Mistral AI · For developers

Deploy and configure Higress AI Gateway for OpenClaw integration.

higress-group/higress

Generates vector embeddings through the 9Router /v1/embeddings endpoint, using models from providers such as OpenAI, Gemini, Mistral and Voyage for RAG and semantic search.

decolua/9router

Adds Liger Kernel support for a new HuggingFace Transformers model, or modifies existing monkey-patching.

linkedin/Liger-Kernel

TRIGGER when working with ai-sdk which is Laravel official first-party AI SDK.

trypostit/trypost

Shows how to build a Vibe plugin package in the Agent Plugins 1.0 format, with a plugin.json manifest and optional skills, MCP servers, hooks and other components.

mistralai/mistral-vibe

Develops production-ready Triton kernels for Liger Kernel. An agent skill from linkedin/Liger-Kernel.

linkedin/Liger-Kernel

Add a new AI model to Pipelex's own inference configuration: the backend TOMLs in .pipelex/inference/backends/ (OpenAI, Azure, Anthropic, Bedrock, Google, Vertex, Mistral and the rest), the kit…

Pipelex/pipelex

LLM provider initialization for bridgic projects. An agent skill from bitsky-tech/bridgic.

bitsky-tech/bridgic

A skill your agent uses when writing or migrating unit tests for the routesapp crate.

BodhiSearch/BodhiApp

Delegate a coding task to Mistral Vibe and supervise the result via git diff.

pcx-wave/vibe-skill

Guides writing or refactoring tests for the Mistral Vibe CLI agent so they check behavior through stable boundaries, like tool invocation or saved session shape, instead of internal calls.

mistralai/mistral-vibe

Entry point for KeiRouter — local/remote AI gateway with OpenAI-compatible REST for chat, image, TTS, embeddings, web search, web fetch.

mydisha/keirouter

A skill your agent uses when writing or migrating unit tests for the services crate.

BodhiSearch/BodhiApp

Draw Sebastian-Raschka-gallery-style TikZ architecture diagrams for any HuggingFace decoder-only LLM, with per-block parameter formulas and concrete numbers.

yzlnew/infra-skills

Chat / code generation via KeiRouter using OpenAI /v1/chat/completions or Anthropic /v1/messages format with streaming + auto-fallback combos.

mydisha/keirouter

Reference for Mistral Vibe, the CLI agent it runs inside: config files, env vars, agents, skills, tools, hooks and MCP servers, so the agent can explain and troubleshoot its own setup.

mistralai/mistral-vibe

Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral).

Orchestra-Research/AI-Research-SKILLs

Generate vector embeddings via KeiRouter /v1/embeddings using OpenAI / Gemini / Mistral / Voyage / Nvidia embedding models for RAG, semantic search, similarity.

mydisha/keirouter

Guides your agent in creating, updating or deleting Mistral Vibe skills: what to ask you, where skills live, how they are discovered and the SKILL.md frontmatter rules.

mistralai/mistral-vibe

Guides development with SAP AI Core and SAP AI Launchpad for enterprise AI/ML workloads on SAP BTP.

secondsky/sap-skills

Git workflow, CI/GitHub Actions, and supply-chain pinning rules for Mistral Vibe.

mistralai/mistral-vibe

Úsalo cuando el usuario pida redactar una factura, una cuenta de cobro o una nota de cobro.

gustavoeenriquez/MakerAi

Selects a base model for the user's use case by querying SageMaker Hub.

awslabs/agent-plugins

Organizes research with the self-hosted Open Notebook alternative to NotebookLM.

K-Dense-AI/scientific-agent-skills

Delegate a coding task to the Mistral Vibe CLI (vibe) as a background implementer, then review its diff and land it yourself.

amElnagdy/delegate-skills

Conventions for building and styling Textual widgets and TCSS in the Mistral Vibe codebase: selectable lists, tool headers, theme variables and overflow.

mistralai/mistral-vibe

Create or update implementation-ready design proposals for Mistral Vibe under docs/design, including a bounded design-tree decision review before drafting.

mistralai/mistral-vibe

Async and concurrency patterns for Mistral Vibe. An agent skill from mistralai/mistral-vibe.

mistralai/mistral-vibe

OpenCode's caching detection misses OpenAI-compatible proxies routing to Anthropic/Bedrock.

OnlyTerp/prompt-cache-skills

OpenCode doesn't set promptcachekey for Mistral models, missing the documented 10% cached-token discount.

OnlyTerp/prompt-cache-skills

Reference-free preference alignment, simpler than DPO. An agent skill from Luciole-Studio/Misaka-Agent.

Luciole-Studio/Misaka-Agent

L3 recipe that runs a Torch LLM PTQ end-to-end for AMD Quark — for PyTorch / HuggingFace transformers models (safetensors input): quantize → validate → evaluate.

amd/Quark

Torch LLM PTQ workflow for AMD Quark — from model selection to quantized output.

amd/Quark

Runs an end-to-end AMD Quark post-training quantization workflow for PyTorch / Hugging Face LLMs: inspect a Hub or local model, choose a quantization plan, create reproducible artifacts, request…

amd/Quark

This skill helps an LLM generate correct AI provider setup and configuration code using @ax-llm/ax.

dosco/aithy

Gate Mistral integrations with offline contract tests and a protected optional live smoke lane.

jeremylongshore/tons-of-skills-marketplace

Diagnose Mistral authentication, validation, throttling, model, transport, and provider failures without unsafe retries.

jeremylongshore/tons-of-skills-marketplace

Design Mistral organization, workspace, role, service-account, workload-identity, and application RBAC boundaries.

jeremylongshore/tons-of-skills-marketplace

Establish Mistral API access with server-side credentials, workspace ownership, and revocation evidence.

jeremylongshore/tons-of-skills-marketplace

Migrate an existing model workload to Mistral through semantic mapping, dual-run evaluation, bounded canary, and provider rollback.

jeremylongshore/tons-of-skills-marketplace

Control Mistral demand with live workspace limits, token-aware admission, bounded retry, and backpressure.

jeremylongshore/tons-of-skills-marketplace

Design a Mistral integration from policy gateway through adapter, queues, state reconciliation, and audited output.

jeremylongshore/tons-of-skills-marketplace

Design a pinned Mistral client adapter with typed results, cancellation, retry classification, and usage accounting.

jeremylongshore/tons-of-skills-marketplace

Implement Mistral Workflows event ingestion over SSE with checkpoints, deduplication, reconnect control, and reconciliation.

jeremylongshore/tons-of-skills-marketplace

Use multiple AI providers (OpenAI, Anthropic, Google, Meta) through OpenRouter's unified API.

jeremylongshore/tons-of-skills-marketplace

Adding LLM and AI capabilities to a MoonBit Golem agent. An agent skill from golemcloud/golem.

golemcloud/golem

Select appropriate Ollama models for processing sensitive but legal content.

divinevideo/divine-mobile

A skill your agent uses when choosing an open-weight LLM and clearing it for use — which family and size fit the task, the hardware and the budget, and above all whether the license permits shipping.

ericrisco/rsc-harness