

The risk profile of this skill

Fix and improve this skill with Tessl

tessl review fix .//.agents/skills/exa-search/SKILL.md

The canonical home for this skill is exa-search in affaan-m/ECC

Quality

Content

64%Scale 1-3

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

This is a solid reference skill that provides clear, actionable tool invocations with good parameter documentation. Its main weaknesses are the lack of error handling/validation guidance (what to do when searches fail or return unexpected results) and some verbosity in sections like 'When to Activate' that Claude could infer. The content is well-organized but could benefit from being slightly more concise.

Suggestions

Add brief error handling guidance: what to do if MCP server isn't available, if searches return no results, or if deep_researcher_check shows incomplete status

Remove or significantly trim the 'When to Activate' section—Claude can infer when web search is appropriate from context

Consider adding a note about rate limits or API usage constraints if applicable

Dimension	Reasoning	Score
Conciseness	The skill is mostly efficient but includes some unnecessary content like the 'When to Activate' section (Claude can infer when to search) and the tips section restates somewhat obvious guidance. The parameter tables are useful but could be slightly more compact.	2 / 3
Actionability	Every tool has concrete, copy-paste-ready invocation examples with specific parameters. The MCP configuration is fully specified with exact JSON. Usage patterns show real-world combinations with actual queries.	3 / 3
Workflow Clarity	The deep_researcher_start/check pattern shows a clear two-step async workflow, and the 'Company Due Diligence' pattern shows multi-tool sequencing. However, there are no validation checkpoints or error handling guidance—what happens if the MCP server isn't configured, if a search returns no results, or if deep_researcher_check shows incomplete status?	2 / 3
Progressive Disclosure	The content is well-structured with clear sections and a logical flow from setup to tools to patterns to tips. However, at ~130 lines it's somewhat long for a single file—the detailed parameter tables could potentially be in a reference file. The 'Related Skills' section provides good navigation but there are no bundle files to offload detail to.	2 / 3
	Total	9 / 12 Passed

Description

82%Scale 1-3

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 description that clearly communicates both purpose and trigger conditions. Its main strengths are the explicit 'Use when...' clause with good trigger term coverage. The primary weakness is that the capabilities are described at a category level rather than as specific concrete actions, and the broad scope of 'web search' could cause conflicts with other search skills.

Suggestions

Add more specific concrete actions instead of categories, e.g., 'Searches the web using Exa's neural engine, finds code snippets and repositories, retrieves company profiles and funding data, looks up people and their backgrounds.'

Differentiate more clearly from generic web search skills by emphasizing what makes Exa's neural search unique (e.g., semantic understanding, similarity search, content extraction).

Dimension	Reasoning	Score
Specificity	Names the domain (neural search via Exa MCP) and lists some action areas (web, code, company research), but doesn't describe concrete actions like 'extract', 'analyze', or 'generate'. The capabilities are described more as categories than specific actions.	2 / 3
Completeness	Clearly answers both 'what' (neural search via Exa MCP for web, code, and company research) and 'when' with an explicit 'Use when...' clause listing multiple trigger scenarios.	3 / 3
Trigger Term Quality	Includes strong natural trigger terms users would say: 'web search', 'code examples', 'company intel', 'people lookup', 'deep research', 'Exa', and 'neural search engine'. Good coverage of variations a user might naturally use.	3 / 3
Distinctiveness Conflict Risk	The mention of 'Exa MCP' and 'neural search engine' provides some distinctiveness, but 'web search' is very generic and could overlap with other search-related skills. The broad scope (web, code, company, people) increases potential conflict with more specialized skills.	2 / 3
	Total	10 / 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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: affaan-m/ECC
Path: /.agents/skills/exa-search/SKILL.md
Commit: d8409a4

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.