$ ~/registry/skill/composiohq-composio-skills-mistral-ai-automation

SKILL

Mistral AI Automation

Name: Mistral AI Automation
Author: Composio

Automate Mistral AI files, fine-tuning, OCR, batch jobs, and RAG workflows.

Stars

★ 67,763

Source

GitHub

Updated

2026-07-15

// securityCaution

Prompt only, no code
Open source
Community-trusted· 64.7k

Summary

This skill appears in a well-known open-source community repository, which lowers baseline concern, but its documentation explicitly routes actions through Composio MCP to operate a Mistral AI account, files, and document libraries. Overall it is best rated as caution due to third-party account access, file transfer, and partially undisclosed tool schemas.

CredentialsCaution

The header says 'no keys', but the README explicitly states 'Connect your Mistral AI account when prompted (API key authentication)', so the credential requirement is described inconsistently. The credential is sensitive, but based on the material it appears tied to the stated Mistral AI/Composio functionality, with no explicit sign of credential abuse.

Network egressCaution

The README instructs users to add the Composio MCP server at `https://rube.app/mcp` and upload files to Mistral AI for fine-tuning, OCR, batch processing, and RAG libraries, so user data is clearly sent to third-party services. The destinations are relevant to the stated purpose, but the material does not fully disclose all effective endpoints or data-flow details.

Code executionLow risk

The system flags it as prompt-only, and the material does not describe spawning local processes, executing shell/scripts, or requesting system-level control. Its behavior is presented as remote tool invocation rather than local code execution.

Data accessCaution

The skill claims it can upload/download files, list and retrieve files, create libraries, and manage RAG documents, so data access centers on files and metadata provided to Mistral AI/Composio. This is consistent with the stated functionality, but it does involve binary content transfer and some input schemas are deferred to runtime lookup, reducing transparency.

Supply chainLow risk

The source is a GitHub open-source repository with very strong community adoption (~64.7k stars), which is a meaningful positive signal. Although the license is unspecified, maintenance status is unknown, and reliance on Composio MCP/rube.app adds third-party dependency surface, the material does not show a concrete supply-chain red flag severe enough to justify a high-risk rating.

Recommendations

Verify the actual API key requirement, permission scope, and who stores it before connecting, since the documentation is inconsistent.
Upload only the minimum necessary files and avoid sending sensitive training data, OCR documents, or internal materials to third-party services.
Request the full tool schemas and a clear data-flow description, especially for transfers involving `rube.app/mcp` and Mistral AI.
Test first with a non-production account and sanitized data, and rotate any related API keys regularly.

Audited by: gpt-5.4 · 2026-06-17

// install

Copy the install command and let the AI configure it · recommended for beginners

Please install the "Mistral AI Automation" skill from askskill:
1. Download https://raw.githubusercontent.com/ComposioHQ/awesome-claude-skills/master/composio-skills/mistral-ai-automation/SKILL.md
2. Save it as ~/.claude/skills/mistral-ai-automation/SKILL.md
3. Reload skills and tell me it's ready

// download

Download SKILL.mdInstall manifest ↗

// docs

Mistral AI Automation

Automate your Mistral AI workflows -- upload files for fine-tuning, batch processing, and OCR, manage document libraries for RAG-enabled agents, list and retrieve files, track fine-tuning jobs, and integrate Mistral AI into cross-app data pipelines.

Toolkit docs: composio.dev/toolkits/mistral_ai

Setup

Add the Composio MCP server to your client: https://rube.app/mcp
Connect your Mistral AI account when prompted (API key authentication)
Start using the workflows below

Core Workflows

1. Upload Files to Mistral AI

Use MISTRAL_AI_UPLOAD_FILE to upload files for fine-tuning, batch processing, or OCR.

Tool: MISTRAL_AI_UPLOAD_FILE
Inputs:
  - file: object (required)
    - name: string -- destination filename (e.g., "training_data.jsonl")
    - mimetype: string -- MIME type (e.g., "application/pdf", "application/jsonl")
    - s3key: string -- S3 key of a previously downloaded/stored file
  - purpose: "fine-tune" | "batch" | "ocr" (default "fine-tune")

Limits: Maximum file size is 512 MB. For fine-tuning, only .jsonl files are supported.

2. List and Retrieve Files

Use MISTRAL_AI_LIST_FILES to browse uploaded files with pagination, and MISTRAL_AI_RETRIEVE_FILE to get metadata for a specific file.

Tool: MISTRAL_AI_LIST_FILES
Inputs:
  - limit: integer (optional, min 1)
  - after: string (file ID cursor for next page)
  - order: "asc" | "desc" (default "desc")

Tool: MISTRAL_AI_RETRIEVE_FILE
Inputs:
  - file_id: string (required) -- UUID obtained from List Files

3. Create Document Libraries

Use MISTRAL_AI_CREATE_LIBRARY to group documents into libraries for use with RAG-enabled Mistral AI agents.

Tool: MISTRAL_AI_CREATE_LIBRARY
Inputs:
  - name: string (required) -- e.g., "Project Documents"
  - description: string (optional)

4. Upload Documents to a Library

Use MISTRAL_AI_UPLOAD_LIBRARY_DOCUMENT to add documents to a library for RAG retrieval by Mistral AI agents.

Tool: MISTRAL_AI_UPLOAD_LIBRARY_DOCUMENT
  - Requires library_id and file details
  - Call RUBE_GET_TOOL_SCHEMAS for full input schema before use

5. List Libraries and Download Files

Use MISTRAL_AI_LIST_LIBRARIES to discover available document libraries, and MISTRAL_AI_DOWNLOAD_FILE to retrieve file content.

Tool: MISTRAL_AI_LIST_LIBRARIES
  - Lists all document libraries with metadata (id, name, document counts)
  - Call RUBE_GET_TOOL_SCHEMAS for full input schema

Tool: MISTRAL_AI_DOWNLOAD_FILE
  - Downloads raw binary content of a previously uploaded file
  - Call RUBE_GET_TOOL_SCHEMAS for full input schema

6. Track Fine-Tuning Jobs

Use MISTRAL_AI_GET_FINE_TUNING_JOBS to list and filter fine-tuning jobs by model, status, and creation time.

Tool: MISTRAL_AI_GET_FINE_TUNING_JOBS
  - Supports filtering by model, status, creation time, and W&B integration
  - Call RUBE_GET_TOOL_SCHEMAS for full input schema

Known Pitfalls

Pitfall	Detail
Fine-tune file format	Only `.jsonl` files are supported for fine-tuning uploads. Other formats will be rejected.
File size limit	Maximum upload size is 512 MB per file.
File object structure	`MISTRAL_AI_UPLOAD_FILE` requires an `s3key` referencing a previously stored file, not raw binary content. Use a download action first to stage files in S3.
Pagination cursors	`MISTRAL_AI_LIST_FILES` uses cursor-based pagination via the `after` parameter (file ID). Continue fetching until no more results are returned.
Library document processing	Uploaded library documents are processed asynchronously. They may not be immediately available for RAG queries after upload.

…

View full docs ↗

Automate ElevenLabs text-to-speech, voice management, and audio history workflows.

ComposioGet→

$ loading_