CtrlK
BlogDocsLog inGet started
Tessl Logo

deepgram-core-workflow-a

Implement production pre-recorded speech-to-text with Deepgram. Use when building audio transcription, batch processing, or implementing diarization and intelligence features. Trigger: "deepgram transcription", "speech to text", "transcribe audio", "batch transcription", "deepgram nova", "diarize audio".

72

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Advisory

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

Quality

Content

80%

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

The content is concise and highly actionable with executable code, but it stops short of a clean progressive-disclosure structure and omits validation feedback loops for its batch and async operations. Wiring the existing reference file into the body and adding validation checkpoints would lift it further.

Suggestions

Link references/implementation.md from the body (e.g., a 'Full implementation' pointer) so the bundle is clearly signaled rather than orphaned, moving inline code toward progressive disclosure.

Add an explicit validation/feedback step for batch processing — e.g., retry failed files, verify non-empty transcripts before counting success — to satisfy the validation-checkpoint expectation for batch operations.

Trim or externalize the duplicated class scaffolding that also appears in implementation.md to reduce redundancy between the body and the reference.

DimensionReasoningScore

Conciseness

Lean body with executable code and tight inline comments ('Audio intelligence', 'Boost weight 1.0-2.0'); no padding explaining concepts Claude already knows. Not a level-2 because nothing reads as unnecessary or loosenable.

3 / 3

Actionability

Provides fully executable TypeScript (createClient, transcribeUrl/transcribeFile, p-limit batch, callback submission, keyword boosting) that is copy-paste ready. Not a level-2 because code is complete rather than pseudocode.

3 / 3

Workflow Clarity

Steps are sequenced (Step 1–5) but batch processing and async submission lack explicit validation checkpoints or fix-and-retry feedback loops; the rubric caps batch/destructive workflows at 2 when validation is missing. Not a level-1 because a clear sequence exists.

2 / 3

Progressive Disclosure

A reference file (references/implementation.md) exists but the body never signals or links it, and the body itself is a monolithic inline code dump that could be split out. Not a level-3 because navigation to the bundle is not clearly signaled; not a level-1 because the body has organized sections and only one-level-deep references.

2 / 3

Total

10

/

12

Passed

Description

100%

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 specific, action-oriented, and gives explicit trigger guidance with natural keyword coverage, making it both complete and distinctive. It is a strong, well-scoped skill description.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Implement production pre-recorded speech-to-text', 'batch processing', 'diarization and intelligence features' — rather than vague language.

3 / 3

Completeness

Explicitly answers both 'what' (implement pre-recorded transcription with Deepgram) and 'when' via the 'Use when...' clause plus an explicit 'Trigger:' list.

3 / 3

Trigger Term Quality

Natural user-facing terms like 'speech to text', 'transcribe audio', 'batch transcription', 'deepgram nova', and 'diarize audio' give good coverage of phrasings a user would actually say.

3 / 3

Distinctiveness Conflict Risk

Deepgram-specific niche with branded triggers makes 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.