groq-inference

Ultra-fast LLM inference on custom LPU hardware. OpenAI-compatible API at api.groq.com. Lowest latency in the industry (500-1000+ tok/s). Supports chat completions, vision, audio (Whisper STT + TTS), tool calling, JSON mode, and streaming. Free tier available. Inference only — no training.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./backend/cli/skills/ml-inference/groq/SKILL.md

Quality

Content

82%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.

The body is highly actionable, well-structured, and mostly concise, with executable examples and practical troubleshooting throughout. Main improvement opportunity is moving the large model/endpoint tables into reference files for better progressive disclosure.

Suggestions

Move the detailed model selection tables and endpoint compatibility tables into a references file (e.g. MODELS.md) to slim the SKILL.md body and improve progressive disclosure.

Tighten the opening paragraph to avoid restating the frontmatter description's marketing framing.

Consider adding a short validation step after credential setup (e.g. a minimal ping call) to confirm the key works before proceeding.

Dimension	Reasoning	Score
Conciseness	Efficient throughout with concrete code and tables, but the opening paragraph restates the description's marketing framing and a few intros could be trimmed.	4 / 5
Actionability	Fully executable, copy-paste-ready code across streaming, JSON mode, tool calling, vision, and audio, plus concrete model IDs and an error-solution table covering common cases.	5 / 5
Workflow Clarity	Credential setup and quick start are clearly sequenced, and the rate-limit section shows a retry feedback loop; it is primarily a reference catalog rather than a fragile multi-step process, so no validation cap applies.	4 / 5
Progressive Disclosure	Well-organized into clear navigable sections with no nested external references, though the sizable model tables and endpoint details could optionally be split into reference files to slim the body.	4 / 5
	Total	17 / 20 Passed

Description

75%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.

The description is specific, actionable, and clearly niched to Groq's LPU offering, but it omits any explicit 'when to use' trigger guidance, which caps completeness. Adding a 'Use when...' clause would raise the score meaningfully.

Suggestions

Add an explicit trigger clause, e.g. 'Use when you need the fastest possible LLM inference, an OpenAI-compatible endpoint for open-weight models, or fast Whisper transcription.'

Include common natural phrasings and synonyms users might say (e.g. 'fast inference', 'low-latency LLM', 'Groq API') to broaden trigger-term coverage.

Trim the marketing claim 'Lowest latency in the industry' which reads as puffery rather than a concrete capability.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'chat completions, vision, audio (Whisper STT + TTS), tool calling, JSON mode, and streaming' — giving comprehensive coverage of the API surface.	5 / 5
Completeness	Has a clear 'what' (LPU inference, OpenAI-compatible API, feature list) but no 'Use when...' clause or equivalent explicit trigger guidance, capping completeness at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	Good keyword coverage including natural terms like 'LLM inference', 'chat completions', 'Whisper', and 'streaming', though coverage leans on product-specific jargon and misses a few common phrasings.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche — Groq LPU hardware with product-specific triggers — making it highly distinct with minimal conflict risk against other inference skills.	5 / 5
	Total	17 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/ml-inference/groq/SKILL.md
Commit: 3a6c3a9

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.