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 1.2.0enterprise edition

Product

Models
Marketplace
Playground
Pricing

Developers

Documentation
REST API
MCP server
Self-hosting

Company

Blog
Changelog
Support
PyPI

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.

141.1K SkillsPublish yours

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

Agents4450 Personas3429 Prompts9946 Templates31 Tools30678 Models

141109 results

444

fp-refactor-v2

Refactoring Imperative Code to fp-ts workflow skill. Use this skill when the user needs Comprehensive guide for refactoring imperative TypeScript code to fp-ts functional patterns and the operator sho

by diegosouzapwGitHub

Not rated yet

Free

chatpack

Integrate Chatpack (@chatpack/core) - an open-source TypeScript chat backend (1:1 and group conversations) with REST + real-time SSE - into any app. Use when adding chat, messaging, DMs, group chats,

by chddanielGitHub

loops

AI驱动的自动化循环集合。覆盖软件开发、数据科学、内容创作、产品运营、学习管理等领域。当用户需要自动化工作流、修复问题、生成内容、分析数据或执行质量检查时使用。

by jwangkunGitHub

x-reach

Check whether a post will get seen, and what would make it get seen more. Use for a handle reach scan, a pasted draft, why a post died, and shadowban differential diagnosis against published x-algorit

by TheMattBermanGitHub

data-chatbots

Design and implement AI copilots that analyze structured data and propose mutations for human approval (draft → apply), not direct writes. Covers prompting, multistep compound requests (remove + add i

by swyxioGitHub

magpie-engineer

Comprehensive guide for writing Magpie (.mp) programs, debugging compiler errors, and using the Magpie CLI. Designed for agents who have never seen Magpie before.

by magpie-langGitHub

office-hours

YC Office Hours — two modes. Startup mode: six forcing questions that expose demand reality, status quo, desperate specificity, narrowest wedge, observation, and future-fit. Builder mode: design think

by mr-daedaliumGitHub

t-invest

Access to the user's Т-Инвестиции / Tinkoff (T-Invest) brokerage account via the T-Invest API — portfolio, positions, cash, quotes and prices, operations, dividends, commissions, yield/returns, bonds,

by nyxandroGitHub

plan

Auto-review pipeline — reads the full CEO, design, and eng review skills from disk and runs them sequentially with auto-decisions using 6 decision principles. Surfaces taste decisions (close approache

by no-sessionGitHub

reflect

Weekly engineering retrospective. Analyzes commit history, work patterns, and code quality metrics with persistent history and trend tracking. Solo-aware: focuses on your shipping velocity, consistenc

by no-sessionGitHub

design-review

Designer's eye QA: finds visual inconsistency, spacing issues, hierarchy problems, AI slop patterns, and slow interactions — then fixes them. Iteratively fixes issues in source code, committing each f

by mr-daedaliumGitHub

java-doctor

Comprehensive Java code health analyzer. 0-100 score with diagnostics. Progressive loading - detects project tech (Spring, gRPC, JPA) and loads relevant rules. Version-aware for Java 8-25 & Spring Boo

by ajaywadharaGitHub

auto-mcm

AutoMCM-Pro industrial-grade math modeling agent. Supports AP (AI-led) and Manual (human-spec-led) dual modes with mandatory GitOps checkpoints, forced self-verification of all solver code before LaTe

by RealSeaberryGitHub

group-sequential-design

Design group sequential clinical trials for survival endpoints (OS, PFS, DFS) with interim analyses, spending functions, boundaries, multiplicity, and event/enrollment prediction. Triggers on: Phase 3

by RConsortiumGitHub

proofread

Proofread an academic paper against a structured checklist covering abbreviations, math notation, introduction structure, grammar and style, figures and tables, and statistical relevance. Two modes —

by JakobThummGitHub

amp

Tari Ootle development instructions for Amp

by tari-projectGitHub

sk-positioning

Phase 4: Market positioning strategy using April Dunford's framework, enriched with JTBD discovery, Moore positioning statement, and Neumeier's Onliness Test. Produces a complete positioning document,

by mohamedameen-ioGitHub

plan-eng-review

Eng manager-mode plan review. Lock in the execution plan — architecture, data flow, diagrams, edge cases, test coverage, performance. Walks through issues interactively with opinionated recommendation

by mr-daedaliumGitHub

powerpoint-slides

Create visually rich PowerPoint (.pptx) presentations from academic papers, research notes, or any content the user wants in slide format. Uses PptxGenJS + LaTeX formula rendering. Always use this ski

review

Code quality review — patterns, security, performance, correctness. Finds bugs, suggests improvements, triggers fix for issues found. Escalates to opus for security-critical code.

by Rune-kitGitHub

07-outline

中文项目申请书写作流程第 07 阶段工具：申请书内容架构与体量规划。读取申请书模板、06-helm 的整体方案蓝图、05-synthesis 的综合理解与证据账本，生成可扩展的申请书大纲、章节体量预算、writing units、证据分配表和逐单元写作状态，为 08-section-write 提供可直接执行的写作任务。当用户输入 /grant-master:07-outline，或在 g

by Lin-zhijieGitHub

aider

Tari Ootle development instructions for Aider

by tari-projectGitHub

cursor

Tari Ootle development instructions for Cursor

by tari-projectGitHub

story-review

多视角对抗式审查。full/lean 模式在已部署 reviewer agents 时并行 spawn；缺失/异常 agents 或 spawn 失败时自动降级 solo，参考文件不可读时使用内置 rubric fallback。触发方式：/story-review、/审查、「审查一下」「帮我审一下」。

by qin1473692580-uxGitHub

1
5802
5803
5804
5805
5806
5880