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 1.1.0enterprise 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

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.

118.5K SkillsPublish yours

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

Agents452 Personas6 Prompts4 Templates4 Tools27710 Models

118505 results

deploy

0

How deployment to Skyr works: pushing to the skyr git remote, environments and the deployment lifecycle, pushing a deployment for approval and approving or rejecting one, rolling a deployment back, ex

by skyr-cloudGitHub

Not rated yet

Free

ClinicalLlmEvaluationBenchmarking_Agent

This skill guides the design, execution, and interpretation of evaluations for clinical LLM outputs, with emphasis on AI-generated clinical notes and adjacent clinical text workflows. It helps select

by mdbabumiamssmGitHub

ship

Ship workflow: detect + merge base branch, run tests, review diff, bump VERSION, update CHANGELOG, commit, push, create PR. Use when asked to "ship", "deploy", "push to main", "create a PR", "merge an

by spalsh-specGitHub

research-paper-writing

End-to-end pipeline for writing ML/AI research papers — from experiment design through analysis, drafting, revision, and submission. Covers NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Integrates automated e

by ouwei2013GitHub

research-paper-writing

Write ML papers for NeurIPS/ICML/ICLR: design→submit.

by LoopyLuciGitHub

review

Pre-landing PR review. Analyzes diff against the base branch for SQL safety, LLM trust boundary violations, conditional side effects, and other structural issues. Use when asked to "review this PR", "

by ibalasiteGitHub

design-html

Design finalization: generates production-quality Pretext-native HTML/CSS. (gstack)

by harshvardhankulkarniGitHub

review

Pre-landing PR review. Analyzes diff against the base branch for SQL safety, LLM trust boundary violations, conditional side effects, and other structural issues. Use when asked to "review this PR", "

by spalsh-specGitHub

review

Pre-landing PR review. Analyzes diff against the base branch for SQL safety, LLM trust boundary violations, conditional side effects, and other structural issues. Use when asked to "review this PR", "

ship

Ship workflow: detect + merge base branch, run tests, review diff, bump VERSION, update CHANGELOG, commit, push, create PR. Use when asked to "ship", "deploy", "push to main", "create a PR", or "merge

by TarunTeja44GitHub

develop-research-question

Conducts cycle-template Stages 1–4 — the theories/variables/datasets/methods exploration grounded in all three Project Reference streams (Stage 1), the Socratic development of the Problem-Related rese

by ScottSavaianoGitHub

case-retrieval

当用户需要查找与当前法律问题相关的类似案例、相关判决、裁判规则时触发此技能。典型触发场景包括：用户明确要求查找类似案例或判例；需要通过既往裁判支撑法律论点；进行案件预判需要参考同类判决；撰写法律文书需要引用权威案例；分析某一法律问题的司法实践趋势；对比不同法院、不同时期对同一问题的裁判立场。关键词包括但不限于：类似案例、相关判决、判例检索、裁判规则、同类案件、指导性案例、典型案例、司法观点、裁判要

by MaryHu-YRGitHub

pytorch-fsdp

Expert guidance for Fully Sharded Data Parallel training with PyTorch FSDP - parameter sharding, mixed precision, CPU offloading, FSDP2

by zangjeicyGitHub

office-hours

YC Office Hours — two modes. (gstack)

by Lord1EgyptGitHub

deepspeed

Expert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam, sparse attention

by ihatesea69GitHub

devex-review

Live developer experience audit. Uses the browse tool to actually TEST the developer experience: navigates docs, tries the getting started flow, times TTHW, screenshots error messages, evaluates CLI h

by huyonghui666GitHub

page-design

The house visual system for anirach.com (this repo) — canonical :root tokens, type scale, layout constants, component vocabulary, breakpoints, modern-CSS verdicts, and the anti-patterns this repo has

by AnirachGitHub

dfx_reviewer

Bundle Framework DFX 代码审查技能，专注于 HiLog API、HiSysEvent 和 HiTrace 组件的审查，包含日志基础规范、常见模式日志打印检查

by openharmonyGitHub

review

Pre-landing PR review. Analyzes diff against the base branch for SQL safety, LLM trust boundary violations, conditional side effects, and other structural issues. Use when asked to "review this PR", "

by TobiasPerryGitHub

review

Pre-landing PR review. Analyzes diff against the base branch for SQL safety, LLM trust boundary violations, conditional side effects, and other structural issues. Use when asked to "review this PR", "

by VertaKhanGitHub

review

Pre-landing PR review. Analyzes diff against the base branch for SQL safety, LLM trust boundary violations, conditional side effects, and other structural issues. Use when asked to "review this PR", "

by shhubbhGitHub

bmad-retrospective

Post-epic review to extract lessons and assess success. Use when the user says "run a retrospective" or "lets retro the epic [epic]"

by matheussluzzGitHub

plan-ceo-review

CEO/founder-mode plan review. (gstack)

by greencmGitHub

review

Pre-landing PR review. Analyzes diff against the base branch for SQL safety, LLM trust boundary violations, conditional side effects, and other structural issues. Use when asked to "review this PR", "

by VertaKhanGitHub

1
4931
4932
4933
4934
4935
4938