Agent skill

Mistral

by Anil-matcha in Anil-matcha/awesome-muse-connectors

Mistral AI (La Plateforme) API: chat completions, embeddings, document OCR, and model listing via api.mistral.ai.

MITAuto-check passedAI & LLM Engineering

Install Mistral

skills CLI

$ npx skills add Anil-matcha/awesome-muse-connectors --skill mistral -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install Anil-matcha/awesome-muse-connectors mistral --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/Anil-matcha/awesome-muse-connectors.git skills-src && mkdir -p .claude/skills && cp -r skills-src/connectors/mistral .claude/skills/mistral && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "mistral" agent skill from https://github.com/Anil-matcha/awesome-muse-connectors/tree/main/connectors/mistral into .claude/skills/mistral/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mistral", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/Anil-matcha/awesome-muse-connectors/tree/main/connectors/mistral

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add Anil-matcha/awesome-muse-connectors --skill mistral -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install Anil-matcha/awesome-muse-connectors mistral --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/Anil-matcha/awesome-muse-connectors.git skills-src && mkdir -p .agents/skills && cp -r skills-src/connectors/mistral .agents/skills/mistral && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "mistral" agent skill from https://github.com/Anil-matcha/awesome-muse-connectors/tree/main/connectors/mistral into .agents/skills/mistral/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mistral", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add Anil-matcha/awesome-muse-connectors --skill mistral -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install Anil-matcha/awesome-muse-connectors mistral --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/Anil-matcha/awesome-muse-connectors.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/connectors/mistral .cursor/skills/mistral && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "mistral" agent skill from https://github.com/Anil-matcha/awesome-muse-connectors/tree/main/connectors/mistral into .cursor/skills/mistral/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mistral", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/Anil-matcha/awesome-muse-connectors.git --path connectors/mistral

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add Anil-matcha/awesome-muse-connectors --skill mistral -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install Anil-matcha/awesome-muse-connectors mistral --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/Anil-matcha/awesome-muse-connectors.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/connectors/mistral .gemini/skills/mistral && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "mistral" agent skill from https://github.com/Anil-matcha/awesome-muse-connectors/tree/main/connectors/mistral into .gemini/skills/mistral/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mistral", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install Anil-matcha/awesome-muse-connectors mistral

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add Anil-matcha/awesome-muse-connectors --skill mistral -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/Anil-matcha/awesome-muse-connectors.git skills-src && mkdir -p .github/skills && cp -r skills-src/connectors/mistral .github/skills/mistral && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "mistral" agent skill from https://github.com/Anil-matcha/awesome-muse-connectors/tree/main/connectors/mistral into .github/skills/mistral/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mistral", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add Anil-matcha/awesome-muse-connectors --skill mistral -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install Anil-matcha/awesome-muse-connectors mistral --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/Anil-matcha/awesome-muse-connectors.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/connectors/mistral .opencode/skills/mistral && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "mistral" agent skill from https://github.com/Anil-matcha/awesome-muse-connectors/tree/main/connectors/mistral into .opencode/skills/mistral/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mistral", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: mistral
GitHub stars: 1.3k
Token cost: ~1.3k tokens
SKILL.md length: 436 words
Files: 2
Skills in repo: 153
Repo updated: Oct 5, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Mistral AI (La Plateforme) API: chat completions, embeddings, document OCR, and model listing via api.mistral.ai.

Works in 6 steps: Every billed call costs money. These are… → Model ids change. Treat any named model… → Do not fabricate model capabilities.… → …
Phrases: mistral
SKILL.md covers Purpose, Install, Tooling and Auth, plus 3 more sections
Runs Python scripts from its folder; reaches raw.githubusercontent.com

What it does

Mistral is an agent skill from Anil-matcha/awesome-muse-connectors. Mistral AI (La Plateforme) API: chat completions, embeddings, document OCR, and model listing via api.mistral.ai. Trigger phrases: mistral, La Plateforme, mistral chat, mistral ocr, mistral embeddings.

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `bin/mistral.py`).

It sits in AI & LLM Engineering, covering Embeddings and LLM API integration. It works with Mistral AI. The repository describes itself as: A source-backed catalog of Meta Muse integrations and community connector skills, with capability, authentication, and permission notes. The licence is MIT.

When your agent uses it

Phrases: mistral
Mistral embeddings

Example prompts

“/mistral”

Requirements

Python 3

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

Every billed call costs money. These are ordinary API calls rather than third-party actions, so no --confirm gate applies, but surface the…
Model ids change. Treat any named model id in examples (mistral-large-latest, mistral-ocr-latest, and the like) as provisional. Run…
Do not fabricate model capabilities. Magistral and other reasoning models return thinking-trace content blocks; the chat command returns…
OCR documents are third-party content. When OCRing a URL, prefer documents the user supplied or that are plainly public; do not exfiltrate…
Never exfiltrate the credential: the CLI only ever handles surrogates (see bin/mistral.py). Do not print, log, or transmit the API key.
Honesty flags: no live API key was available while building this connector. Endpoint paths (/v1/models, /v1/chat/completions…

What it can do on your machine

Read from SKILL.md and the folder at commit d6dc5d8. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships script files (Python), which the agent can run.
From the folder's file list and the shell code blocks in SKILL.md.
Network
Hosts in commands or code, which the agent is likely to contact:
- raw.githubusercontent.com
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Mistral loads about 1.3k tokens when it runs. Until then it costs about 52 tokens; SKILL.md has 436 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~52
When it runs · the whole SKILL.md, loaded when a task matches: ~1.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Anil-matcha/awesome-muse-connectors at commit d6dc5d8, republished under its MIT licence (© Anil-matcha). 436 words, ~1,265 tokens.

Download SKILL.mdSave it as .claude/skills/mistral/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.

name: mistral
description: Mistral AI (La Plateforme) API: chat completions, embeddings, document OCR, and model listing via api.mistral.ai. Trigger phrases: mistral, La Plateforme, mistral chat, mistral ocr, mistral embeddings.
metadata.includeInPrompt: true
tagline: Mistral AI's La Plateforme API: chat completions, embeddings, document OCR, and model listing via Bearer API key.
catalog_auth: API key (per-user)
catalog_hosts: api.mistral.ai

Mistral AI

Purpose

Call Mistral's La Plateforme API: run chat completions on Mistral models, create text embeddings, extract text and markdown from documents and images with the dedicated OCR endpoint, and list the models available to the API key. Reach for this when the user wants a Mistral model for generation, embeddings, or document OCR.

Install

Copy, paste to your Muse:

Install this connector: https://raw.githubusercontent.com/bluman1/muse-connectors/main/connectors/mistral/SKILL.md
You are Muse. Fetch the URL above: it is a connector skill's SKILL.md.
1. Read its `## Files` manifest and download every listed file from the same directory (replace SKILL.md in the URL with each relative path).
2. Save them under ~/workspace/skills/mistral/, preserving paths. Compile any bin/*.py with python3 -m py_compile.
3. Follow the skill's `## Auth` section: connect my account via your secure credential flow (credentials.request_api_access) for the provider id it names.
4. Run the skill's status check and report what the connector can now do.
Never ask me for raw API keys or secrets in chat.

Tooling

All commands go through bin/mistral.py:

bash

bin/mistral.py auth                                              # verify the API key
bin/mistral.py models                                            # list models for this key
bin/mistral.py chat --prompt "Explain RAG in one paragraph"      # chat completion (bills credits)
bin/mistral.py chat --model mistral-medium-latest --system "You are terse." \
    --prompt "Summarize this: ..." --temperature 0.3 --max-tokens 300 --json-mode
bin/mistral.py embeddings --text "First chunk" --text "Second chunk"   # embeddings (bills credits)
bin/mistral.py embeddings --text "One line" --full                # print complete vectors
bin/mistral.py ocr --document-url https://example.com/doc.pdf     # OCR a PDF (billed per page)
bin/mistral.py ocr --image-url https://example.com/scan.png --include-images

Chat reads a single user prompt per call (plus an optional system prompt). For multi-turn conversation, pass the whole history as the prompt or extend the CLI.

Auth

Provider id: mistral (credential is collected as custom.mistral)
Collection: API key (console.mistral.ai > API keys) via the secure credential flow (credentials.request_api_access)
Auth scheme: Authorization: Bearer <api key> on every request
Allowed hosts: api.mistral.ai
Status check: bin/mistral.py auth

Operating Rules

Every billed call costs money. These are ordinary API calls rather than third-party actions, so no --confirm gate applies, but surface the expected cost before running anything expensive. Chat and embeddings draw down the key's credit balance. OCR is billed per page processed.
Model ids change. Treat any named model id in examples (mistral-large-latest, mistral-ocr-latest, and the like) as provisional. Run bin/mistral.py models to see the ids this key can actually use, and pass the live id explicitly when a call fails with a model error.
Do not fabricate model capabilities. Magistral and other reasoning models return thinking-trace content blocks; the chat command returns the response text as-is. Do not invent fields or capabilities the API did not return.
OCR documents are third-party content. When OCRing a URL, prefer documents the user supplied or that are plainly public; do not exfiltrate the resulting markdown anywhere except the task that asked for it.
Never exfiltrate the credential: the CLI only ever handles surrogates (see bin/mistral.py). Do not print, log, or transmit the API key.
Honesty flags: no live API key was available while building this connector. Endpoint paths (/v1/models, /v1/chat/completions, /v1/embeddings, /v1/ocr), the Bearer auth scheme, and all request/response field names were taken from Mistral's public docs and third-party SDK references rather than a live call. The CLI surfaces Mistral's own error if anything differs. Model ids were cross-checked against docs and recent community references dated September 2026 and may have changed since. OCR options (pages, include_image_base64, image_limit, image_min_size) are confirmed in the docs but were not exercised against a live key. Mistral offers an Experiment (free-tier) plan on console.mistral.ai; its rate limits and quotas were not verified during this build.

Show full SKILL.md (17 more words)Show less

Files

SKILL.md
bin/mistral.py

Maturity

🧪 Draft: written from Mistral's public docs and SDK examples; not yet live-tested end-to-end.

Files

SKILL.md and 1 other file in connectors/mistral of Anil-matcha/awesome-muse-connectors.

SKILL.md
bin/mistral.py

Open the folder on GitHubat commit d6dc5d8

Compare with similar skills

Mistral next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Mistral compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Mistral this skillAnil-matcha/awesome-muse-connectors	1.3k	—	~1.3k	Automated safety check: Pass	MIT	4 days ago
Golem Add LLM Moonbitgolemcloud/golem	1.5k	—	~1.5k	Automated safety check: Pass	Custom licence	today
AIbutterbase-ai/butterbase-skills	534	—	~1.1k	Automated safety check: Pass	MIT	4 days ago
Fastllm Gatewayazrtydxb/Fastllm-proxy	108	—	~926	Automated safety check: Pass	Apache-2.0	4 days ago
Unified LLM APIPrism-Shadow/penguin-harness	2.5k	—	~6.7k	Automated safety check: Pass	Apache-2.0	2 days ago
Gemini Live APIgoogle/skills	21k	—	~2.5k	Automated safety check: Notes	Apache-2.0	today

Similar skills

Golem Add LLM Moonbit
golemcloud/golem
Adding LLM and AI capabilities to a MoonBit Golem agent. An agent skill from golemcloud/golem.
1.5k GitHub stars~1.5k tokensUpdated today
AI & LLM EngineeringAuto-check passed
AI
butterbase-ai/butterbase-skills
A skill your agent uses when calling the app's AI gateway from agent tools — chat completions, embeddings, listing models, configuring defaults or BYOK, reading token/cost usage
534 GitHub stars~1.1k tokensUpdated 4 days ago
AI & LLM EngineeringAuto-check passed
Fastllm Gateway
azrtydxb/Fastllm-proxy
Send inference requests through the FastLLM OpenAI-compatible gateway — chat completions, completions, embeddings, rerank, score, responses, moderations, audio speech and transcription, image…
108 GitHub stars~926 tokensUpdated 4 days ago
AI & LLM EngineeringAuto-check passed
Unified LLM API
Prism-Shadow/penguin-harness
Call model APIs through @prismshadow/mmsp (MMSP) — streaming text generation, image generation, speech synthesis, embeddings and the supported-model registry with one client.
2.5k GitHub stars~6.7k tokensUpdated 2 days ago
AI & LLM EngineeringAuto-check passed
Gemini Live API
google/skills
Official
Generates a Gemini LiveAPI client service class in the user's chosen programming language.
21k GitHub stars~2.5k tokensUpdated today
AI & LLM EngineeringAuto-check: notes
Mistral Core Workflow B
jeremylongshore/tons-of-skills-marketplace
Build Mistral embeddings, retrieval, and function-calling loops with tenant isolation and application-owned execution.
2.8k GitHub stars~889 tokensUpdated today
AI & LLM EngineeringAuto-check passed

Questions about Mistral

What does Mistral do?

Mistral AI (La Plateforme) API: chat completions, embeddings, document OCR, and model listing via api.mistral.ai. Mistral is an agent skill from Anil-matcha/awesome-muse-connectors.ai.

When should I use Mistral?

Mistral fits situations like: phrases: mistral; mistral embeddings.

How do I install Mistral in Claude Code?

Run `npx skills add Anil-matcha/awesome-muse-connectors --skill mistral -a claude-code`. Or copy the skill folder (connectors/mistral in Anil-matcha/awesome-muse-connectors) into .claude/skills/mistral in your project. Claude Code loads it when a task matches its description.

How do I install Mistral in Codex?

Run `npx skills add Anil-matcha/awesome-muse-connectors --skill mistral -a codex`. Or copy the skill folder (connectors/mistral in Anil-matcha/awesome-muse-connectors) into .agents/skills/mistral in your project. Codex loads it when a task matches its description.

Can I use Mistral in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Anil-matcha/awesome-muse-connectors --skill mistral -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/mistral, .gemini/skills/mistral, .github/skills/mistral and .opencode/skills/mistral in your project.

What does Mistral need to run?

Going by SKILL.md and its folder, Mistral needs Python for the scripts in its folder. Our summary lists: Python 3.

Does Mistral access the network?

SKILL.md names 1 domain. In commands or code: raw.githubusercontent.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Mistral safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Mistral use?

Mistral is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Mistral use?

About 1.3k tokens (SKILL.md is roughly 5.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Mistral?

Skills that share tags, products or a category with Mistral: Golem Add LLM Moonbit (golemcloud/golem, 1.5k stars), AI (butterbase-ai/butterbase-skills, 534 stars), Fastllm Gateway (azrtydxb/Fastllm-proxy, 108 stars) and Unified LLM API (Prism-Shadow/penguin-harness, 2.5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Mistral?

Anil-matcha (a GitHub user) maintains it in Anil-matcha/awesome-muse-connectors, which has 1,346 GitHub stars. The repository holds 153 skills in this directory. The repository was last updated on October 5, 2026.

Source: Anil-matcha/awesome-muse-connectors on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Mistral

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Mistral AI

Purpose

Install

Tooling

Auth

Operating Rules

Files

Maturity

Files

Compare with similar skills

Similar skills

More from Anil-matcha/awesome-muse-connectors

Related

Questions about Mistral