AGENT SKILL

mistral_ai-automation

Automate Mistral AI tasks via Rube MCP (Composio): completions, embeddings, fine-tuning, and model management. Always search tools first for current schemas.

License 许可
MIT
最近更新
2026-11-03
Stars
★ 1
Forks
0

01 前言 Front Matter

name
mistral_ai-automation
requires
{ "mcp": [ "rube" ] }
description
Automate Mistral AI tasks via Rube MCP (Composio): completions, embeddings, fine-tuning, and model management. Always search tools first for current schemas.

03 SKILL.md 正文

Mistral AI Automation via Rube MCP

Automate Mistral AI operations through Composio's Mistral AI toolkit via Rube MCP.

Toolkit docs: composio.dev/toolkits/mistral_ai

Prerequisites

  • Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
  • Active Mistral AI connection via RUBE_MANAGE_CONNECTIONS with toolkit mistral_ai
  • Always call RUBE_SEARCH_TOOLS first to get current tool schemas

Setup

Get Rube MCP: Add https://rube.app/mcp as an MCP server in your client configuration. No API keys needed — just add the endpoint and it works.

  1. Verify Rube MCP is available by confirming RUBE_SEARCH_TOOLS responds
  2. Call RUBE_MANAGE_CONNECTIONS with toolkit mistral_ai
  3. If connection is not ACTIVE, follow the returned auth link to complete setup
  4. Confirm connection status shows ACTIVE before running any workflows

Tool Discovery

Always discover available tools before executing workflows:

RUBE_SEARCH_TOOLS: queries=[{"use_case": "completions, embeddings, fine-tuning, and model management", "known_fields": ""}]

This returns:

  • Available tool slugs for Mistral AI
  • Recommended execution plan steps
  • Known pitfalls and edge cases
  • Input schemas for each tool

Core Workflows

1. Discover Available Mistral AI Tools

RUBE_SEARCH_TOOLS:
  queries:
    - use_case: "list all available Mistral AI tools and capabilities"

Review the returned tools, their descriptions, and input schemas before proceeding.

2. Execute Mistral AI Operations

After discovering tools, execute them via:

RUBE_MULTI_EXECUTE_TOOL:
  tools:
    - tool_slug: "<discovered_tool_slug>"
      arguments: {<schema-compliant arguments>}
  memory: {}
  sync_response_to_workbench: false

3. Multi-Step Workflows

For complex workflows involving multiple Mistral AI operations:

  1. Search for all relevant tools: RUBE_SEARCH_TOOLS with specific use case
  2. Execute prerequisite steps first (e.g., fetch before update)
  3. Pass data between steps using tool responses
  4. Use RUBE_REMOTE_WORKBENCH for bulk operations or data processing

Common Patterns

Search Before Action

Always search for existing resources before creating new ones to avoid duplicates.

Pagination

Many list operations support pagination. Check responses for next_cursor or page_token and continue fetching until exhausted.

Error Handling

  • Check tool responses for errors before proceeding
  • If a tool fails, verify the connection is still ACTIVE
  • Re-authenticate via RUBE_MANAGE_CONNECTIONS if connection expired

Batch Operations

For bulk operations, use RUBE_REMOTE_WORKBENCH with run_composio_tool() in a loop with ThreadPoolExecutor for parallel execution.

Known Pitfalls

  • Always search tools first: Tool schemas and available operations may change. Never hardcode tool slugs without first discovering them via RUBE_SEARCH_TOOLS.
  • Check connection status: Ensure the Mistral AI connection is ACTIVE before executing any tools. Expired OAuth tokens require re-authentication.
  • Respect rate limits: If you receive rate limit errors, reduce request frequency and implement backoff.
  • Validate schemas: Always pass strictly schema-compliant arguments. Use RUBE_GET_TOOL_SCHEMAS to load full input schemas when schemaRef is returned instead of input_schema.

Quick Reference

Operation Approach
Find tools RUBE_SEARCH_TOOLS with Mistral AI-specific use case
Connect RUBE_MANAGE_CONNECTIONS with toolkit mistral_ai
Execute RUBE_MULTI_EXECUTE_TOOL with discovered tool slugs
Bulk ops RUBE_REMOTE_WORKBENCH with run_composio_tool()
Full schema RUBE_GET_TOOL_SCHEMAS for tools with schemaRef

Toolkit docs: composio.dev/toolkits/mistral_ai

04 同仓库更多 Skills

siuserxiaowei
siuserxiaowei/xiaowei-ai-tools

x-article-draft-uploader

把本地 Markdown 转为经核验的 X Articles 新草稿。适用于需要保留首图封面、正文图片相对位置,并在独立 Playwright 会话中复用用户已授权 Chrome 登录态的任务;不负责公开发布。

★ 1
siuserxiaowei
siuserxiaowei/xiaowei-ai-tools

wecom-operations

通过用户已配置的官方 wecom-cli 管理企业微信文档、智能文档、待办、会议和日程。适合创建或查询这些云端对象、把本地 Markdown 转为智能文档,以及在明确确认后更新或取消对象;不发送消息、不控制桌面客户端。

★ 1
siuserxiaowei
siuserxiaowei/xiaowei-ai-tools

wecom-local-vault

Inspect authorized local WeCom databases on macOS, create private plaintext snapshots, and query or export contacts, conversations, and messages without modifying the source account store. Use when the user asks to parse 企业微信/WeCom local data, recover a private database snapshot, inspect local contacts or sessions, search chat history, or export a bounded conversation.

★ 1
siuserxiaowei
siuserxiaowei/xiaowei-ai-tools

wechat-reading

Read and analyze WeRead/微信读书 search results, book metadata, bookshelf entries, progress, notes, highlights, public reviews, recommendations, and reading statistics through the official read-only Agent Gateway. Use for WeRead account questions or exports; do not imply that the current Gateway can add, remove, upload, rate, like, or edit content.

★ 1
siuserxiaowei
siuserxiaowei/xiaowei-ai-tools

wechat-mp-batch-exporter

Build a bounded, private archive from known WeChat Official Account article URLs or an owner-authorized account-history export, with explicit reconciliation of article, publish-group, and platform-marked-original counts. Use for batch body capture, history normalization, or enhanced metrics/comments workflows. Do not use for a one-page summary or to automate the WeChat client.

★ 1
siuserxiaowei
siuserxiaowei/xiaowei-ai-tools

wechat-local-vault

在 macOS 本机建立并查询私有微信数据快照。适用于盘点数据库、离线校验已有密钥候选、创建全量或增量明文快照、查会话与联系人、按时间检索消息、导出指定聊天、查看朋友圈或收藏,以及准备群聊摘要素材。所有查询只读,默认隐藏内部账号标识,不操控微信界面,也不发送任何内容。

★ 1