deepgram-core-workflow-a
Implement production pre-recorded speech-to-text with Deepgram. Use when building audio transcription, batch processing, or implementing diarization and intelligence features. Trigger: "deepgram transcription", "speech to text", "transcribe audio", "batch transcription", "deepgram nova", "diarize audio".
64
77%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/saas-packs/deepgram-pack/skills/deepgram-core-workflow-a/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-structured skill description that clearly identifies its niche (Deepgram pre-recorded speech-to-text), provides explicit 'Use when' guidance, and lists strong trigger terms. Its main weakness is that the capability description could be more specific about concrete actions beyond high-level feature areas. Overall it is a strong description that would perform well in skill selection.
Suggestions
Add more specific concrete actions such as 'transcribe audio files to text, extract speaker labels via diarization, detect topics and sentiment via intelligence features, support multiple audio formats' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (speech-to-text with Deepgram) and mentions some actions like 'audio transcription', 'batch processing', 'diarization and intelligence features', but doesn't list multiple concrete actions in detail (e.g., no mention of specific output formats, API usage patterns, or configuration steps). | 2 / 3 |
Completeness | Clearly answers both 'what' (implement pre-recorded speech-to-text with Deepgram) and 'when' (explicit 'Use when' clause covering audio transcription, batch processing, diarization) with explicit trigger terms listed separately. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms including 'deepgram transcription', 'speech to text', 'transcribe audio', 'batch transcription', 'deepgram nova', and 'diarize audio'. These are terms users would naturally use when requesting this functionality. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to the specific Deepgram branding, 'pre-recorded' qualifier, and specialized trigger terms like 'deepgram nova' and 'diarize audio'. Unlikely to conflict with other speech-to-text or general 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, actionable skill with production-ready TypeScript code covering multiple Deepgram transcription patterns. Its main strengths are concrete, executable examples and good error handling documentation. Weaknesses include missing validation checkpoints in the workflow (especially for batch operations), some verbosity in restating outputs, and a monolithic structure that could benefit from splitting advanced topics into separate files.
Suggestions
Add explicit validation checkpoints: verify API key is set before instantiation, validate audio file exists and has correct headers before transcription, and add a retry loop for failed batch items.
Remove the 'Output' section which merely restates what the code already demonstrates, or convert it to a brief summary of what the class exposes.
Consider splitting advanced features (audio intelligence, batch processing, callback pattern) into a referenced companion file to improve progressive disclosure and reduce the main skill's token footprint.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient with executable code and useful tables, but includes some unnecessary commentary (e.g., explaining what callback does, inline comments restating obvious things). The Output section largely restates what was already shown in the steps. Some trimming is possible. | 2 / 3 |
Actionability | Fully executable TypeScript code throughout, with concrete class implementations, specific API parameters, real error handling patterns, and copy-paste ready examples including batch processing and keyword boosting with actual syntax. | 3 / 3 |
Workflow Clarity | Steps are clearly sequenced and logically ordered from basic transcription through batch processing and async patterns. However, there are no explicit validation checkpoints—no step to verify the transcription result is valid, check API key configuration, or validate audio files before processing. The batch processing uses Promise.allSettled but lacks a retry/fix feedback loop for failed items. | 2 / 3 |
Progressive Disclosure | The content is well-structured with clear sections and a reference to a companion workflow (deepgram-core-workflow-b). However, the skill is quite long with all code inline, and there are no bundle files to offload detailed reference material. The error handling table and resources section are good, but the main body could benefit from splitting advanced features (intelligence, batch, callback) into separate referenced files. | 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
5da23fb
- 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.