CtrlK
BlogDocsLog inGet started
Tessl Logo

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".

67

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

65%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with complete executable scripts, but it is over-inlined: the same scripts already live in references/implementation.md, which is never referenced from the body, and the packaging workflow lacks an explicit validation checkpoint. Tighter cross-linking to the reference and a verify step would lift the weaker dimensions.

Suggestions

Replace the fully inlined scripts with concise summaries and link to references/implementation.md (e.g., "See [implementation.md](references/implementation.md) for the complete scripts") to remove duplication and improve progressive disclosure.

Add an explicit validation checkpoint before packaging — e.g., verify each output file is non-empty and that no raw API key remains via a grep — with a fix-and-retry loop, so the batch workflow has a real feedback step.

Trim the inlined TypeScript request logger and support ticket template to the essentials or move them to the reference, since they duplicate implementation.md and inflate the body without adding new information.

DimensionReasoningScore

Conciseness

The body is mostly efficient and does not explain concepts Claude already knows, but it inlines six full scripts (bash + TypeScript) and a ticket template, much of which is duplicated in references/implementation.md; it could be tightened by pointing to the reference instead of repeating it.

2 / 3

Actionability

Every step provides complete, copy-paste-ready code — real curl endpoints with sanitizing sed, ffprobe commands, a TypeScript capture function, and packaging commands — with no pseudocode or placeholders.

3 / 3

Workflow Clarity

Steps 1-6 are clearly sequenced, but this batch/collect-and-package operation has no inline validation checkpoint or verify-then-retry feedback loop; the Error Handling table is reactive rather than an explicit "validate before packaging" step, so clarity is capped at 2 per the destructive/batch guideline.

2 / 3

Progressive Disclosure

A reference file (references/implementation.md) exists but is never linked or signaled from the body, while content that belongs in it (full scripts) is inlined in SKILL.md — matching the anchor where references are present but not clearly signaled and inline content should be split out.

2 / 3

Total

9

/

12

Passed

Description

100%Weight 40%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is concrete, third-person, and answers both what and when with an explicit trigger clause and natural keywords. It is a strong, well-targeted description with no over-claims or fluff.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "Collect Deepgram debug evidence", "preparing support tickets", "investigating issues", "collecting diagnostic information" — rather than vague language, matching the anchor that names several specific actions.

3 / 3

Completeness

Clearly answers both what ("Collect Deepgram debug evidence for support and troubleshooting") and when ("Use when preparing support tickets, investigating issues..." plus an explicit Trigger clause), satisfying the anchor for explicit triggers on both axes.

3 / 3

Trigger Term Quality

The explicit Trigger line provides natural phrases a user would say ("deepgram debug", "collect deepgram logs", "deepgram diagnostic", "deepgram support ticket", "deepgram debug bundle"), giving good coverage of common variations.

3 / 3

Distinctiveness Conflict Risk

The Deepgram-specific niche and Deepgram-prefixed trigger terms make it clearly distinguishable and unlikely to fire for unrelated skills.

3 / 3

Total

12

/

12

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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

14

/

16

Passed

Repository
jeremylongshore/claude-code-plugins-plus-skills
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.