exa-known-pitfalls
Identify and avoid Exa anti-patterns and common integration mistakes. Use when reviewing Exa code, onboarding new developers, or auditing existing Exa integrations for correctness. Trigger with phrases like "exa mistakes", "exa anti-patterns", "exa pitfalls", "exa what not to do", "exa code review".
88
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 well-structured skill description with strong completeness and trigger term coverage. Its main weakness is that the 'what' portion could be more specific about the concrete anti-patterns or types of mistakes it addresses, which would help Claude better understand the skill's scope. Overall, it follows good practices with explicit 'Use when' and 'Trigger with' clauses.
Suggestions
Add specific examples of the anti-patterns or mistake categories covered (e.g., 'incorrect query formatting, missing error handling, improper pagination') to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (Exa anti-patterns/mistakes) and some actions (identify, avoid, review, audit), but doesn't list specific concrete anti-patterns or integration mistakes. It stays at a moderate level of specificity without enumerating what kinds of mistakes or what specific corrections it provides. | 2 / 3 |
Completeness | The description clearly answers both 'what' (identify and avoid Exa anti-patterns and common integration mistakes) and 'when' (reviewing Exa code, onboarding new developers, auditing existing integrations) with explicit trigger phrases provided. | 3 / 3 |
Trigger Term Quality | The description explicitly lists natural trigger phrases like 'exa mistakes', 'exa anti-patterns', 'exa pitfalls', 'exa what not to do', 'exa code review'. It also includes contextual triggers like 'reviewing Exa code', 'onboarding new developers', and 'auditing existing Exa integrations', providing good coverage of terms users would naturally say. | 3 / 3 |
Distinctiveness Conflict Risk | The skill is narrowly scoped to Exa-specific anti-patterns and integration mistakes, which is a clear niche. The 'exa' prefix on all trigger terms and the focus on anti-patterns (rather than general Exa usage) makes it unlikely to conflict with a general Exa skill or other code review 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 strong, well-structured anti-patterns skill with excellent actionability through concrete BAD/GOOD code examples for each pitfall. The progressive disclosure and workflow clarity are appropriate for a reference-style skill. The main weakness is mild verbosity in introductory sentences that Claude doesn't need, though the overall token efficiency is reasonable.
Suggestions
Trim the overview paragraph — Claude doesn't need an explanation of what embeddings-based search is or why failure modes differ from traditional search APIs.
Some per-pitfall explanatory sentences (e.g., 'Date filters silently exclude results') could be shortened or folded into code comments to reduce token count.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The overview paragraph explaining that Exa uses embeddings-based search is somewhat unnecessary context for Claude. The BAD/GOOD pattern is efficient but the file is lengthy at ~150 lines; some pitfalls could be more terse. The brief explanatory sentences before each code block are mostly justified but occasionally redundant given the code speaks for itself. | 2 / 3 |
Actionability | Every pitfall includes fully executable TypeScript code with clear BAD/GOOD contrasts. The examples are copy-paste ready, use real API methods with realistic parameters, and demonstrate specific failure modes alongside correct usage. The checklist at the end is immediately actionable for code review. | 3 / 3 |
Workflow Clarity | This is a reference/checklist skill rather than a multi-step workflow, so the single-task clarity standard applies. Each pitfall is unambiguous with clear wrong/right patterns. Pitfall 4 includes a fallback/retry pattern. The review checklist provides a clear sequential verification process. | 3 / 3 |
Progressive Disclosure | Content is well-organized with clear section headers per pitfall, a summary checklist, external resource links, and cross-references to related skills (exa-sdk-patterns, exa-common-errors). The structure allows scanning by pitfall number without reading everything. | 3 / 3 |
Total | 11 / 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
3e83543
- 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.