Skip to content

Pricing
Blog

Sign in Get started

Site footer

Spend less on every AI request. Safe before it leaves, explained after.

curl -LsSf https://opensmartroute.ai/install.sh | sh

Apache-2.0v1.8.0enterprise 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
Security
Observability
Pricing

Solutions

Who it is for
Budget owners
Platform teams
Security teams
Developers
Industries
Enterprise
Bring your bill
ROI calculator
Compare

Developers

SDKs and API
Documentation
REST API
Python SDK
TypeScript SDK
MCP server
Agent skills
Self-hosting
Downloads

Company

Blog
Newsletter
Changelog
Support
Contact sales
Status
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.

169.9K SkillsPublish yours

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

Agents6.9K Personas6.8K Prompts19.7K Templates33 Tools34.4K Models

169852 results

459

research-workflow

以研究文档组织人与 AI 的持续协作：同步正文编辑和评论、记录反馈处理、调整研究计划并恢复中断的研究。适用于明确要求文档协作或恢复既有研究的任务。

by hs3180GitHub

Not rated yet

Free

tdd

Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.

by chinglung-angh27GitHub

agent-script-role

프롬프트를 포함해 LLM을 호출하는 스크립트·파이프라인을 작성하거나 수정할 때 사용합니다.

by chaconne67GitHub

optimize-cuda-memory-locality

Design, implement, and review CUDA tiled and stencil kernels that use shared memory, registers, caches, halos, and coalesced global access. Use for matrix tiles, convolutions, PDE solvers, image filte

by olibartfastGitHub

gitnexus-cli

Use when the user needs to run GitNexus CLI commands like analyze/index a repo, check status, clean the index, generate a wiki, or list indexed repos. Examples: "Index this repo", "Reanalyze the codeb

by suchetranaGitHub

grilling

The reusable relentless-interview loop. Reach for it whenever a plan, decision, or idea needs stress-testing - building or not - or the user asks to be grilled.

redis-development

Redis performance optimization and best practices. Use this skill when working with Redis data structures, Redis Query Engine (RQE), vector search with RedisVL, semantic caching with LangCache, or opt

by oinoneGitHub

review-bugbot

Review code changes with Bugbot subagent.

by mdelriolanseGitHub

malware-genome

Comprehensive malware classification, behavioral fingerprinting, and family attribution system. Covers ransomware, trojans, worms, bots, rootkits, spyware, cryptominers, APT toolkits, and self-mutatin

by M-Inc-labGitHub

frontend-design

Designs, builds, or refactors user-facing web or application interfaces with deliberate visual direction, typography, color and spacing tokens, content hierarchy, responsive behavior, accessible inter

by thiientvGitHub

implement-change

Implement a verdaccio bug fix, feature, or refactor — establish the affected release lines, check whether existing configuration, package-access rules, plugins, or uplink options already solve it, put

by verdaccioGitHub

nunit-skill

Generates NUnit 3 tests in C#. Covers Assert.That constraint model, parameterized tests, setup/teardown, and Moq mocking. Use when user mentions "NUnit", "[TestFixture]", "[Test]", "Assert.That", "C#

by NeelakshSaxenaGitHub

board-digest

LINE WORKS の掲示板から情報を集めて要約・ダイジェスト・情報探索を行う。「掲示板をまとめて」「お知らせを探して」「今週の投稿を要約して」などの依頼で使う。

by aalto-consulting-incGitHub

agent-handoff

Use for agent handoffs and ongoing mailbox coordination: verify status, name the next owner and action, protect private data, and escalate blockers.

huggingface-hub

HuggingFace hf CLI: search/download/upload models, datasets.

by GreenyZAGitHub

prune-review

既存コードを厳し目にレビューし、過剰・冗長・残骸・継ぎ足しの歪みを指摘する。デフォルトは差分、差分だけで是非を判断できなければ周辺・全体まで読む。各観点で該当箇所を file:line で引用し、指摘のみ返す（修正はしない）。「厳し目にレビューして」「これ全部必要？」「1から書いても同じ？」と頼まれたときに使う。

by kazu728GitHub

diseno-ui

Checklist y principios de diseño visual con valor real (color, tipografía, layout, contraste) para usar al crear el sistema de diseño de un proyecto DevSquad AI, o al implementar/revisar código que de

saas-security

Comprehensive SaaS security skill covering code auditing, checklist generation, and vulnerability reporting. TRIGGER this skill whenever the user asks to: audit code for security issues, review a code

by vitormiziaraGitHub

archdoc-backfill

Use when recording decisions or designs in an ArchDoc repository that were taken before the repository existed, including the front matter shape, the Sources requirement, and the rule against inventin

by archdochqGitHub

interrogate

Use for "interrogate", "adversarial review", "challenge this", "stress test this code", "find blind spots", or "tear this apart". Multiple LLM reviewers challenge changes from independent angles.

by nathanwbaileyGitHub

fr-execute

Execute an agentic phase from a plan. Use when implementing assigned work from a plan file. Agent-facing skill.

by derio-netGitHub

candoitall-api-access

Use when authenticating to CanDoItAll, using Swagger JWT authorization, or managing API users, capabilities, sessions and machine-token registrations through the HTTP API.

by fyziktomGitHub

tinyvault-claude-review

Dispatch a fresh read-only Claude Opus 5 plan, QA, or security review for an Astra-led TinyVault session and collect verified results. Use for independent Claude review gates or an explicit request to

by jonathanavniGitHub

bmad-testarch-nfr

Audit NFR evidence for performance, security, reliability, and maintainability. Use when implementation evidence exists and the user says "audit NFR evidence", "audit NFRs", or "evaluate non-functiona

by sergio-salcedo-devGitHub

1
254
255
256
257
258
7078