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-2.0v1.7.0enterprise edition

The daily newsletter

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

Email address

Product

Services
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
Talk to sales
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.

161.2K SkillsPublish yours

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

Agents6760 Personas6743 Prompts19362 Templates32 Tools33107 Models

161196 results

453

customs-trade-compliance

Codified expertise for customs documentation, tariff classification, duty optimization, restricted party screening, and regulatory compliance across multiple jurisdictions. Informed by trade complianc

by GalihAdiPrayogaGitHub

Not rated yet

Free

write-workflows

Author Mendix workflows in MDL — user tasks, decisions, parallel splits, jumps, waits and boundary events, with CREATE, ALTER and DROP. Use when building a business process with human steps, timers or

by mendixlabsGitHub

prisma-composer-core-concepts

Use when deploying or managing an app that uses Prisma Composer (`@prisma/composer`): wiring its services and Modules, running it locally, testing composed services, or standing up / tearing down an e

by harshcsrivastavaGitHub

turborepo

Turborepo monorepo build system guidance. Triggers on: turbo.json, task pipelines, dependsOn, caching, remote cache, the "turbo" CLI, --filter, --affected, CI optimization, environment variables, inte

by itsramaaGitHub

autoreview

Pre-commit/ship code review: Codex default; optional Claude or Pi.

by BramVRGitHub

yomihon

How to write Markdown that yomihon reads as a course, a map and a searchable note: frontmatter, filenames, the study-path marker, the dialect.

by Koopa0GitHub

writing-skills

Use when creating new skills, editing existing skills, or verifying skills work before deployment

by gustavo-ooGitHub

mc-style-latin

★ **"拉丁"不是一个风格，是三个互不通婚的家族。** 《The Drummer's Bible》在巴西一章开头就把话说死了：**不要把巴西与 Afro-Cuban 混为一谈，两者各有各的特征与具体节奏，一首歌被标成 "Latin" 时，先得知道该打哪一类节奏型**（p0059）。本 skill 做的就是这个分家的决定，具体鼓型不在这里。

by jtydhr88GitHub

yb-k8s-operator

Use when provisioning, managing, or troubleshooting YugabyteDB universes on Kubernetes via the YugabyteDB Kubernetes Operator and YugabyteDB Anywhere CRDs (YBUniverse, YBProvider, Release, Backup, Sto

by yugabyteGitHub

editorial-review

Apply the final editorial and factual-quality gate to a prepared Red Horizon article package.

by janpolacekGitHub

skill-creator

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill

by WifabricGitHub

boss-finalize

End-of-session workflow ensuring all work is committed and pushed. Use when ending a work session or when asked to "land the plane".

by bossanova-devGitHub

comprehensive-thinking

Use when Codex must make a high-quality judgment on any complex problem, not only technical problems. Trigger when a question has high complexity, uncertainty, cost of being wrong, long-term impact, v

by syzkillallGitHub

emil-design-eng

This skill encodes Emil Kowalski's philosophy on UI polish, component design, animation decisions, and the invisible details that make software feel great.

by beelabstudioGitHub

ppt-deck-pro-max

PPT Deck Pro Max builds product-grade PPT/HTML decks from briefs, strategy docs, product narratives, or solution materials. It manages brief, narrative, visual system, image-led build, QA, and rollbac

by MainQuestAIGitHub

version-diff-review

Use this skill whenever you review a game version's change set — Excel config-table diffs, Git commit diffs, weekly version deltas — and need to judge release risk. It fixes the review protocol, the p

by huangsj47GitHub

problem-brief

Use when asked to build, publish, refresh or update an artefact (or brief, findings report, open-questions page, decisions page) that lists problems, issues, findings, review results or open questions

by zaytsevandGitHub

sexual-health-analyzer

Sexual Health Analyzer

by Krrish284GitHub

grok-playtest

Narration discipline, session continuity, and world-state verification for Grok Web playtesting

by myarichukGitHub

skill-creator

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill

by jnooreeGitHub

profiling

CPU profiling -- where the time went (perf) and what the machine did there (PAPI counters, per-thread CPI and imbalance).

build-and-dependencies

Maven and Gradle build configuration and dependency governance for Java 21+ Spring Boot projects. Use when changing build files, dependencies, plugins, versions, compiler settings, annotation processo

by mzivkovicdevGitHub

pack

Start a new project. Sets the user's role, calibrates help style, fires the beneficiary challenge, optionally runs the idea hunt for users without a concrete idea, and drafts the project map. The entr

lfg

Run the full autonomous shipping pipeline end-to-end, hands-off with no check-ins: plan, implement, review and fix, commit, push a branch, open a PR, and watch CI to green. Use only when the user expl

by Stab-Rabbit-codingGitHub

1
190
191
192
193
194
6717