exa-core-workflow-b
Execute Exa findSimilar, getContents, answer, and streaming answer workflows. Use when finding pages similar to a URL, retrieving content for known URLs, or getting AI-generated answers with citations. Trigger with phrases like "exa find similar", "exa get contents", "exa answer", "exa similarity search", "findSimilarAndContents".
67
82%
Does it follow best practices?
Impact
—
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 strong skill description that clearly identifies the Exa-specific workflows it handles, provides explicit 'Use when' guidance, and lists concrete trigger phrases. The description is concise, uses third-person voice, and is highly distinctive due to the product-specific terminology.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: findSimilar, getContents, answer, and streaming answer workflows. Also describes concrete use cases like finding similar pages, retrieving content, and getting AI-generated answers with citations. | 3 / 3 |
Completeness | Clearly answers both 'what' (execute Exa findSimilar, getContents, answer, and streaming answer workflows) and 'when' (explicit 'Use when' clause with triggers, plus a 'Trigger with phrases like' section providing additional guidance). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms: 'exa find similar', 'exa get contents', 'exa answer', 'exa similarity search', 'findSimilarAndContents'. These cover both natural language and API-style terms users would actually say when working with the Exa API. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to the specific 'Exa' product name and its unique API methods (findSimilar, getContents, answer). Very unlikely to conflict with other skills since it targets a specific tool's workflows. | 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 all three Exa endpoints. Its main weaknesses are moderate verbosity (some unnecessary explanatory comments and a redundant Output section) and the lack of validation/error-recovery steps within the workflows, particularly for the batch processing example. The progressive disclosure references other skills but no bundle files exist to back them up.
Suggestions
Add error handling and validation within the batch URL retrieval example (e.g., try/catch per batch, verify results count matches input count) to improve workflow clarity.
Remove the 'Output' section as it merely restates what the code examples already demonstrate, and trim inline comments that explain obvious behavior to improve conciseness.
Consider creating the referenced bundle files (exa-common-errors, exa-sdk-patterns) or remove references to non-existent resources to improve progressive disclosure accuracy.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient with good code examples, but includes some unnecessary commentary (e.g., 'Useful when you have URLs from a previous search or external source') and the Output section restates what's already obvious from the code examples. Some inline comments are helpful but others explain what Claude would already know. | 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 provides specific HTTP codes and solutions. The practical examples (competitive intelligence, batch retrieval) are complete and actionable. | 3 / 3 |
Workflow Clarity | Steps are clearly sequenced and well-labeled, but these are independent API endpoints rather than a true multi-step workflow requiring validation checkpoints. The batch URL retrieval example lacks error handling/validation within the loop (e.g., what if a batch fails?), and there are no explicit verification steps after API calls to confirm results are valid. | 2 / 3 |
Progressive Disclosure | References to related skills (exa-core-workflow-a, exa-common-errors, exa-sdk-patterns) and external docs are present, but no bundle files exist to support them. The content is somewhat long for a single file — the examples section and error table could potentially be split out. However, the structure with clear headers aids navigation. | 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
c2ae302
- 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.