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-2.0v1.4.0enterprise edition

The daily newsletter

Models, LLMs and agents, one email a day. Confirm by email; leave with one click.

Email address

Product

Models
Marketplace
Playground
Browser extension
Desktop app
Pricing

Developers

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

Company

Blog
Newsletter
Changelog
Support
Status
Security
PyPI
npm

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.

153.1K SkillsPublish yours

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

Agents6549 Personas6713 Prompts18720 Templates31 Tools31899 Models

153105 results

448

dask

Parallel/distributed computing. Scale pandas/NumPy beyond memory, parallel DataFrames/Arrays, multi-file processing, task graphs, for larger-than-RAM datasets and parallel workflows.

by plurigridGitHub

Not rated yet

Free

sympy

Use this skill when working with symbolic mathematics in Python. This skill should be used for symbolic computation tasks including solving equations algebraically, performing calculus operations (der

by agent-skills-hubGitHub

post-optimizer

将平实、准确的内容改写成有网感、能引发互动的社交媒体文案。适用于 Twitter/X、小红书、即刻等平台的短文案优化。当用户希望优化推文、笔记、短帖子，或者想让功能描述/产品更新变得更抓人眼球时，使用此 skill。也适用于用户给出一个主题、一段草稿、或一组功能点，希望生成一条有活人感的推文。不适用于长文章、博客、正式文档。

by okooo5kmGitHub

pydicom

Python library for working with DICOM (Digital Imaging and Communications in Medicine) files. Use this skill when reading, writing, or modifying medical imaging data in DICOM format, extracting pixel

by agent-skills-hubGitHub

herdr

Control herdr from inside it. Manage workspaces and tabs, split panes, run commands, read output, and wait for state changes — all via CLI commands that talk to the running herdr instance over a local

by ninehillsGitHub

design-guide-mlp

MLP Finanzberatung SE Corporate Design System combined with modern UI principles. Use when creating any UI, presentations, documents, or materials for MLP financial advisors. Ensures brand-compliant c

by majiayu000GitHub

sympy

Use this skill when working with symbolic mathematics in Python. This skill should be used for symbolic computation tasks including solving equations algebraically, performing calculus operations (der

by Zaoqu-LiuGitHub

golang-patterns

견고하고 효율적이며 유지보수 가능한 Go 애플리케이션 구축을 위한 관용적 Go 패턴, 모범 사례 및 규칙.

by tpavanipradeepGitHub

法律溯因推理

法律溯因推理（Abductive Reasoning）技能，用于在证据不完整、事实模糊时生成并评估最合理的解释性假设。结合米尔五法（求同、求异、求同求异、剩余、共变）进行结构化因果推断。当用户需要"提出可能的法律解释"、"生成辩护/起诉假设"、"评估证据的多种解读"或"基于不完整事实推断最佳解释"时触发。适用于案例分析、证据评估、规则适用争议、因果关系推断等场景。

by sunyifeisb-artGitHub

laozi-perspective

老子的思维框架与哲学体系。基于《道德经》81章一手原文（王弼通行本为主，异文处标注帛书/楚简）深度提炼，6个核心心智模型（反者道之动、有无相生、柔弱胜刚强、道法自然、损之又损、知止知足）、8条决策启发式、40余条可溯源原文。适用于形势与周期判断、策略选择、风险管理、修身与欲望管理。触发词：老子、道德经、道家、无为、道法自然、柔弱胜刚强、上善若水、反者道之动、知足不辱、不争、无为而治、物极必反。

by Luyu2026GitHub

pydicom

Python library for working with DICOM (Digital Imaging and Communications in Medicine) files. Use this skill when reading, writing, or modifying medical imaging data in DICOM format, extracting pixel

by Zaoqu-LiuGitHub

formal-review

This skill should be used when the user asks to "formal review", "formal lens review", or invokes /formal-review. A fixed-lens PR review for this repository's formally-structured protocol changes: it

by jongwonyGitHub

add-telegram-swarm

Add Agent Swarm (Teams) support to Telegram. Each subagent gets its own bot identity in the group. Requires Telegram channel to be set up first (use /add-telegram). Triggers on "agent swarm", "agent t

by sliamh11GitHub

resend

Use when working with the Resend email API — sending transactional emails (single or batch), receiving inbound emails via webhooks, managing email templates, tracking delivery events, managing domains

by motormetricsGitHub

alterlab-hypogenic

Runs automated LLM-driven hypothesis generation and testing on tabular datasets with HypoGeniC, combining literature insights with data-driven testing. Use when systematically exploring hypotheses abo

by AlterLab-IEUGitHub

prd-generator

协助产品经理生成专业的产品需求文档(PRD)，通过交互式问答收集信息，进行竞品研究，迭代优化各模块内容，最终输出结构化的PRD文档。

by KuhakucaiGitHub

backend-go

Enforces Go backend best practices following clean architecture, dependency injection, and test-driven development. Automatically applied for Go backend implementation, API development, and microservi

by majiayu000GitHub

flux

"Configures flux in cloud-native engineering - gitops for kubernetes for cloud-native deployment and infrastructure management."

by paulpasGitHub

dask

Parallel/distributed computing. Scale pandas/NumPy beyond memory, parallel DataFrames/Arrays, multi-file processing, task graphs, for larger-than-RAM datasets and parallel workflows.

by sankalpsharmaaGitHub

launch-campaign

Orchestrate the full multi-channel launch of an approved campaign plan — pre-launch checklist, asset readiness gate, channel-by-channel activation, CRM campaign record creation, kickoff comms, day-1 m

by majiayu000GitHub

debug-quantized-kernel-accuracy

2. **Isolate the quantization step responsible.** The quantization pipeline is: ``` fp32 input → quantize → int8 input int8 GEMM (or other op) with int32 accumulation int32 accumulation → dequantize →

by tensormuxGitHub

sp

sp.h - 单头文件C标准库替代方案。本指南提供了使用sp.h编写现代C代码的最佳实践。即使你是一个AI助手，遵循这些规则也能写出高质量的C代码。

by majiayu000GitHub

message-system-architect

Use when the user asks to "author our durable brand message hierarchy", "build the brand message house that seeds the canon", or "define the main narrative, three pillars, and tagline for the whole br

by majiayu000GitHub

total-recall

The only memory skill that watches on its own. No database. No vectors. No manual saves. Just an LLM observer that compresses your conversations into prioritised notes, consolidates when they grow, an

by monasproxGitHub

1
5734
5735
5736
5737
5738
6380