GroqCloud Automation
Automate AI inference, chat completions, audio translation, and TTS voice management through GroqCloud's high-performance API via Composio
Get the complete skill folder, including its scripts and reference files.
This workflow depends on an external MCP integration. Check the source for the server, account access and setup it requires.
When to use this skill
Use GroqCloud Automation when an AI agent needs a reusable SKILL.md workflow for this job: Automate AI inference, chat completions, audio translation, and TTS voice management through GroqCloud's high-performance API via Composio
When not to use it
Skip GroqCloud Automation when the task is outside the productivity category, or when a more specific skill in this directory already covers the same workflow with clearer triggers.
How to install
Where will you use it?
mkdir -p ~/.claude/skills/groqcloud-automation # Save SKILL.md to ~/.claude/skills/groqcloud-automation/SKILL.md
- Claude Code personal install: place the skill and its bundled files at ~/.claude/skills/groqcloud-automation/SKILL.md. For a shared project, commit the folder at .claude/skills/groqcloud-automation/ instead.
- Current Claude Code detects SKILL.md changes in watched directories during the session. If you just created a top-level skills directory, run /reload-skills. Check that the skill is listed before testing its trigger.
- For Claude chat or Cowork in the Desktop app, manage uploaded skills in Customize > Skills; copying files into a local Claude Code folder is not a Desktop install. Other agents may use different install locations.
Full install guide for Claude, Cursor, and Codex →
Try a starter prompt
After installing the skill, paste this starter prompt into your agent to verify it triggers on a small task.
Use the GroqCloud Automation skill for this task: Use GroqCloud Automation when this documented workflow matches the task. Confirm any required inputs or files before making changes.
What supports this recommendation?
71/100 provisional content score. This measures documentation, practical detail and source signals. It is not a measured task success rate or a security certification.
- Documentation
- 74/100
- Practical detail
- 68/100
- Source evidence
- 63/100
- Source signals
- 80/100
Model compatibility evidence
- claudeinferred
The skill text mentions Claude or a closely associated term. This is keyword-derived compatibility; no hands-on model test is recorded.
- chatgptuntested
No model-specific signal or recorded compatibility test was found.
- geminiuntested
No model-specific signal or recorded compatibility test was found.
- copilotuntested
No model-specific signal or recorded compatibility test was found.
- llamauntested
No model-specific signal or recorded compatibility test was found.
- perplexityuntested
No model-specific signal or recorded compatibility test was found.
- mistraluntested
No model-specific signal or recorded compatibility test was found.
- grokuntested
No model-specific signal or recorded compatibility test was found.
Inferred compatibility is based on content signals. Check the app, its available tools and setup requirements before running a skill.
What this skill does
# GroqCloud Automation
Automate AI inference workflows using GroqCloud's ultra-fast API -- chat completions, model discovery, audio translation, and TTS voice selection -- all orchestrated through the Composio MCP integration.
**Toolkit docs:** [composio.dev/toolkits/groqcloud](https://composio.dev/toolkits/groqcloud)
---
## Setup
1. Connect your GroqCloud account through the Composio MCP server at `https://rube.app/mcp` 2. The agent will prompt you with an authentication link if no active connection exists 3. Once connected, all `GROQCLOUD_*` tools become available for execution
---
## Core Workflows
### 1. Discover Available Models List all models available on GroqCloud to find valid model IDs before running inference.
**Tool:** `GROQCLOUD_LIST_MODELS`
``` No parameters required -- returns all available models with metadata. ```
Use this as a prerequisite before any chat completion call to ensure you reference a valid, non-deprecated model ID.
---
### 2. Run Chat Completions Generate AI responses for conversational prompts using a specified GroqCloud model.
**Tool:** `GROQCLOUD_GROQ_CREATE_CHAT_COMPLETION`
| Parameter | Type | Required | Description | |-----------|------|----------|-------------| | `model` | string | Yes | Model ID from `GROQCLOUD_LIST_MODELS` | | `messages` | array | Yes | Ordered list of `{role, content}` objects (`system`, `user`, `assistant`) | | `temperature` | number | No | Sampling temperature 0-2 (default: 1) | | `max_completion_tokens` | integer | No | Max tokens to generate | | `top_p` | number | No | Nucleus sampling 0-1 (default: 1) | | `stop` | string/array | No | Up to 4 stop sequences | | `stream` | boolean | No | Enable SSE streaming (default: false) |
---
### 3. Inspect Model Details Retrieve detailed metadata for a specific model including context window and capabilities.
**Tool:** `GROQCLOUD_GROQ_RETRIEVE_MODEL`
| Parameter | Type | Required | Description | |-----------|------|----------|-------------| | `model` | string | Yes | Model identifier (e.g., `groq-1-large`) |
---
### 4. Translate Audio to English Translate non-English audio files into English text using Whisper models.
**Tool:** `GROQCLOUD_GROQ_CREATE_AUDIO_TRANSLATION`
| Parameter | Type | Required | Description | |-----------|------|----------|-------------| | `file_path` | string | Yes | Local path, HTTP(S) URL, or base64 data URL for audio | | `model` | string | No | Model ID (default: `whisper-large-v3`). Note: `whisper-large-v3-turbo` may not support translations | | `response_format` | string | No | `json`, `verbose_json`, or `text` (default: `json`) | | `temperature` | number | No | Sampling temperature 0-1 (default: 0) |
---
### 5. List TTS Voices Enumerate available text-to-speech voices for Groq PlayAI models to drive voice selection UX.
**Tool:** `GROQCLOUD_LIST_VOICES`
``` Returns the set of supported TTS voices. Note: this is a static list maintained manually. ```
---
## Known Pitfalls
| Pitfall | Details | |---------|---------| | **Nested model list** | `GROQCLOUD_LIST_MODELS` response may be nested at `response['data']['data']` -- do not assume a flat top-level array | | **Hard-coded model IDs break** | Always fetch model IDs dynamically via `GROQCLOUD_LIST_MODELS`; hard-coded names can break when models are deprecated or renamed | | **Audio format validation** | `GROQCLOUD_GROQ_CREATE_AUDIO_TRANSLATION` rejects invalid or unsupported audio formats silently -- validate inputs before calling | | **Model metadata drifts** | Data from `GROQCLOUD_GROQ_RETRIEVE_MODEL` (context window, features) can change as models update -- do not treat it as static | | **TTS voice changes** | Voice sets from `GROQCLOUD_LIST_VOICES` may shrink or rename over time -- handle missing voices gracefully |
---
## Quick Reference
| Tool Slug | Purpose | |-----------|---------| | `GROQCLOUD_LIST_MODELS` | List all available models and metadata | | `GROQCLOUD_GROQ_CREATE_CHAT_COMPLETION` | Generate chat-based AI completions | | `GROQCLOUD_GROQ_RETRIEVE_MODEL` | Get detailed info for a specific model | | `GROQCLOUD_GROQ_CREATE_AUDIO_TRANSLATION` | Translate non-English audio to English text | | `GROQCLOUD_LIST_VOICES` | Retrieve available TTS voices for PlayAI |
---
*Powered by [Composio](https://composio.dev)*
Intended uses
- Use GroqCloud Automation when this documented workflow matches the task.
Implementation notes
- Review the source instructions and adapt inputs before running the workflow.
Try it, then tell us how it went
A copied prompt does not tell us whether the task worked. Report your result after checking the output. We collect your tool and outcome, never your files or prompt.