deepgram-python-audio-intelligence
Use when writing or reviewing Python code in this repo that calls Deepgram audio analytics overlays on `/v1/listen` - summarize, topics, intents, sentiment, diarize, redact, detect_language, entity detection. Same endpoint as plain STT but with analytics params. Covers both REST (`client.listen.v1.media.transcribe_url`/`transcribe_file`) and the WSS-supported subset (`client.listen.v1.connect`). Use `deepgram-python-speech-to-text` for plain transcription, `deepgram-python-text-intelligence` for analytics on already-transcribed text. Triggers include "diarize", "summarize audio", "sentiment from audio", "redact PII", "topic detection audio", "audio intelligence", "detect language audio".
68
82%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
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.
This is an excellent skill description that clearly defines its scope (audio analytics overlays on Deepgram's /v1/listen endpoint), lists specific capabilities, provides explicit trigger terms, and carefully delineates boundaries with related skills. The description is information-dense without being padded, and uses appropriate third-person voice throughout.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: summarize, topics, intents, sentiment, diarize, redact, detect_language, entity detection. Also specifies exact API paths and client methods (REST and WSS). | 3 / 3 |
Completeness | Clearly answers both 'what' (audio analytics overlays on /v1/listen including summarize, topics, intents, sentiment, etc.) and 'when' (explicit 'Use when' clause at the start plus explicit trigger terms at the end). Also provides boundary guidance distinguishing from related skills. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'diarize', 'summarize audio', 'sentiment from audio', 'redact PII', 'topic detection audio', 'audio intelligence', 'detect language audio'. These are realistic phrases a developer would use. | 3 / 3 |
Distinctiveness Conflict Risk | Explicitly distinguishes itself from related skills ('deepgram-python-speech-to-text' for plain transcription, 'deepgram-python-text-intelligence' for text analytics), creating clear boundaries. The analytics-on-audio niche is well-defined and unlikely to conflict. | 3 / 3 |
Total | 12 / 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.
A solid, actionable skill with excellent executable code examples covering REST and WSS paths for Deepgram audio intelligence features. The feature availability table and gotchas are genuinely useful additions. Main weaknesses are the length (could be more concise by trimming the diarization deep-dive and some routing boilerplate) and the absence of error handling or validation steps in the workflows.
Suggestions
Add basic error handling/validation to at least one code example (e.g., check response status, handle auth failures) to improve workflow clarity.
Consider moving the detailed diarization word-level fields table and the extended diarization example into a separate reference file to improve conciseness and progressive disclosure.
Trim the 'When to use this product' routing section — a simple bullet list of skill names without full descriptions would suffice since Claude can look up the other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient with good use of tables and code examples, but includes some unnecessary explanation (e.g., the 'When to use this product' section rehashes routing logic Claude can infer, the diarization section is quite lengthy with a full field table, and the 'Central product skills' section at the bottom adds marginal value). The gotchas section is valuable but could be tighter. | 2 / 3 |
Actionability | Provides fully executable, copy-paste-ready code examples for REST URL, REST file, diarization with word-level timings, and WSS. Parameters are concrete with specific values (e.g., `summarize="v2"`, `redact=["pci", "pii"]`), and response access patterns are explicitly shown. | 3 / 3 |
Workflow Clarity | The skill covers multiple quick-start paths clearly, but lacks validation/verification steps — there's no error handling, no checking of response status, and no guidance on what to do when API calls fail or return unexpected results. For API operations that could fail (auth issues, unsupported params on WSS), this is a gap. | 2 / 3 |
Progressive Disclosure | References to external docs and related skills are well-organized in a layered API reference section, but the skill itself is quite long (~180 lines) with inline content that could be split out (e.g., the detailed diarization word-level fields table, the full gotchas list). The reference to `reference.md` is good but no bundle files are provided to verify it exists. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- deepgram/deepgram-python-sdk
- Commit
e169f63
- 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.