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-2.0v1.5.0enterprise 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

react

React 19 performance optimization guidelines for concurrent rendering, Server Components, actions, hooks, and memoization (formerly react-19). This skill should be used when writing React 19 component

by haotoolGitHub

Not rated yet

Free

token-optimizer

Reduces LLM token consumption by 60-90% on common commands. Filters and compresses command outputs before they reach LLM context. Use when executing shell commands, reading files, running tests, or an

by wcz234GitHub

scientific-critical-thinking

Evaluate scientific claims and evidence quality. Use for assessing experimental design validity, identifying biases and confounders, applying evidence grading frameworks (GRADE, Cochrane Risk of Bias)

by OleaflyGitHub

bauplan-data-pipelines

Creates bauplan data pipeline projects with SQL and Python models. Use when starting a new pipeline, defining DAG transformations, writing models, or setting up bauplan project structure from scratch.

by majiayu000GitHub

clui-cc-claude-overlay

Command Line User Interface for Claude Code — a floating macOS desktop overlay with multi-tab sessions, permission approval UI, voice input, and skills marketplace.

by AradotsoGitHub

changelog-newsletter

Transform technical changelog entries into user-friendly newsletter content for email, blog posts, and release notes. Use when converting CHANGELOG.md files, git commit logs, or release notes into cus

by majiayu000GitHub

pptx-posters

Create and audit editable scientific posters in macro-free PowerPoint (.pptx) from author-approved local content and assets. Use when the requested deliverable is a PowerPoint research/conference post

by gabrielmoreiraGitHub

delivery

Use when explicitly invoked to conduct a large outcome decomposed into changes: decompose a requirements document if needed, then dispatch every ready change to a sw-change-owner in parallel, one work

by ribeirogabGitHub

ppt-workbench-studio

Use when working inside the ppt-workbench-studio repo, or when the user asks to use their Studio/plugin workflow to generate a deck in the browser editor. Default to reading source links first, then u

by Mijiang111GitHub

e2e-prove

Run and prove x0x end-to-end tests across VPS, LAN, and local. Uses haiku to run tests, sonnet to evaluate results, opus for code fixes. Generates proof reports with round-trip verification.

by saorsa-labsGitHub

golang-safety

Defensive Golang coding to prevent panics, silent data corruption, and subtle runtime bugs. Use when encountering nil panics, append aliasing, map concurrent access, float comparison pitfalls, or zero

competitor-intel

Researches and analyzes competitors for small businesses. Builds competitive intelligence reports with pricing, positioning, marketing strategies, strengths/weaknesses, and actionable differentiation

by Amazon-QuickGitHub

ui5-best-practices-smart-controls

UI5 smart controls (sap.ui.comp) best practices for OData V2 annotation-driven controls. Use when creating/troubleshooting SmartField, SmartForm, SmartFilterBar, SmartChart, SmartLink, SmartMultiInput

design-taste

Design direction, judgment calls, and anti-AI-slop review for crypto UIs. Use when the user says "this looks generic", "this looks AI-generated", "anti-slop", "design judgment", "premium feel", "desig

by stantheman0128GitHub

uniapp-subpackage-node-modules

仅用于诊断 uni-app 小程序分包场景下，分包引用的 node_modules 依赖为什么仍被打进主包 common/vendor.js，而没有进入分包 vendor.js。适用于检查 uni-app 或 HBuilderX 版本、manifest.json 的分包优化开关、pages.json 的 subPackages 配置、分包根目录 package.json、以及主包与分包对 npm

by uni-toolkitGitHub

Security Scanning Security Hardening

Coordinate multi-layer security scanning and hardening across application, infrastructure, and compliance controls.

by mayurrathiGitHub

redis-queue

How to use @owlmeans/redis-queue — the BullMQ-over-Redis driver for @owlmeans/queue, appendRedisQueue wiring, its key prefixing and connection rules, worker defaults and dispatch, what a broker cannot

by owlmeansGitHub

attribution-reconciler

Use when platform-reported conversions disagree with GA4/ecommerce, when you suspect Meta and Google are double-counting the same sales, or for a standing (monthly) reconciliation workbook that de-dup

by majiayu000GitHub

professional-proofreader

Professional Proofreader workflow skill. Use this skill when the user needs > and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off

by diegosouzapwGitHub

tdd-execution

This skill should be used when executing plan tasks autonomously, implementing features using TDD, running the red-green-refactor cycle, handling code review loops, or dealing with blocked tasks. Prov

by majiayu000GitHub

sdlc-develop

Orchestrates 6-phase SDLC pipeline (discovery, requirements, architecture, workstreams, implementation, summary) for guided feature development. Use when user runs /core:develop command, requests spec

by majiayu000GitHub

Frameworks Integration

Use when asking about "Hono", "itty-router", "routing frameworks", "middleware", "API framework", "web framework for Workers", "request routing", "Express-like", or choosing between web frameworks for

by majiayu000GitHub

customer-intel

Synthesize recent customer feedback and pain points

by davekilleenGitHub

ln-741-linter-configurator

Configures ESLint, Prettier, Ruff, mypy, and .NET analyzers. Use when setting up linting and formatting for a project.

by majiayu000GitHub

1
5518
5519
5520
5521
5522
6380