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".

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

80%

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

A dense, highly actionable SDK skill that delivers copy-paste code for each endpoint with strong reference tables. Its weaknesses are the lack of validation/verification checkpoints in batch or file-writing operations and a monolithic structure with no progressive offloading to bundle files.

Suggestions

Add explicit validation/verification steps for operations that write files or run in batch (e.g., check the saved TTS file exists and is non-empty; wrap benchmark loops with error handling and report failures) to lift workflow clarity above 2.

Move the Audio Models and Error Handling reference tables into a references/ file (e.g., MODELS.md and ERRORS.md) and link from SKILL.md so the body stays an overview, improving progressive disclosure.

Tighten the Overview by dropping the marketing-style speed claims ('ultra-fast', '216x real-time') or relocate them to a model reference table, keeping the intro purely orientational.

Dimension	Reasoning	Score
Conciseness	The body is code- and table-forward with minimal prose, never explaining concepts Claude already knows; the only mild padding is speed marketing ('216x real-time') in the Overview, so it stays lean and efficient.	3 / 3
Actionability	Provides fully executable TypeScript and Python snippets with concrete model IDs, parameters, and return handling — copy-paste ready rather than pseudocode.	3 / 3
Workflow Clarity	Steps are listed as numbered recipes but they are independent endpoints rather than a sequenced pipeline, and the batch benchmarking step (Step 6) plus file-writing TTS lack validation/verification checkpoints, capping clarity at 2.	2 / 3
Progressive Disclosure	Well-sectioned but monolithic: all six recipes, model tables, and the error-handling reference live inline in one ~150-line file with no bundle files to offload detail, fitting 'content that should be separate is inline'.	2 / 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.

A strong, third-person description that names concrete capabilities and pairs them with natural trigger phrases covering both 'what' and 'when'. It avoids fluff and is clearly distinguishable from sibling Groq skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'audio transcription (Whisper), vision, text-to-speech, and batch model evaluation' — matching the anchor for several specific actions rather than vague domain naming.	3 / 3
Completeness	Explicitly states what it does (the four secondary workflows) and provides explicit trigger guidance via 'Trigger with phrases like...', satisfying both the 'what' and 'when' requirements rather than leaving 'when' implied.	3 / 3
Trigger Term Quality	Provides natural user phrases — 'groq whisper', 'groq transcription', 'groq audio', 'groq vision', 'groq TTS', 'groq speech' — giving good coverage of how a user would actually invoke the skill.	3 / 3
Distinctiveness Conflict Risk	Scoped to Groq's non-chat endpoints with Groq-prefixed triggers, carving a clear niche that is unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 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	14 / 16 Passed

Repository: jeremylongshore/claude-code-plugins-plus-skills
Commit: 3022dd3

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

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.