groq-core-workflow-b

Use when you need Groq's non-chat endpoints — transcribing or translating audio with Whisper, understanding images with Llama 4 vision, generating speech (TTS), or benchmarking models for speed vs quality. Trigger with phrases like "groq whisper", "groq transcription", "groq audio", "groq vision", "groq TTS", "groq speech".

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

78%Weight 40%Scale 1-5

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

A well-organized, actionable body that keeps the overview compact and pushes full walkthroughs into real reference files. Inline code covers the two most common workflows fully while the remaining three rely on signatures or references, and there is no explicit validation loop.

Suggestions

Add a short inline benchmarking code snippet (or a one-line copy-paste loop) so all five workflows have equally executable guidance rather than deferring benchmarking entirely to examples.md.

Consolidate the inline transcription skeleton into references/implementation.md (or trim it) to reduce duplication with the referenced full walkthrough and tighten conciseness.

Add an explicit error-recovery checkpoint in the benchmarking workflow (e.g., 'if a 429 is hit, back off and retry') to strengthen workflow clarity for the batch-style operation.

Dimension	Reasoning	Score
Conciseness	Mostly lean and assumes Claude's competence (no explanations of what Whisper/TTS are), with minor trimmable redundancy such as an inline transcription skeleton that largely duplicates content in references/implementation.md.	4 / 5
Actionability	Provides concrete, executable SDK calls with exact model IDs and parameters plus a copy-paste transcription skeleton and vision example, but translation, TTS, and benchmarking workflows only give method signatures or defer to references rather than full inline code.	4 / 5
Workflow Clarity	The five workflows are clearly numbered and each framed as a single SDK call with a structured error-handling table for recovery; no explicit validate-fix-retry loop, but the operations are read-only API calls where checkpoints are less critical.	4 / 5
Progressive Disclosure	Clear overview with well-signaled, one-level-deep references to the real files references/implementation.md and references/examples.md, with key examples inline and bulk detail appropriately split into those references.	5 / 5
	Total	17 / 20 Passed

Description

95%Weight 40%Scale 1-5

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, well-targeted description that concretely enumerates capabilities and supplies natural trigger phrases with clear what/when coverage. The only ding is second-person voice in the trigger clause ("you need").

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ("transcribing or translating audio with Whisper", "understanding images with Llama 4 vision", "generating speech (TTS)", "benchmarking models for speed vs quality") with comprehensive coverage, but the trigger clause uses second person ("Use when you need"), which reduces specificity by one per the voice guideline.	4 / 5
Completeness	Explicitly answers both what (Groq's non-chat endpoints: Whisper, Llama 4 vision, TTS, benchmarking) and when (an explicit "Use when you need..." clause plus concrete trigger phrases).	5 / 5
Trigger Term Quality	Provides comprehensive, natural trigger phrases a user would actually say ("groq whisper", "groq transcription", "groq audio", "groq vision", "groq TTS", "groq speech") covering synonyms and the relevant capability areas.	5 / 5
Distinctiveness Conflict Risk	Clear niche (Groq non-chat endpoints) with "groq"-prefixed triggers that distinguish it from the sibling chat-completions skill, giving minimal conflict risk.	5 / 5
	Total	19 / 20 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
Path: plugins/saas-packs/groq-pack/skills/groq-core-workflow-b/SKILL.md
Commit: 8585d6d

Reviewed: 13 days 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.