CtrlK
BlogDocsLog inGet started
Tessl Logo

deepgram-python-conversational-stt

Use when writing or reviewing Python code in this repo that calls Deepgram Conversational STT v2 / Flux (`/v2/listen`) for turn-aware streaming transcription. Covers `client.listen.v2.connect(...)`, Flux models, end-of-turn detection. Use `deepgram-python-speech-to-text` for standard v1 ASR, `deepgram-python-voice-agent` for full-duplex interactive assistants. Triggers include "flux", "v2 listen", "conversational STT", "turn detection", "end of turn", "EOT", "listen.v2", "flux-general-en", "flux-general-multi".

91

1.19x
Quality

86%

Does it follow best practices?

Impact

100%

1.19x

Average score across 3 eval scenarios

SecuritybySnyk

Advisory

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

Quality

Content

72%

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

This is a strong, well-organized skill that provides concrete, executable guidance for Deepgram's Conversational STT v2 API. Its main strengths are the actionable code examples, comprehensive gotchas section, and clear progressive disclosure structure. The main weaknesses are minor verbosity in promotional/routing sections and the lack of explicit error recovery workflows for what is inherently a fragile WebSocket streaming operation.

Suggestions

Add an explicit error recovery/reconnection workflow for handling ListenV2FatalError and WebSocket disconnects, since streaming operations are inherently fragile.

Trim the 'Central product skills' section and 'When to use this product' routing guidance — the YAML description already handles skill selection, so this duplicates context.

DimensionReasoningScore

Conciseness

Generally efficient but includes some unnecessary sections like the 'Central product skills' promo block and the 'When to use this product' section which could be trimmed. The 'Related skills' and cross-references add some bloat. However, the core technical content is well-condensed.

2 / 3

Actionability

Provides fully executable code for both sync and async usage, concrete parameter tables with specific values, and a comprehensive gotchas section with exact method names and types. The quick start is copy-paste ready with real SDK imports and method calls.

3 / 3

Workflow Clarity

The quick start shows a clear sequence (connect → register handlers → send audio → close), but there's no explicit validation or error recovery workflow. For a WebSocket-based streaming operation, there should be more explicit guidance on handling ListenV2FatalError recovery, reconnection logic, or verifying the connection is healthy before sending audio.

2 / 3

Progressive Disclosure

Well-structured with clear sections progressing from when-to-use → auth → quick start → parameters → events → async → references. External references are clearly signaled and one level deep (reference.md, AsyncAPI docs, product docs). Example files in the repo are pointed to directly.

3 / 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.

This is an excellent skill description that hits all the marks. It opens with a clear 'Use when' clause, specifies concrete actions and API surfaces, explicitly differentiates from sibling skills to prevent conflicts, and provides a comprehensive list of natural trigger terms. The description is concise yet thorough, using third-person voice throughout.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions and entities: 'calls Deepgram Conversational STT v2 / Flux', 'client.listen.v2.connect(...)', 'Flux models', 'end-of-turn detection', and distinguishes from related skills with specific alternatives.

3 / 3

Completeness

Clearly answers both 'what' (writing/reviewing Python code for Deepgram Conversational STT v2/Flux streaming transcription) and 'when' (explicit 'Use when' clause at the start, plus explicit trigger terms and differentiation from related skills).

3 / 3

Trigger Term Quality

Excellent coverage of natural trigger terms explicitly listed: 'flux', 'v2 listen', 'conversational STT', 'turn detection', 'end of turn', 'EOT', 'listen.v2', 'flux-general-en', 'flux-general-multi'. These cover both technical and natural language variations users would say.

3 / 3

Distinctiveness Conflict Risk

Exceptionally distinctive — explicitly differentiates itself from two related skills ('deepgram-python-speech-to-text' for v1 ASR and 'deepgram-python-voice-agent' for voice agents), creating clear boundaries and minimizing conflict risk.

3 / 3

Total

12

/

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.

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository
deepgram/deepgram-python-sdk
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.