deepgram-debug-bundle
Collect Deepgram debug evidence for support and troubleshooting. Use when preparing support tickets, investigating issues, or collecting diagnostic information for Deepgram problems. Trigger: "deepgram debug", "deepgram support ticket", "collect deepgram logs", "deepgram diagnostic", "deepgram debug bundle".
85
83%
Does it follow best practices?
Impact
Pending
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-structured skill description with strong trigger terms and clear 'when' guidance. Its main weakness is that the 'what' could be more specific about the concrete actions performed (e.g., what types of evidence are collected, what format the output takes). Overall it performs well for skill selection purposes.
Suggestions
Add more specific concrete actions to improve specificity, e.g., 'Collects API request/response logs, configuration snapshots, error traces, and SDK version info into a debug bundle for Deepgram support.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | It names the domain (Deepgram debug evidence) and some actions (collect, prepare support tickets, investigate issues), but doesn't list specific concrete actions like 'capture API logs, export configuration, gather error traces'. The actions remain somewhat high-level. | 2 / 3 |
Completeness | Clearly answers both 'what' (collect Deepgram debug evidence for support and troubleshooting) and 'when' (preparing support tickets, investigating issues, collecting diagnostic information) with explicit trigger terms listed. | 3 / 3 |
Trigger Term Quality | Excellent trigger term coverage with explicit natural phrases: 'deepgram debug', 'deepgram support ticket', 'collect deepgram logs', 'deepgram diagnostic', 'deepgram debug bundle'. These are terms users would naturally say when needing this skill. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche — Deepgram-specific debug/diagnostic collection. The explicit product name and specific use case make it very 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 strong, highly actionable skill with fully executable code across all steps and a clear multi-step workflow for collecting Deepgram debug information. Its main weakness is length — the skill packs a lot of inline code that could be split into referenced bundle files for better progressive disclosure. Minor conciseness issues include the overview paragraph and the dynamic 'Current State' header section.
Suggestions
Extract the bash scripts (Steps 1-3, 5) and TypeScript logger (Step 4) into separate bundle files (e.g., collect-env.sh, debug-request.ts) and reference them from SKILL.md to improve progressive disclosure.
Remove the Overview paragraph — the skill title and step descriptions already convey the purpose without explaining what a debug bundle is.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient with executable scripts, but includes some unnecessary elements: the 'Current State' section with shell commands at the top is unusual, the Overview paragraph explains what a debug bundle is (which Claude knows), and the support ticket template includes placeholder dates and version numbers that add bulk. The audio analysis function is thorough but lengthy. | 2 / 3 |
Actionability | Excellent actionability — every step contains fully executable bash scripts or TypeScript code that can be copy-pasted. The curl commands include specific endpoints, headers, and output formatting. The audio analysis function includes concrete ffprobe commands with specific flags and compatibility checks with actual thresholds. | 3 / 3 |
Workflow Clarity | The 6-step workflow is clearly sequenced from environment collection through packaging and ticket creation. Step 5 includes a final sanitization pass as a validation checkpoint, Step 2 redacts keys inline, and the error handling table provides a feedback loop for common failure modes. The progression from collection → testing → analysis → capture → package → submit is logical and complete. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear sections and a summary output section, but it's a long monolithic file (~180 lines of content) with no references to external files. The TypeScript logger (Step 4) and the bash scripts could reasonably be split into separate referenced files. The error handling table and resources section are appropriately placed, but the overall length could benefit from 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
3a2d27d
- 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.