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

arm-cortex-expert

Senior embedded software engineer specializing in firmware and driver development for ARM Cortex-M microcontrollers (Teensy, STM32, nRF52, SAMD).

by Krrish284GitHub

Not rated yet

Free

codex-delegator

Automatically delegate complex, logic-intensive tasks to OpenAI Codex CLI via `codex exec --full-auto`. Claude Code uses this skill to invoke Codex for complex backend logic, intricate algorithms, or

by eddiearcGitHub

extract-adrs

Drive a guided conversation that converts a stable design or spec document into multiple ADRs at `docs/adr/`, then either shrinks or deletes the source doc.

by dimagiGitHub

cometweb-context

Builds a fresh, provenance-aware context snapshot for CometWeb and its active projects before product, portfolio, strategy, GTM, pricing, outreach, meeting, content, or advisory work. Use when the req

by CometWeb-ioGitHub

sqg

Generate type-safe TypeScript, Java, or Python code from annotated SQL files using SQG (SQL Query Generator). Use whenever the user works with `.sql` files containing `-- QUERY`, `-- EXEC`, `-- MIGRAT

by sqg-devGitHub

clinical-trials-database

Query ClinicalTrials.gov via APIv2. Use when you want to search for trials by condition, drug, location, status, or phase; retrieve trial details by NCT ID; check eligibility/inclusion criteria; count

by fmenolGitHub

seo-backlinks

Backlink profile analysis: referring domains, anchor text distribution, toxic link detection, competitor gap analysis. Works with free APIs (Moz, Bing Webmaster, Common Crawl) and DataForSEO extension

by Cortex-AI-IDEGitHub

component-builder

Component builder for Sunrise. Creates reusable React components following shadcn/ui patterns: TypeScript interfaces, accessibility attributes, Tailwind CSS styling, Server Components by default (`'us

by human-centric-engineeringGitHub

any2card

将任意文本、网页或 URL 转成可直接发布的 HTML 信息卡片。适合把文章、线程、论文、观点、数据摘要做成适合微信、小红书、X 发布的图片卡。当用户提到“信息卡、卡片摘要、文章配图、内容提炼、社交分享图、把链接做成卡片、生成海报式摘要”时优先使用本技能。

by geekjourneyxGitHub

plantuml

Generate leftover PlantUML types Mermaid cannot do easily (Salt wireframes, use case, timing, ArchiMate, nwdiag, WBS) and convert them to PNG/SVG. Use when asked for a wireframe, PlantUML image export

by SpillwaveSolutionsGitHub

research-question-validator

Fast research question validity check using Consensus. Runs 4-5 targeted searches to assess whether a proposed research question is novel, saturated, or somewhere in between — with evidence. Returns a

by stephenturnerGitHub

performing-serverless-function-security-review

Performing security reviews of serverless functions across AWS Lambda, Azure Functions, and GCP Cloud Functions to identify overly permissive execution roles, insecure environment variables, injection

by baohonfGitHub

godot-scene-management

Expert blueprint for scene loading, transitions, async (background) loading, instance management, and caching. Covers fade transitions, loading screens, dynamic spawning, and scene persistence. Use wh

by xZeroWGitHub

mate-harness-hardening

Audit and sharpen the agentic harness itself — the loaded rules, skills, agents, gates, and the doctrine graph. Finds drift, collisions, dead surfaces, missing gates, and over-orchestration; proposes

by ydnikolaevGitHub

niubash-native-codex

Native Niubash execution guidance for Codex running as a first-class Niubash citizen in the unixwin/niubash environment. Use when Codex handles Niubash shell tasks, .niubashrc edits, oh-my-niu bundles

by unixwinGitHub

codex

Get code reviews, plan evaluations, and second opinions using OpenAI Codex CLI (GPT-5.5). Use for reviewing code changes, evaluating implementation plans, getting alternative perspectives, or validati

by letitbkGitHub

requesting-code-review

Use when completing tasks, implementing major features, or before merging. Routes to the right review agent(s) based on context. For full suite use /review all. For targeted review use /review <type>.

by CagesThrottleUsGitHub

annual-report-red-flag-auditor

把上市公司年报转成可追溯的财务质量评分、账户级红旗地图和核查计划。Use for annual-report red flags, earnings-management or fraud-risk signals, asset/profit/cash-flow quality, parent-versus-consolidated differences, related-party risk,

by noahnan-maxGitHub

study

Interactive learning tutor with spaced repetition, research helpers, and restart-safe study workspaces. Use when the user wants to learn something new: teach me, I want to study, help me learn, study

by mordor-forgeGitHub

penpot-component-factory

Build and maintain Penpot components with COMPLETE variant matrices — sizes, hierarchies, and all interactive states (default/hover/pressed/focus/disabled) — fully tokenized and correctly named. Use t

by GolinSkyGitHub

stakeholder-summary

Translates a contract review into a summary the business stakeholder will actually read. Not a legal memo — a two-minute answer to "can I sign this and what do I need to know." Use when user says "sum

by hermes-max100GitHub

skill-systematic-debugging

Use when diagnosing bugs, failures, or unexpected behavior before proposing fixes.

by longdang193GitHub

agentic-payment-protocol-convergence-2026

Navigate the converging agentic payment protocol ecosystem — ACP, UCP, AP2, Verifiable Intent, Visa TAP, Mastercard Agent Pay, Web Bot Auth, and x402 — that defines how AI agents transact when no huma

by hamishfromatechGitHub

ait-crafting

Turn a settled feature discussion or plan document into consultant-ready ait issues — an initiative/epic vision document plus implementation specs a fresh agent could pick up cold, tomorrow. Use towar

by ohnotnowGitHub

1
184
185
186
187
188
6717