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 excellent trigger terms and clear 'what/when' guidance. Its main weakness is that the capabilities described are somewhat general ('collect debug evidence') rather than listing specific concrete actions the skill performs. The explicit trigger term list is a strong feature that aids skill selection.
Suggestions
Add more specific concrete actions, e.g., 'Captures API request/response logs, gathers SDK versions, exports configuration details, and bundles diagnostic artifacts for Deepgram support tickets.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | 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 request/response traces, gather SDK version info'. | 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 coverage of natural trigger terms including '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 — the combination of 'Deepgram' with 'debug', 'support ticket', and 'diagnostic' creates a very clear niche that is 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-crafted, highly actionable debug bundle skill with executable code across bash and TypeScript, clear step sequencing, and good safety practices (key redaction). Its main weakness is length — the inline code blocks make it a large skill that could benefit from splitting code into referenced files. The error handling table and support ticket template are practical additions that round out the workflow.
Suggestions
Consider moving the bash scripts and TypeScript logger into separate referenced files (e.g., `scripts/collect-env.sh`, `scripts/debug-request.ts`) to reduce the SKILL.md token footprint and improve progressive disclosure.
Remove the Overview paragraph — the skill description and step titles already convey the purpose; Claude doesn't need an explanation of what a debug bundle is.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly efficient but includes some unnecessary elements like the overview paragraph explaining what a debug bundle is, and the Current State section with shell commands that may not always be relevant. The code blocks are substantial but mostly justified given the multi-step nature of the task. | 2 / 3 |
Actionability | Highly actionable with fully executable bash scripts, TypeScript code, and curl commands that are copy-paste ready. Each step provides concrete, runnable code with specific API endpoints, headers, and parameters. | 3 / 3 |
Workflow Clarity | Clear 6-step sequential workflow with explicit validation (sanitization pass in Step 5, compatibility checks in Step 3). The final sanitization step acts as a safety net for leaked keys, and the bundle packaging provides a clear completion checkpoint. The error handling table adds recovery guidance. | 3 / 3 |
Progressive Disclosure | Content is well-structured with clear sections, but it's quite long and monolithic — the TypeScript request logger (Step 4) and the bash scripts could be referenced as separate files rather than inlined. The Resources section provides external links but no internal file references for the substantial code blocks. | 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
70e9fa4
- 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.