exa-common-errors
Diagnose and fix Exa API errors by HTTP code and error tag. Use when encountering Exa errors, debugging failed requests, or troubleshooting integration issues. Trigger with phrases like "exa error", "fix exa", "exa not working", "debug exa", "exa 429", "exa 401".
68
84%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
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 well-crafted skill description that excels in completeness and distinctiveness. It clearly identifies the domain (Exa API), states what it does, when to use it, and provides explicit trigger phrases. The only minor weakness is that the specificity of capabilities could be slightly more detailed about what kinds of fixes or diagnostics it performs.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | It names the domain (Exa API errors) and describes actions (diagnose and fix by HTTP code and error tag), but doesn't list multiple specific concrete actions like listing specific error types handled or specific resolution steps. | 2 / 3 |
Completeness | Clearly answers both 'what' (diagnose and fix Exa API errors by HTTP code and error tag) and 'when' (encountering Exa errors, debugging failed requests, troubleshooting integration issues) with explicit trigger phrases. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms including 'exa error', 'fix exa', 'exa not working', 'debug exa', 'exa 429', 'exa 401' — these are phrases users would naturally say when encountering Exa API issues. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — 'Exa API' is a specific product/service, and the trigger terms are all Exa-specific, making it very unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
79%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong reference skill with excellent use of tables for error lookup and executable code examples for the most common issues (auth verification, rate limiting, diagnostics). The main weaknesses are the lack of a structured troubleshooting workflow with feedback loops and the references to bundle files that don't exist. Overall it serves its purpose well as a quick-reference error guide.
Suggestions
Add a brief escalation workflow with feedback loops: e.g., 'If solution doesn't resolve the error → run diagnostic script → capture requestId → contact support', making the troubleshooting process more sequential and recoverable.
Either create the referenced bundle files (exa-debug-bundle, exa-rate-limits) or remove the references to avoid dead-end navigation.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. Tables are used effectively to compress information. No unnecessary explanations of what HTTP status codes are or how APIs work. Every section delivers actionable reference data without padding. | 3 / 3 |
Actionability | Provides executable bash and TypeScript code for key scenarios (API key verification, rate limit backoff, diagnostic script). Error tables give specific error tags, causes, and concrete solutions. The curl commands and backoff implementation are copy-paste ready. | 3 / 3 |
Workflow Clarity | The Instructions section provides a basic 4-step diagnostic sequence, but it lacks explicit validation checkpoints or feedback loops. For a troubleshooting skill, there's no 'if fix doesn't work, try next' escalation path beyond the initial lookup. The diagnostic script is helpful but disconnected from the resolution workflow. | 2 / 3 |
Progressive Disclosure | References to external resources (docs, status page) and next steps (exa-debug-bundle, exa-rate-limits) are present, but no bundle files exist to support the references. The content is well-structured with clear sections, but the inline content is quite long (~120 lines of tables and code) — some of the per-URL content fetch errors or the diagnostic script could potentially be split out. | 2 / 3 |
Total | 10 / 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.