exa-debug-bundle
Collect Exa debug evidence for support tickets and troubleshooting. Use when encountering persistent issues, preparing support tickets, or collecting diagnostic information for Exa problems. Trigger with phrases like "exa debug", "exa support bundle", "collect exa logs", "exa diagnostic".
68
83%
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 solid description with excellent trigger terms and clear 'when' guidance, making it easy for Claude to select appropriately. Its main weakness is that the 'what' portion is somewhat general—it says 'collect debug evidence' without specifying the concrete actions involved (e.g., gathering logs, capturing configs, exporting error states). Overall it performs well for skill selection purposes.
Suggestions
Add more specific concrete actions to the 'what' portion, e.g., 'Collects Exa logs, captures configuration snapshots, gathers error traces, and packages diagnostic bundles for support tickets.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (Exa debug evidence, support tickets) and a general action (collect), but doesn't list multiple specific concrete actions like 'gather logs, capture configuration, snapshot system state, export error traces'. | 2 / 3 |
Completeness | Clearly answers both 'what' (collect Exa debug evidence for support tickets and troubleshooting) and 'when' (encountering persistent issues, preparing support tickets, collecting diagnostic information) with explicit trigger phrases. | 3 / 3 |
Trigger Term Quality | Explicitly lists natural trigger phrases: 'exa debug', 'exa support bundle', 'collect exa logs', 'exa diagnostic'. These are terms users would naturally say and cover good variation. | 3 / 3 |
Distinctiveness Conflict Risk | Very specific niche targeting Exa debug/diagnostic collection. The 'Exa' product name and debug-specific triggers make it highly unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, highly actionable diagnostic skill with clear step-by-step workflows and executable code for each phase. Its main weakness is length — the full bash bundle script inline makes the skill verbose, and it could benefit from splitting the script into a bundle file. The sensitive data handling section and error table are strong additions that demonstrate good safety awareness.
Suggestions
Extract the debug bundle bash script (Step 3) into a separate bundle file (e.g., scripts/exa-debug-bundle.sh) and reference it from SKILL.md to reduce inline verbosity.
Tighten the summary.txt generation in the bundle script by using a heredoc or function instead of repetitive echo/append lines.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient and avoids explaining basic concepts, but the debug bundle script is quite verbose with repetitive echo/append patterns that could be tightened. The TypeScript capture step is useful but lengthy for what it demonstrates. | 2 / 3 |
Actionability | All three steps provide fully executable, copy-paste ready code — a bash connectivity test, a TypeScript debug function, and a complete bundle creation script. The error handling table provides specific causes and solutions for common issues. | 3 / 3 |
Workflow Clarity | The three steps form a clear escalating sequence: quick connectivity check → detailed request capture → full bundle creation. The sensitive data handling section serves as a validation checkpoint before sharing, and the error handling table provides a feedback loop for common failures. | 3 / 3 |
Progressive Disclosure | The skill references related skills (exa-rate-limits, exa-common-errors) and external resources, which is good. However, the inline content is quite long (~120 lines of code) and the debug bundle script could potentially be a referenced file rather than inline. No bundle files are provided despite the content being substantial enough to warrant splitting. | 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.