tdg-personal/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.
86
86%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
82%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 what the skill does and when to use it, with a good explicit 'Use when...' clause containing multiple natural trigger terms. Its main weaknesses are that the capability description could be more specific about concrete actions (e.g., 'search websites, find code snippets, retrieve company profiles') and the 'web search' trigger is generic enough to potentially conflict with other search skills.
Suggestions
Replace general domain labels with specific concrete actions, e.g., 'Searches the web, finds code snippets, retrieves company profiles, and looks up people using Exa's neural search engine via MCP.'
Add file type or output format details if applicable (e.g., 'returns summarized results, URLs, and snippets') to further distinguish from generic web search skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (neural search via Exa MCP) and mentions several areas (web, code, company research), but doesn't list specific concrete actions like 'extract', 'summarize', or 'crawl'. The actions are implied rather than explicitly stated. | 2 / 3 |
Completeness | Clearly answers both 'what' (neural search via Exa MCP for web, code, and company research) and 'when' (explicit 'Use when...' clause listing specific trigger scenarios like web search, code examples, company intel, people lookup, and AI-powered deep research). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'web search', 'code examples', 'company intel', 'people lookup', 'deep research', 'neural search', and 'Exa'. Good coverage of variations and use cases. | 3 / 3 |
Distinctiveness Conflict Risk | 'Web search' is a fairly generic trigger that could overlap with other search-related skills. However, the specific mention of 'Exa', 'neural search engine', and 'Exa MCP' helps distinguish it. The 'company intel' and 'people lookup' terms could also overlap with CRM or database skills. | 2 / 3 |
Total | 10 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, actionable skill that clearly documents two MCP tools with concrete invocation examples for multiple use cases. The content is mostly efficient though it could trim the activation triggers and some light redundancy between usage patterns and tips. Overall it serves as an effective reference for using Exa search capabilities.
Suggestions
Remove or significantly trim the 'When to Activate' section — Claude can infer when search is needed from context without explicit trigger phrases.
Consolidate the Tips section into the Usage Patterns section to reduce redundancy, since tips like 'use web_search_exa for current information' are already demonstrated by the examples.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Mostly efficient but has some unnecessary content. The 'When to Activate' section lists trigger phrases Claude can infer, and the parameter tables include obvious defaults. The tips section is somewhat redundant with the usage patterns already shown. | 2 / 3 |
Actionability | Provides concrete, copy-paste ready tool invocations with specific parameters for every use case. The MCP configuration JSON is complete and executable, and parameter tables give precise types and defaults. | 3 / 3 |
Workflow Clarity | This is a single-task skill (search queries) with no multi-step destructive operations. The usage patterns clearly show which tool to use for which scenario, and the two-tool surface is unambiguous. No validation checkpoints are needed for read-only search operations. | 3 / 3 |
Progressive Disclosure | Well-structured with clear sections progressing from setup to core tools to usage patterns to tips. References to related skills (deep-research, market-research) are one level deep and clearly signaled. Content length is appropriate for inline presentation. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
90%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 | |
Reviewed
Table of Contents