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

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

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.

Highly actionable and well-sequenced code, but the body monolithically duplicates an orphaned reference file and omits validation checkpoints on destructive retention/erasure workflows. Tightening duplication and linking the reference would lift the weaker dimensions.

Suggestions

Link references/implementation.md from the body and move the duplicated full-class implementations (SecureAudioUpload, RetentionManager, GDPRCompliance) there, keeping the body as an overview with concise snippets — improves both conciseness and progressive_disclosure.

Add validation checkpoints to the destructive Step 5/6 workflows: a dry-run count preview, confirmation of affected rows, and a database transaction with rollback so atomic deletes can be verified before commit.

Remove the redundant 'Output' summary section and trim chatty inline comments to reduce token overhead while keeping the executable code intact.

Dimension	Reasoning	Score
Conciseness	The body is almost entirely executable code with little concept-explanation, but it duplicates much of references/implementation.md inline and carries minor redundancy (the 'Output' restating the steps, chatty comments), so it could be tightened.	2 / 3
Actionability	Every step ships complete, copy-paste-ready TypeScript with real imports and SDK calls (transcribeUrl with redact, S3 PutObject with KMS, retention/erasure DB queries), matching the fully-executable anchor.	3 / 3
Workflow Clarity	Steps 1-6 are clearly sequenced, but the destructive Step 5 (retention enforcement) and Step 6 (GDPR erasure) batch S3/DB deletes lack validation checkpoints (dry-run, count verification, transactional rollback), which caps this dimension at 2 per the rubric.	2 / 3
Progressive Disclosure	A bundle file references/implementation.md exists with expanded implementations, but it is never linked from the body, which inlines six full code steps instead — content that should be separate is inline and the reference is unsignaled.	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.

A strong description: third-person, concrete, with an explicit Use-when clause and a thorough natural-language trigger list scoped to a distinct Deepgram niche. The only soft spot is the mildly buzzy 'best practices' phrasing, but the concrete actions that follow outweigh it.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions in the 'Use when' clause — 'managing audio file storage, implementing data retention, or ensuring GDPR/HIPAA compliance for transcription data' — matching the anchor for listing several specific concrete actions.	3 / 3
Completeness	Clearly answers both 'what' ('Implement audio data handling best practices for Deepgram integrations') and 'when' via an explicit 'Use when...' clause plus a Trigger keyword list.	3 / 3
Trigger Term Quality	The explicit Trigger list ('deepgram data', 'audio storage', 'transcription data', 'deepgram GDPR', 'deepgram HIPAA', 'deepgram privacy', 'PII redaction') gives good coverage of natural terms a user would actually say.	3 / 3
Distinctiveness Conflict Risk	The 'Deepgram'-prefixed triggers and narrow focus on audio/transcription data compliance define a clear niche unlikely to conflict with unrelated skills.	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
Path: plugins/saas-packs/deepgram-pack/skills/deepgram-data-handling/SKILL.md
Commit: 0540a62

Reviewed: 1 day 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.