Skip to content

Pricing
Compare
Blog

Sign in Get started

Site footer

Route every request to the right model, agent, skill, tool or human, and know why.

curl -LsSf https://opensmartroute.ai/install.sh | sh

Apache-2.0SDK 1.3.0enterprise edition

Product

Models
Marketplace
Playground
Browser extension
Pricing

Developers

Documentation
REST API
Python SDK
TypeScript SDK
MCP server
Self-hosting

Company

Blog
Changelog
Support
Security
PyPI
npm
Source

OpenSmartRouteCopyright 2026 the OpenSmartRoute contributors. Open source under Apache-2.0.

Terms Privacy Report a vulnerability

Support assistant

Connecting...

Hi - I answer from the OpenSmartRoute documentation: routing, the API, plans and quotas, self-hosting. Ask away, or open a support ticket if you need a person.

Grounded in the docs - follow a source before acting on it.

Marketplace/Skills

Skills that teach a model one job well

Step-by-step SKILL.md packages an AI follows for a single kind of task.

A skill is a focused playbook - instructions, examples and constraints - that makes any model reliable at one job, from SQL reporting to changelog writing. The router fills a plan's skill slot with the best match for the request.

150.3K SkillsPublish yours

One job, done consistently
Model-agnostic instructions
Composable into plans

Agents6380 Personas6399 Prompts17744 Templates31 Tools31517 Models

150630 results

446

invairiant

invAIriant — an evidence-based, multi-lens architecture-audit protocol for LLM coding agents. This skill IS the product: it runs the audit. Commands: audit-pr, audit-range, audit-commit, audit-module,

by mindicatorGitHub

Not rated yet

Free

arc-worktrees

Use when starting work on a separate task — in particular a new ticket that differs from the current branch. Also use when needing isolated workspace for parallel work, multiple agents on different ta

by alchemmistGitHub

alps

Create, validate, and improve ALPS profiles. Generate from natural language descriptions, validate existing profiles, and get improvement suggestions.

by majiayu000GitHub

in-app-purchases

| Atributo | Valor |

by majiayu000GitHub

skill-creator-anthropic

Guide for creating effective skills. Use when users want to create a new skill (or update an existing skill) that extends the model's capabilities with specialized knowledge, workflows, or tool integr

by majiayu000GitHub

grok-build-supervisor

Initialize the persistent local proxy, then immediately ensure a visible Grok Build TUI for the current workspace when /grok_execute on activates, and continuously supervise that coding-agent session

by VanyangyangGitHub

sun-style-writing

用"孙学"风格写作：极度克制的白描叙事，短句节奏，数字锚定，物件承载情感，沉默即高潮。适用于第一人称非虚构叙事、个人经历长文、情感故事、回忆录、纪实散文、人物特写。当用户要求"孙哥风格""孙学写法""冷叙事""白描长文" "克制的情感表达""不煽情的故事""冰山写法""像《我的女友景甜》那样写"时使用此技能。也适用于用户要求写出"不像 AI""有人味""高级感""文学性"的中文叙事长文。核

by KKKenChowGitHub

claude-md-drift-check

Use when detecting drift between CLAUDE.md (or AGENTS.md, the Codex CLI alias) / _meta narrative and live repository state. Ten checks: absolute-path resolution, 01-projects/ count claims, issue-refer

by majiayu000GitHub

advanced-evaluation

This skill should be used when the user asks to "implement LLM-as-judge", "compare model outputs", "create evaluation rubrics", "mitigate evaluation bias", or mentions direct scoring, pairwise compari

by anubhavg-icplGitHub

ai-security

Use when assessing AI/ML systems for prompt injection, jailbreak vulnerabilities, model inversion risk, data poisoning exposure, or agent tool abuse. Covers MITRE ATLAS technique mapping, injection si

by bestagentkitsGitHub

directory-layout

Generates optimal directory layout patterns for any project. Takes an idea description, a single file, or an existing folder of files and produces a cohesive, principled directory structure with READM

by jairferraraGitHub

tscg-instance-pipeline

Complete pipeline for creating a TSCG Instance in 4 sequential steps: Proposition, Analysis, Modeling, and Simulation. Use this skill whenever the user mentions an instance, wants to model a system wi

by EchopraxiumGitHub

dingtalk-doc

钉钉文档管理技能。当用户发送的消息中包含 alidocs.dingtalk.com 链接、要求总结/读取/查看/更新钉钉文档或钉钉知识库文档，或当前上下文已明确对象是钉钉文档时使用。关键词：钉钉文档、钉钉知识库、alidocs、总结、读取、查看、更新、修改、文档、链接。

by ShyZhenGitHub

Aerodrome Router

This skill should be used when the user asks about "router", "swap", "addLiquidity", "removeLiquidity", "zap", "multi-hop", or needs to understand Aerodrome's Router operations.

by cyoteeGitHub

frontend

MUST USE for frontend/web UI/UX/visual work: building, styling, redesigning pages/components, React setup, performance audits, visual QA, taste, and polish. Routes four rulesets: design taste router a

by majiayu000GitHub

crystallize

Turns a finished MCP investigation into a standalone Python script that calls the Falcon API directly — no model, no tokens, no MCP server — and renders an HTML dashboard. Use after an investigation h

by kyle9021GitHub

mde-maps

mdeai Google Maps: Places (New), ChatMap, Gemini grounding, MCP tools, keys, Mastra maps. Quick routing; legacy `google-maps` name archived (see `_archive/2026-05-14`). NOT for: Mapbox-only, pure GIS

by amo-tech-aiGitHub

vectorize

Manage codebase and database vectorization for semantic search. Use when initializing, refreshing, or querying the vector index. Triggers on: vectorize init, vectorize refresh, vectorize search, seman

by mdmagnuson-creatorGitHub

multi-agent-causal-reasoning-system

Build multi-agent systems that discover causal rules from event sequences using specialized agents (causal discovery, contextual information, orchestrator). Use when asked to: 'find causal patterns in

by ndpvt-webGitHub

cross-lingual-stability-judges-under

Detect and fix cross-lingual evaluation instabilities in LLM-as-a-judge pipelines. Use when: 'audit my multilingual eval pipeline', 'check if my LLM judge is stable across languages', 'set up cross-li

by ndpvt-webGitHub

outlines

Outlines: structured JSON/regex/Pydantic LLM generation.

by openamerGitHub

backend-patterns

Backend architecture patterns, API design, database optimization, and server-side best practices for Node.js, Express, and Next.js API routes.

by rinchsanGitHub

checkpoint

Persist the current session into `.claude/tmp/checkpoint.md` as a VERY detailed handoff document, then return a copy-paste activation prompt the user can use to resume the work in a fresh session. Pre

by pontschoGitHub

celery-expert

Expert Celery distributed task queue engineer specializing in async task processing, workflow orchestration, broker configuration (Redis/RabbitMQ), Celery Beat scheduling, and production monitoring. D

by aibot88GitHub

1
5848
5849
5850
5851
5852
6277