code-search-exa
Code context using Exa. Finds real snippets and docs from GitHub, StackOverflow, and technical docs. Use when searching for code examples, API syntax, library documentation, or debugging help.
89
87%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
89%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 skill description that clearly communicates its purpose and when to use it. The explicit 'Use when' clause with natural trigger terms is a strength, and the mention of Exa and specific sources (GitHub, StackOverflow) provides good distinctiveness. The main weakness is that the capability description could be more specific about what concrete actions it performs beyond 'finds snippets and docs'.
Suggestions
Expand the capability list with more specific actions, e.g., 'Finds real code snippets, API references, usage examples, and troubleshooting solutions from GitHub, StackOverflow, and technical docs.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (code context) and some actions ('Finds real snippets and docs'), but doesn't list multiple specific concrete actions like extracting, analyzing, or comparing. The actions are somewhat general. | 2 / 3 |
Completeness | Clearly answers both 'what' (finds real snippets and docs from GitHub, StackOverflow, and technical docs using Exa) and 'when' (explicit 'Use when' clause covering code examples, API syntax, library documentation, or debugging help). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'code examples', 'API syntax', 'library documentation', 'debugging help', plus source names like 'GitHub', 'StackOverflow'. These are terms users naturally use when seeking code help. | 3 / 3 |
Distinctiveness Conflict Risk | The mention of 'Exa' as the specific tool, combined with the focus on external code search from specific sources (GitHub, StackOverflow, technical docs), creates a clear niche that is unlikely to conflict with general coding skills or other search skills. | 3 / 3 |
Total | 11 / 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, concise skill that clearly communicates constraints (tool restriction, token isolation) and provides actionable query-writing guidance. Its main weakness is the lack of a concrete example showing an actual web_search_exa tool invocation with parameters, which would make it fully copy-paste actionable rather than descriptive.
Suggestions
Add a concrete example of a web_search_exa tool call with sample parameters (e.g., query string, any relevant options) and a brief expected response to make the skill fully executable.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every section is lean and purposeful. No unnecessary explanations of what Exa is or how search works. The query writing patterns section adds genuine value without padding. | 3 / 3 |
Actionability | Provides clear guidance on query construction and output format, but lacks a concrete executable example of an actual Exa tool call (e.g., a sample web_search_exa invocation with parameters and expected response). The MCP config is concrete and copy-paste ready, but the core workflow is described rather than demonstrated. | 2 / 3 |
Workflow Clarity | The workflow is clear: spawn a Task agent → agent calls web_search_exa → agent deduplicates → agent returns snippets. The token isolation section acts as an explicit constraint/checkpoint. For a single-purpose skill like this, the sequence is unambiguous and the deduplication step serves as a validation checkpoint. | 3 / 3 |
Progressive Disclosure | For a skill under 50 lines with a single purpose, the content is well-organized into clearly labeled sections (tool restriction, token isolation, when to use, query patterns, output format, MCP config). No need for external references and no monolithic walls of text. | 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 | |
- Repository
- exa-labs/exa-mcp-server
- Commit
c6ec084
- Reviewed
Table of Contents
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.