deepgram-core-workflow-b
Implement real-time streaming transcription with Deepgram WebSocket. Use when building live transcription, voice interfaces, real-time captioning, or voice AI applications. Trigger: "deepgram streaming", "real-time transcription", "live transcription", "websocket transcription", "voice streaming", "deepgram live".
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-core-workflow-b/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 well-crafted skill description with strong trigger terms, clear 'when' guidance, and excellent distinctiveness due to the specific Deepgram + WebSocket niche. Its main weakness is that the 'what' portion could be more specific about the concrete actions the skill enables beyond just 'implement real-time streaming transcription'. Overall it is a strong description that would perform well in skill selection.
Suggestions
Add more specific concrete actions to the capability description, e.g., 'Implement real-time streaming transcription with Deepgram WebSocket, including connection setup, audio streaming, interim/final result handling, and error recovery.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (real-time streaming transcription) and a key technology (Deepgram WebSocket), but only describes one core action ('implement real-time streaming transcription') rather than listing multiple specific concrete actions like handling audio input, processing interim results, managing connection lifecycle, etc. | 2 / 3 |
Completeness | Clearly answers both 'what' (implement real-time streaming transcription with Deepgram WebSocket) and 'when' (building live transcription, voice interfaces, real-time captioning, or voice AI applications), with an explicit 'Use when' clause and explicit trigger terms. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms including 'deepgram streaming', 'real-time transcription', 'live transcription', 'websocket transcription', 'voice streaming', and 'deepgram live'. These are terms users would naturally use when seeking this functionality, with good variation coverage. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: Deepgram-specific WebSocket streaming transcription. The combination of 'Deepgram' and 'real-time/streaming' makes it very unlikely to conflict with other skills like general speech-to-text, batch transcription, or other audio processing 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.
This is a solid, highly actionable skill with excellent executable code examples covering the full spectrum of Deepgram live streaming use cases. Its main weaknesses are length (the monolithic structure could benefit from splitting advanced patterns into separate files) and the lack of inline validation checkpoints within the workflow steps. The error handling table is a strong addition but would be more effective if validation checks were woven into the steps themselves.
Suggestions
Add inline validation checkpoints, e.g., after Step 1 instruct to verify a Transcript event is received before proceeding to microphone capture, and after Step 2 verify audio chunks are being sent successfully.
Split Steps 3-5 (diarization, auto-reconnect, SSE endpoint) into separate referenced files to reduce the main skill's token footprint and improve progressive disclosure.
Remove the Output section which merely restates what each step already demonstrates, saving tokens without losing clarity.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient with executable code examples, but includes some unnecessary commentary (e.g., the Output section just restates what was already shown, and some inline comments explain obvious things). The overview could be trimmed. However, it avoids explaining basic concepts like what WebSockets are. | 2 / 3 |
Actionability | Every step contains fully executable TypeScript code with specific SDK methods, configuration options, and real commands. The code is copy-paste ready with concrete parameters (sample rates, encoding formats, event names) and covers multiple real-world scenarios. | 3 / 3 |
Workflow Clarity | Steps are clearly sequenced from basic to advanced, but there are no explicit validation checkpoints. For a WebSocket-based streaming system where misconfigured audio parameters silently fail, there should be verification steps (e.g., 'confirm you receive a Transcript event before proceeding'). The error handling table helps but is separate from the workflow. | 2 / 3 |
Progressive Disclosure | The content is well-structured with clear step headings and a useful error table, but it's quite long (~200 lines of code) and could benefit from splitting advanced patterns (auto-reconnect, SSE endpoint, diarization) into separate referenced files. The Resources and Next Steps sections provide good external navigation. | 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
c8a915c
- 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.