Use when writing or reviewing JavaScript/TypeScript in this repo that calls Deepgram Conversational STT v2 / Flux (`/v2/listen`) for turn-aware streaming transcription. Covers `client.listen.v2.createConnection()` / `connect()`, Flux models, and turn events like `TurnInfo`. Use `deepgram-js-speech-to-text` for standard v1 ASR and `deepgram-js-voice-agent` for full-duplex assistants. Triggers include "flux", "v2 listen", "conversational STT", "turn detection", "end of turn", "EOT", and "listen.v2".
72
88%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
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 hits all the marks. It opens with a clear 'Use when' clause, specifies concrete API methods and models, explicitly lists trigger terms, and proactively disambiguates from related skills to minimize conflict risk. The description is concise yet comprehensive, making it easy for Claude to select the right skill from a large pool.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and artifacts: 'client.listen.v2.createConnection() / connect()', 'Flux models', 'turn events like TurnInfo', and clearly names the API endpoint '/v2/listen'. Also distinguishes from related skills by naming specific alternatives. | 3 / 3 |
Completeness | Clearly answers both 'what' (calls Deepgram Conversational STT v2/Flux for turn-aware streaming transcription, covers specific methods and events) and 'when' (explicit 'Use when' clause at the start, plus explicit trigger terms and disambiguation guidance for when NOT to use it). | 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'. These are terms a developer would naturally use when working with this specific API. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — explicitly disambiguates from two related skills ('deepgram-js-speech-to-text' for v1 ASR and 'deepgram-js-voice-agent' for full-duplex assistants), carving out a clear niche for v2/Flux conversational STT specifically. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, actionable skill with executable code examples and well-structured workflow guidance for Deepgram's Conversational STT v2. Its main strengths are the concrete quick start, specific gotchas, and clear event handling patterns. Minor weaknesses include some token overhead from the product routing section and central skills promo, plus references to source files without bundle support.
Suggestions
Trim or remove the 'Central product skills' section at the bottom — it's promotional and doesn't help Claude execute the task.
Consider condensing the 'When to use this product' routing table since the YAML description already covers trigger conditions and alternative skills.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient but includes some unnecessary sections like the 'Central product skills' promo block and the 'When to use this product' section which, while useful, adds tokens for routing decisions Claude could handle from the YAML description. The gotchas and API reference sections are well-targeted though. | 2 / 3 |
Actionability | Provides fully executable, copy-paste-ready code for authentication and the main quick start flow. Key parameters, socket methods, and specific event types (TurnInfo, Connected, FatalError) are concretely named. The gotchas section gives specific, actionable guidance (e.g., 'use sendCloseStream not sendFinalize'). | 3 / 3 |
Workflow Clarity | The quick start demonstrates a clear sequence: create connection → register handlers → connect → wait for open → stream audio → close stream. The event handling shows error recovery (FatalError → close). The gotchas reinforce correct ordering ('createConnection is lazy, call connect() after registering handlers'). For a WebSocket streaming skill, this is a well-sequenced workflow. | 3 / 3 |
Progressive Disclosure | The API reference section provides a layered approach pointing to source files and external docs, which is good. However, there are no bundle files to support the references to source paths like 'src/CustomClient.ts' or 'src/api/resources/listen/resources/v2/client/Client.ts'. The skill also inlines content that could be split (gotchas, full parameter lists) but given no bundle exists, this is reasonable. The reference to a non-existent 'reference.md' that 'does not currently document listen.v2' is slightly confusing. | 2 / 3 |
Total | 10 / 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.
bcffba7
Table of Contents
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.