exa-core-workflow-a
Execute Exa neural search with contents, date filters, and domain scoping. Use when building search features, implementing RAG context retrieval, or querying the web with semantic understanding. Trigger with phrases like "exa search", "exa neural search", "search with exa", "exa searchAndContents", "exa query".
84
82%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
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.
This is a well-crafted skill description that clearly identifies the specific tool (Exa), lists concrete capabilities (neural search, contents retrieval, date filters, domain scoping), provides clear use-case triggers (RAG, search features, semantic queries), and includes explicit trigger phrases. The description is concise, uses third person voice, and would be easily distinguishable from other skills in a large collection.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'neural search with contents', 'date filters', and 'domain scoping'. These are concrete, actionable capabilities rather than vague language. | 3 / 3 |
Completeness | Clearly answers both 'what' (execute Exa neural search with contents, date filters, and domain scoping) and 'when' (building search features, implementing RAG context retrieval, querying the web with semantic understanding), plus explicit trigger phrases. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms including 'exa search', 'exa neural search', 'search with exa', 'exa searchAndContents', 'exa query'. Also includes contextual triggers like 'RAG context retrieval' and 'semantic understanding' that users might naturally mention. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to the specific 'Exa' product name and API-specific terms like 'searchAndContents'. Unlikely to conflict with generic search skills or other API integrations. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
64%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, actionable skill with excellent executable code examples covering the full range of Exa search capabilities. Its main weaknesses are moderate verbosity (some explanatory text Claude doesn't need) and lack of validation checkpoints integrated into the workflow steps. The progressive disclosure could be improved by splitting detailed reference material into bundle files.
Suggestions
Integrate validation/verification into the workflow steps (e.g., 'Check results.results.length > 0 before processing; if empty, widen date filters or rephrase query') rather than having error handling as a separate disconnected table.
Remove explanatory text Claude already knows, such as the description of what neural search is in the Overview and the prerequisites about 'understanding tradeoffs' — just show the code patterns and constraints.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient with good code examples, but includes some unnecessary explanation (e.g., 'Exa's neural search understands query meaning rather than matching keywords' is something Claude already knows about neural search). The prerequisites section mentioning 'Understanding of neural vs keyword search tradeoffs' is padding. The search types table is useful but some entries could be tighter. | 2 / 3 |
Actionability | All code examples are fully executable TypeScript with real API calls, concrete parameters, and copy-paste ready patterns. The error handling table maps specific errors to solutions. The RAG context retrieval example is a complete, practical function. Every step provides working code with inline comments explaining key parameters. | 3 / 3 |
Workflow Clarity | The steps are clearly sequenced from basic search to advanced features (content extraction, filtering, categories, freshness), but there are no validation checkpoints or feedback loops. For an API integration skill, there should be guidance on verifying results quality, checking for empty results, or handling rate limits between steps. The error handling table is separate rather than integrated into the workflow. | 2 / 3 |
Progressive Disclosure | The content is well-structured with clear sections and a reference to 'exa-core-workflow-b' for next steps, plus external documentation links. However, the skill is quite long (~150 lines of content) and could benefit from splitting the detailed examples (RAG context retrieval) or the error handling table into separate reference files. No bundle files exist to support progressive disclosure. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Commit
3a2d27d
- 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.