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

Design System Français (DSFR)

Documentation et accessibilité concernant le Design System Français (DSFR), un ensemble de composants et de bonnes pratiques pour créer des interfaces utilisateur conformes aux standards du gouverneme

by majiayu000GitHub

Not rated yet

Free

Shodan Reconnaissance and Pentesting

This skill should be used when the user asks to "search for exposed devices on the internet," "perform Shodan reconnaissance," "find vulnerable services using Shodan," "scan IP ranges with Shodan," or

by xfstudioGitHub

security-review

Provides security review guidance including OWASP Top 10, threat modeling, secure coding practices, and security checklists. Triggers on security, threat model, vulnerability, OWASP, authentication, a

by doancanGitHub

mobile-development-skill

Master iOS, Android, React Native, and Flutter development. Build native and cross-platform mobile apps with modern frameworks, handle platform-specific features, optimize performance, and deploy to a

by majiayu000GitHub

Security Scanning Tools

This skill should be used when the user asks to "perform vulnerability scanning", "scan networks for open ports", "assess web application security", "scan wireless networks", "detect malware", "check

by majiayu000GitHub

nav-start

Load SuperNavigator (OS + App layers) documentation when starting development session. Loads Navigator context + injects using-superpowers App layer. Use when user mentions starting work, beginning se

by majiayu000GitHub

technical-lead

Use for delivery leadership on this Homebridge SoundTouch plugin — NOT for writing code. Trigger when the user wants to: prioritize or sequence the plans backlog, figure out what's next after merging

by forktruckaGitHub

jetson-validate-image

Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.

by waggle-sensorGitHub

@3073/virtual-trading

Degenerate Claw is a **perpetuals trading competition with public forums** for ACP agents. Trade perps directly on Hyperliquid via your own API wallet, compete on a seasonal leaderboard, and build rep

by Starchild-ai-agentGitHub

playwright-java

Scaffold, write, debug, and enhance enterprise-grade Playwright E2E tests in Java using Page Object Model, JUnit 5, Allure reporting, and parallel execution.

by JantonioFCGitHub

lint-remediation

Use when Ruff, mypy, pyright, pylint, Bandit, SQLFluff, Tombi, or another managed checker reports findings that need structural code-quality remediation rather than suppressions or config weakening.

by paudleyGitHub

claude-md

Expert skill for creating, reading, auditing, planning, and optimizing CLAUDE.md files — the persistent memory and context layer for Claude agents in Claude Code projects and Claude.ai Projects. Use t

by thisisgaganbirruGitHub

knowledge-distillation

Compress large language models using knowledge distillation from teacher to student models. Use when deploying smaller models with retained performance, transferring GPT-4 capabilities to open-source

by majiayu000GitHub

add-new-cli-command

Add or change a command in Contract Kit's `conkit` Rust CLI. Use for clap grammar in `conkit/args.rs`, native async dispatch through `CommandContext` and `AppCommand`, CLI-owned filesystem and persist

by genapticGitHub

infostyle-editor

Копирайтер и редактор в информационном стиле по принципам «Пиши, сокращай»: полезное действие текста, факты вместо оценок, глаголы вместо канцеляризмов, короткие предложения, честность без штампов. Ис

by BelkovGBGitHub

langgraph

Expert in LangGraph - the production-grade framework for building stateful, multi-actor AI applications. Covers graph construction, state management, cycles and branches, persistence with checkpointer

by sitaursGitHub

arize-dataset

INVOKE THIS SKILL when creating, managing, or querying Arize datasets and examples. Covers dataset CRUD, appending examples, exporting data, and file-based dataset creation using the ax CLI.

by jcasnellie69GitHub

table-extractor

Extract tables from PDFs with high accuracy using camelot - handles complex table structures

by kbarbel640-delGitHub

hic-compartments-calling

This skill performs PCA-based A/B compartments calling on Hi-C .mcool datasets using pre-defined MCP tools from the cooler-tools, cooltools-tools, and plot-hic-tools servers.

by majiayu000GitHub

table-extractor

Extract tables from PDFs with high accuracy using camelot - handles complex table structures

by johnalbertini14-glitchGitHub

table-extractor

Extract tables from PDFs with high accuracy using camelot - handles complex table structures

by TrompetillaGitHub

box-automation

Automate Box operations including file upload/download, content search, folder management, collaboration, metadata queries, and sign requests through Composio's Box toolkit.

by yashas-30GitHub

agent-browser

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, tes

by whywaitaGitHub

sprint-review

Sprint quality review. Runs type-check, lint, test suite, build validation. Spawns reviewer agents for code quality and security. Auto-fixes failures. Use when: "review sprint", "check quality", "run

by lasswelltGitHub

1
5722
5723
5724
5725
5726
6380