deepgram-data-handling

Implement audio data handling best practices for Deepgram integrations. Use when managing audio file storage, implementing data retention, or ensuring GDPR/HIPAA compliance for transcription data. Trigger: "deepgram data", "audio storage", "transcription data", "deepgram GDPR", "deepgram HIPAA", "deepgram privacy", "PII redaction".

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

65%

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 executable, well-sequenced code, but it is over-long for inline presentation and the destructive retention/erasure workflows lack explicit verification checkpoints. An existing reference file is orphaned rather than woven into the navigation.

Suggestions

Add explicit validation checkpoints before the destructive batch deletes in Steps 5 and 6 (e.g., dry-run count, confirm legal_hold exclusion, verify-then-delete) so the workflow includes a validate -> fix -> retry loop.

Link the existing references/implementation.md from the body (e.g., a '## Implementation details' pointer) so the bundled reference is discoverable rather than orphaned.

Move detailed inline code such as the StoredTranscript interface and SecureAudioUpload implementation into references/implementation.md, keeping the body to concise canonical snippets to reduce token load.

Dimension	Reasoning	Score
Conciseness	The body is ~280 lines with six substantial inline TypeScript blocks (e.g., the full StoredTranscript interface and retentionPolicies object); it is domain-specific rather than padded with basic concepts, but it could be tightened. Not a 3 because the volume of inline code exceeds a lean token budget, and not a 1 because it avoids explaining concepts Claude already knows.	2 / 3
Actionability	Provides fully executable, copy-paste-ready TypeScript with real imports and API calls (e.g., `deepgram.listen.prerecorded.transcribeUrl`, `s3.send(new PutObjectCommand(...))`). Not a 2 because the code is complete and concrete rather than pseudocode or abstract direction.	3 / 3
Workflow Clarity	Steps 1-6 are clearly sequenced, but the destructive batch operations in Step 5 (enforceRetention deletes S3 audio and DB rows) and Step 6 (GDPR erasure deletes audio and DB records) lack explicit validate-before-delete checkpoints. Capped at 2 per the rubric's feedback-loop rule for destructive/batch/database operations; not a 1 because the sequence itself is clear.	2 / 3
Progressive Disclosure	The body has section structure but the bundled references/implementation.md is never linked from the body, and detailed implementation code that could live in the reference is inline. Not a 3 because the existing reference is not signaled, and not a 1 because the body is organized into sections rather than a monolithic wall.	2 / 3
	Total	9 / 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.

A strong, well-scoped description that clearly states capabilities, supplies natural trigger terms, and explicitly answers both what the skill does and when to use it. It is distinguishable from other skills and free of vague fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "managing audio file storage", "implementing data retention", "ensuring GDPR/HIPAA compliance for transcription data" — rather than vague language. Not a 2 because coverage spans storage, retention, and compliance comprehensively, not just a domain plus a few actions.	3 / 3
Completeness	Explicitly answers both what ("Implement audio data handling best practices for Deepgram integrations") and when ("Use when managing audio file storage, implementing data retention...") with an explicit Trigger clause. Not a 2 because the 'when' is explicit, not merely implied.	3 / 3
Trigger Term Quality	Provides good coverage of natural terms users would say: "deepgram data", "audio storage", "transcription data", "deepgram privacy", and "PII redaction". Not a 2 because it includes common variations rather than only a single relevant keyword.	3 / 3
Distinctiveness Conflict Risk	Targets a clear Deepgram-specific audio/compliance niche with distinct triggers unlikely to overlap with unrelated skills. Not a 2 because the Deepgram + compliance scoping makes conflict with other skills unlikely.	3 / 3
	Total	12 / 12 Passed

Validation

87%

Warnings & errors only

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

Validation — 14 / 16 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	14 / 16 Passed

Repository: jeremylongshore/claude-code-plugins-plus-skills
Commit: 02d6341

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

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.