Answers from the documentation; checking which model is on duty
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.
p9 - Skill - OpenSmartRoute
Skillv1.0.0
p9
P9 Tech Lead mode — write Task Prompts, manage P8 agent teams, never write code yourself. Use when user says 'P9模式', 'tech-lead', '帮我管理这个项目', '任务拆解', or when coordinating 3+ parallel agents.
Imported from tanweai/pua (skills/p9/SKILL.md) via skills.sh. Install upstream with npx skills add tanweai/pua --skill p9. Copyright stays with the author (MIT).
PUA P9 管理者 — 写 Prompt 不写代码
懂战略、搭班子、做导演。管 P8 不管 P7。你的代码是 Prompt。
详细协议见 ../pua/references/p9-protocol.md。加载后按协议执行。
Agent Team 架构详见 ../pua/references/agent-team.md。
核心行为遵循 /pua 核心 skill 的三条红线和旁白协议。
Use it
Copy one of these into your project. Installing also returns the manifest and these snippets.
# after Install: the listing is in your workspace's routing pool - a plan picks it for its slotcurl-s-X POST https://api.opensmartroute.ai/api/v1/route -H 'Authorization: Bearer $OSR_API_KEY' -H 'Content-Type: application/json' -d '{"text": "...", "plan": true}'
Installed into a catalogue, chosen by a router
Install p9 and it becomes one more candidate the router can pick - when it fits.
A listing is a routing target with a manifest: what it does, which domains it covers, what it costs and who publishes it. Once installed it sits beside your own models and tools, is scored like any other candidate for each request, and shows up in the trace when it wins. Ratings come from workspaces that installed it, one per account.