groq-core-workflow-b
Execute Groq secondary workflows: audio transcription (Whisper), vision, text-to-speech, and batch model evaluation. Trigger with phrases like "groq whisper", "groq transcription", "groq audio", "groq vision", "groq TTS", "groq speech".
84
82%
Does it follow best practices?
Impact
Pending
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 a strong skill description that concisely communicates specific capabilities (audio transcription, vision, TTS, batch evaluation) within the Groq platform context. It includes explicit trigger phrases covering natural user language variations and is clearly distinguishable from other skills. The description uses proper third-person voice and avoids vague language.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: audio transcription (Whisper), vision, text-to-speech, and batch model evaluation. These are distinct, named capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (execute Groq secondary workflows: audio transcription, vision, TTS, batch evaluation) and 'when' (explicit trigger phrases provided). The 'Trigger with phrases like...' clause serves as an explicit 'Use when' equivalent. | 3 / 3 |
Trigger Term Quality | Includes natural trigger terms users would say: 'groq whisper', 'groq transcription', 'groq audio', 'groq vision', 'groq TTS', 'groq speech'. These cover common variations of how users would phrase requests. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with the 'Groq' qualifier and specific modality terms (Whisper, TTS, vision). The combination of platform name + specific workflow types makes it very unlikely to conflict with other skills. | 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.
This skill provides highly actionable, executable code examples across multiple Groq secondary workflows with good error handling documentation. Its main weaknesses are that the 'steps' aren't a true sequential workflow but rather independent capabilities, and the content is somewhat long with all examples inline rather than using progressive disclosure. The content could be tightened by removing some redundant examples and splitting detailed usage patterns into separate reference files.
Suggestions
Restructure the numbered steps as independent sections rather than a sequential workflow, since audio transcription, vision, and TTS are independent capabilities—not a pipeline.
Add validation checkpoints such as file existence checks before audio operations and response status verification after API calls.
Move detailed examples (base64 images, multiple images, Python transcription, benchmarking) into a separate reference file and link from the main skill to reduce inline bulk.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient with good code examples, but includes some unnecessary explanation (e.g., 'Beyond chat completions, Groq provides ultra-fast audio transcription (Whisper at 216x real-time)' in the overview) and the model speed table duplicates information Claude doesn't need explained. The base64 image example and multiple images example add bulk that could be trimmed. | 2 / 3 |
Actionability | All code examples are fully executable, copy-paste ready TypeScript and Python with proper imports, typed function signatures, and realistic API calls. The error handling table provides specific solutions for specific errors, and model IDs are given as exact strings. | 3 / 3 |
Workflow Clarity | The steps are clearly numbered and sequenced, but they aren't really a sequential workflow—they're independent capabilities labeled as 'steps.' There are no validation checkpoints (e.g., checking if the file exists before transcription, verifying output quality, handling partial failures in benchmarking). For audio file operations, missing validation caps this at 2. | 2 / 3 |
Progressive Disclosure | The content is fairly long (~170 lines of substantive content) with all examples inline. The vision examples (basic, multiple images, base64) and both TypeScript and Python transcription examples could be split into referenced files. The Resources section and 'Next Steps' reference are good, but the main body could benefit from better separation of concerns. | 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
70e9fa4
- 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.