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".
80
77%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/saas-packs/deepgram-pack/skills/deepgram-data-handling/SKILL.mdQuality
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 solid skill description with excellent trigger term coverage and clear 'when to use' guidance. Its main weakness is that the 'what' portion could be more specific about the concrete actions the skill performs, listing high-level categories rather than detailed operations. The Deepgram-specific focus and compliance-oriented trigger terms make it highly distinctive.
Suggestions
Add more specific concrete actions to the description, e.g., 'configure data retention policies, redact PII from transcripts, set up encryption for stored audio, implement consent management workflows'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (Deepgram audio data handling) and mentions some actions like 'audio file storage', 'data retention', and 'GDPR/HIPAA compliance', but these are more like categories than concrete specific actions. It lacks detail on what exactly the skill does (e.g., 'configure retention policies', 'redact PII from transcripts', 'encrypt audio at rest'). | 2 / 3 |
Completeness | The description clearly answers both 'what' (implement audio data handling best practices for Deepgram integrations) and 'when' (managing audio file storage, implementing data retention, ensuring GDPR/HIPAA compliance), with explicit trigger terms listed. | 3 / 3 |
Trigger Term Quality | The description includes a well-curated list of natural trigger terms that users would likely say: 'deepgram data', 'audio storage', 'transcription data', 'deepgram GDPR', 'deepgram HIPAA', 'deepgram privacy', 'PII redaction'. These cover multiple natural variations and compliance-related terms users would use. | 3 / 3 |
Distinctiveness Conflict Risk | The description is highly specific to Deepgram integrations combined with data handling/compliance, creating a clear niche. The trigger terms are sufficiently specific (e.g., 'deepgram GDPR', 'deepgram HIPAA') that they are unlikely to conflict with general audio processing or generic compliance skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill provides comprehensive, executable TypeScript code for Deepgram data handling with good coverage of PII redaction, storage, retention, and GDPR compliance. However, it's overly long for a SKILL.md — much of the generic infrastructure code (S3 uploads, database CRUD, regex patterns) could be trimmed or moved to bundle files. The compliance-critical workflows lack explicit validation checkpoints and dry-run capabilities that would be expected for destructive operations.
Suggestions
Add validation checkpoints to the retention enforcement and GDPR erasure workflows — e.g., a dry-run mode that lists what would be deleted before executing, and a verification step after deletion.
Extract the application-level PII redaction patterns, S3 upload utilities, and retention enforcement into separate bundle files, keeping SKILL.md as a concise overview with references.
Trim generic infrastructure code (standard S3 upload, basic database queries) that Claude can derive, and focus the inline content on Deepgram-specific configuration and compliance-specific gotchas.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly long (~200 lines of code) and includes some patterns Claude could derive (e.g., basic S3 upload, regex PII patterns, GDPR deletion logic). The quick reference table and Deepgram-specific redact parameters earn their place, but the generic application-level code (S3 uploads, database queries, retention enforcement) is verbose for what is largely standard CRUD with compliance labels. | 2 / 3 |
Actionability | All code examples are fully executable TypeScript with proper imports, concrete API calls, and realistic patterns. The Deepgram SDK usage, S3 integration, and database queries are copy-paste ready with clear parameter usage and expected outputs. | 3 / 3 |
Workflow Clarity | Steps are clearly numbered and sequenced, but there are no explicit validation checkpoints between steps. For operations involving data deletion (retention enforcement, GDPR erasure) and compliance-critical workflows, there are no verify-before-proceed gates, dry-run options, or feedback loops for error recovery beyond basic try/catch. | 2 / 3 |
Progressive Disclosure | The content is structured with clear sections and a quick reference table, but it's monolithic — all ~200 lines of code are inline with no separation into supporting files. The transcript storage pattern, retention enforcement, and GDPR erasure could each be separate referenced files, keeping the SKILL.md as a concise overview. | 2 / 3 |
Total | 9 / 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
3a2d27d
- 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.