exa-hello-world
Create a minimal working Exa search example with real results. Use when starting a new Exa integration, testing your setup, or learning basic search, searchAndContents, and findSimilar patterns. Trigger with phrases like "exa hello world", "exa example", "exa quick start", "simple exa search", "first exa query".
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 well-crafted skill description that clearly defines its scope (minimal Exa search examples), specifies when to use it (new integrations, testing, learning), and provides explicit trigger phrases. It uses third-person voice correctly and is concise without being vague. The only minor note is that it could mention the output format or language, but this is not a significant gap.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: creating a minimal working example, testing setup, and learning specific patterns (search, searchAndContents, findSimilar). These are concrete, named API methods. | 3 / 3 |
Completeness | Clearly answers both 'what' (create a minimal working Exa search example with real results) and 'when' (starting a new Exa integration, testing setup, or learning basic patterns), with explicit trigger phrases provided. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms: 'exa hello world', 'exa example', 'exa quick start', 'simple exa search', 'first exa query'. Also includes technical terms like 'searchAndContents' and 'findSimilar' that users familiar with the API would use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — targets a very specific niche (Exa API hello-world/quickstart examples) with unique trigger terms like 'exa hello world' and 'exa quick start' that are unlikely to conflict with other skills. | 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 hello-world skill with excellent actionability — every code block is executable and demonstrates real API patterns with concrete parameters. The main weaknesses are moderate verbosity from duplicated examples (steps vs. complete script) and missing validation checkpoints between steps. The error handling table is a nice addition but would be more useful if integrated into the workflow as actual checks.
Suggestions
Remove or significantly trim the 'Complete Runnable Script' section since it largely duplicates Steps 1-3, or move it to a separate file and reference it.
Add a validation checkpoint after Step 1 (e.g., check results.results.length > 0 before proceeding) and guard Step 3's findSimilar with a check, matching the pattern already shown in the complete script.
Remove the 'Output' section — it restates what the code examples already demonstrate and adds no new information.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient with good code examples, but includes some unnecessary elements: the 'Output' section restates what the code already shows, the 'Overview' sentence is redundant given the title and structure, and the complete runnable script in 'Examples' largely duplicates Steps 1-3. The prerequisites and error table earn their place, but overall it could be tightened. | 2 / 3 |
Actionability | All code examples are fully executable TypeScript with real SDK calls, concrete parameter values, and copy-paste ready patterns. The error handling table provides specific error codes with solutions. Every step demonstrates a distinct API method with realistic usage. | 3 / 3 |
Workflow Clarity | Steps are clearly sequenced and each demonstrates a distinct operation, but there are no validation checkpoints — no verification that the API key works before proceeding, no check that results are non-empty before using them in Step 3's findSimilar (the complete script does this but the main steps don't), and no explicit feedback loop for error recovery despite the error table. | 2 / 3 |
Progressive Disclosure | The content is well-structured with clear sections and references to next steps (exa-core-workflow-a, exa-sdk-patterns) and external docs. However, with no bundle files, the internal references are unverifiable, and the skill is somewhat long (~120 lines of content) with the complete runnable script duplicating the step-by-step examples — that content could have been split into a separate file. | 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
a04d1a2
- 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.