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-2.0SDK 1.2.0enterprise edition

Product

Models
Marketplace
Playground
Pricing

Developers

Documentation
REST API
MCP server
Self-hosting

Company

Blog
Changelog
Support
PyPI

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.

141.6K SkillsPublish yours

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

Agents4450 Personas3429 Prompts9946 Templates31 Tools31217 Models

141624 results

446

thesys-generative-ui

Production-ready skill for integrating TheSys C1 Generative UI API into React applications. This skill should be used when building AI-powered interfaces that stream interactive components (forms, cha

by majiayu000GitHub

Not rated yet

Free

specificationbyexample

OpenRequirements.AI Specification by Example (SBE) skill using 7 specialized AI analyst agents based on the key process patterns from Specification by Example methodology. Transforms DeFOSPAM requirem

by AgenticTestingGitHub

gendoc-auto

任意輸入→IDEA.md+BRD→移交 gendoc-flow — 支援 idea/圖片/文件/URL/codebase/git 輸入，素材保存至 docs/req/（唯讀原則），生成 IDEA.md + BRD，再由 gendoc-flow 接手純文件生成流水線

by ibalasiteGitHub

browse

Fast headless browser for QA testing and site dogfooding. (gstack)

by adobetoby-makerGitHub

td-ralph-loop

Set up and run autonomous overnight coding loops that process td epic tasks one at a time. Includes the loop runner, Rich TUI cockpit dashboard, and prompt template. Use when automating multi-day feat

by marcusGitHub

dcf-model

Build discounted cash flow valuation workbooks in Excel.

by gabrielmoreiraGitHub

tmux-pair-orchestration

Use when the user wants to run, monitor, or recover a tmux-pair solo coding workflow through `/run` or `/solo`: one agent in a fresh git worktree, gated recon, plan checks, implementation, final verif

by derveloperGitHub

dcf-model

Build institutional-quality DCF valuation models in Excel — revenue projections, FCF build, WACC, terminal value, Bear/Base/Bull scenarios, 5x5 sensitivity tables. Pairs with excel-author. Use for int

by wishmaster108GitHub

qa-only

Report-only QA testing. Systematically tests a web application and produces a structured report with health score, screenshots, and repro steps — but never fixes anything. Use when asked to "just repo

by mostafasudoGitHub

scientific-slides

Build slide decks and presentations for research talks. Use this for making PowerPoint slides, conference presentations, seminar talks, research presentations, thesis defense slides, or any scientific

by Yezez9GitHub

qa

Systematically QA test a web application and fix bugs found. Runs QA testing, then iteratively fixes bugs in source code, committing each fix atomically and re-verifying. Use when asked to "qa", "QA",

by zz8011GitHub

pair-agent

Pair a remote AI agent with your browser. One command generates a setup key and prints instructions the other agent can follow to connect. Works with OpenClaw, Hermes, Codex, Cursor, or any agent that

by huyonghui666GitHub

psychologist

Provides scientifically grounded psychological insights and evidence-based coping strategies using named therapeutic frameworks (CBT, DBT, ACT), with a mandatory Validation-Analysis-Strategy-Action pr

by princemanjeeGitHub

orchestrate

Conduct a ticket end-to-end through the seven-phase lifecycle — capture original ticket, investigate, report, probe and spec, prep for implementation, implement, manual review — with full-rigor artifa

by SirGuntherGitHub

graphify

any input (code, docs, papers, images, videos) to knowledge graph. Use when user asks any question about a codebase, documents, or project content - especially if graphify-out/ exists, treat the quest

by MYounesDevGitHub

officecli-financial-model

Use this skill when the user wants to build a financial model — 3-statement model, DCF valuation, LBO, SaaS unit economics, sensitivity / scenario analysis, debt schedule, or fundraising projections —

by BaranziniLabGitHub

officecli-pptx

Use this skill any time a .pptx file is involved -- as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx f

by IceHeartGitHGitHub

gtm-engineering

When the user wants to build GTM automation with code, design workflow architectures, use AI agents for GTM tasks, or implement the 'architecture over tools' principle. Also use when the user mentions

by mattonwebGitHub

latex-posters

Create professional research posters in LaTeX using beamerposter, tikzposter,

by loganylchenGitHub

write-ggc

Manage the Glossary, Guidance, and Corrections (GGC) pipeline — from correction detection through glossary promotion, plus direct glossary management.

by DektoraGitHub

einja-task-exec

タスク実行 Skill

by einja-incGitHub

ce-compound-refresh

Refresh stale learning and pattern docs under docs/solutions/ by reviewing them against the current codebase, then updating, consolidating, or deleting drifted ones. Use when the user asks to "refresh

by qm-pallasigui-archGitHub

tensorleap-integration-creation

Use when writing or fixing a Tensorleap integration in the decorator style — leap_integration.py / leap.yaml, @tensorleap_preprocess, input/GT encoders, @tensorleap_load_model, @tensorleap_integration

by tensorleapGitHub

legal-interpretation-argument

当法律推理过程中遇到以下情形时触发本技能：（1）法条文本含义模糊、存在多种理解可能；（2）法条适用于具体案件事实时产生争议；（3）需要论证某一法条应当/不应当适用于特定情形；（4）当事人双方对同一法条的理解存在分歧；（5）法条之间存在表面冲突，需要通过解释协调；（6）新型案件事实无法直接对应既有法条文本；（7）需要对裁判文书中的法律适用进行分析或质疑。本技能的核心是运用文义解释、体

by MaryHu-YRGitHub

1
5801
5802
5803
5804
5805
5901