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

Agents6470 Personas6713 Prompts18605 Templates31 Tools31899 Models

153105 results

448

zomboid-modding

Project Zomboid mod creation and maintenance workflow for local B42.20 mods. Use when Codex is creating, forking, fixing, packaging, installing, linking, or debugging a Project Zomboid mod; working in

by mrStorrsGitHub

Not rated yet

Free

dependabot-alert-issue

Dependabot alerts または外部 audit findings（例 pnpm audit の正規化 JSON）を確認し、解消 Issue を `gh` で作成するスキル。対象を「すぐ着手できるか」で分類し、着手可能なものは severity 毎、ブロック中のものは脆弱パッケージ＋解決バージョン毎にまとめる。既存 Issue/PR はスキップし、特定 alert の ignore/di

by shoji9x9GitHub

feature-investment-advisor

Evaluate feature investments using revenue impact, cost structure, ROI, and strategy. Use when deciding whether a feature deserves investment.

by gabrielmoreiraGitHub

transformers-js

Use Transformers.js to run state-of-the-art machine learning models directly in JavaScript/TypeScript. Supports NLP (text classification, translation, summarization), computer vision (image classifica

by konstantinosmpourosGitHub

marketing-psychology

When the user wants to apply psychological principles, mental models, or behavioral science to marketing. Also use when the user mentions 'psychology,' 'mental models,' 'cognitive bias,' 'persuasion,'

by MarcoBolsaGitHub

eventmodeling-integrating-legacy-systems

Apply Event Modeling to legacy systems using side-car pattern. Freeze old system, extract events, build new features without rewriting. Use when modernizing legacy applications. Do not use for: greenf

by TrogonStackGitHub

ai-frontend-mastery

Premium non-generic AI frontend design playbook.

by TylerSimons1127GitHub

higgsfield-generate

Generate images/videos via Higgsfield AI. Default: GPT Image 2 for images/design/text, Seedance 2.0 for video, Nano Banana 2/Pro for character/reference image work, Marketing Studio for ads with avata

growth-model

Reforge-style growth loop design — acquisition, retention, and monetization loops

by GeorgeQLeGitHub

inventory-demand-planning

Codified expertise for demand forecasting, safety stock optimization, replenishment planning, and promotional lift estimation at multi-location retailers. Informed by demand planners with 15+ years ex

by ziyabicilecommerce-hubGitHub

ubuntu-collective-knowledge-task-designer

Design learning tasks built on Ubuntu philosophy emphasising collective knowledge-building and mutual responsibility. Use when fostering collaboration that values community over individual competition

by Nicooo-WangGitHub

rar-cowork-cookbook-teams-update-lease-assets

Drafts a Teams channel post on lease assets status with an interactive Adaptive Card for quick triage.

by kody-wGitHub

carrier-relationship-management

您是一名拥有15年以上经验的资深运输经理，管理着从40家到200多家活跃承运商的组合，涵盖整车运输、零担运输、联运和经纪业务。您负责全生命周期管理：寻找新承运商、协商费率、执行RFP、建立路由指南、通过记分卡跟踪绩效、管理合同续签以及做出运力分配决策。您使用的系统包括TMS（运输管理系统）、费率管理平台、承运商入驻门户、用于市场情报的DAT/Greenscreens，以及用于合规性的FMCSA S

by marlo9981GitHub

using-ui-bundle-salesforce-data

MUST activate when the project contains a uiBundles/*/src/ directory and the task involves ANY Salesforce record operation — reading, creating, updating, or deleting. Use this skill when building form

by dmckeeSFGitHub

github-workflow-automation

Patterns for automating GitHub workflows with AI assistance, inspired by [Gemini CLI](https://github.com/google-gemini/gemini-cli) and modern DevOps practices.

by foolhardy45GitHub

top-web-vulnerabilities

Provide a comprehensive, structured reference for the 100 most critical web application vulnerabilities organized by category. This skill enables systematic vulnerability identification, impact assess

by Pranjal240GitHub

inventory-demand-planning

Codified expertise for demand forecasting, safety stock optimization, replenishment planning, and promotional lift estimation at multi-location retailers. Informed by demand planners with 15+ years ex

by Long-NguyenHaiGitHub

design-taste-frontend-v1

The original v1 taste-skill, preserved for projects depending on its exact behavior. The current default is `design-taste-frontend` (v2 experimental), which is a substantial rewrite. Use this v1 insta

by shikhar13012001GitHub

mcp-java-dev-tools-regression-suite

Run MCP-first HTTP regression suites (endpoint, service, or API scope) with optional strict probe-hit verification, bounded Watchers for downstream completion checks, and external verification for dow

by nimbly-devGitHub

autoresearch

Orchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inner loop runs rapid experiment iterations with clear optimization targets. The outer loop synthesizes resul

by nota-americaGitHub

skill-finder

Navigation aid for the processkit skill catalog — maps natural-language cues and task types to the right skill. Read this when you are unsure which skill applies to the current task, when the user nam

by projectious-workGitHub

glossary-builder

Expert glossary builder who creates comprehensive definitions and descriptions for all terms in a taxonomy. Your goal is to produce clear, accurate, and contextually appropriate definitions that help

by HoogkamerGitHub

finalize

Final gate for a feature — re-run `verify` for any tasks that deferred behavior checks, then run lint/typecheck/tests/check:docs; fix everything they expose; confirm acceptance criteria; open the pull

by stoodderGitHub

run-harness-task

Use when executing a rigor:full task spec or a chosen full workflow through the locked verification pipeline. Use when a task spec is filled and ready, or when resuming a partially completed locked ru

by MadhavMareddyGitHub

1
6112
6113
6114
6115
6116
6380