skills
來自 scenario-labs/skills 的 67 項代理技能 — 包含 scenario、scenario-game-assets、scenario-video。使用 npx skills add scenario-labs/skills 安裝。
AI 翻譯
個人 GitHub 帳號下公開儲存庫的擁有者可以登入並驗證所有權,自行管理介紹,無需管理員核准。
登入並產生驗證檔案,在 30 分鐘內將其提交至此儲存庫的預設分支。其他分支或分叉儲存庫中的檔案無效。然後在下方檢查檔案,即可無需管理員核准直接管理專案。請保留檔案以維持管理權限。
如需登入,將前往登入頁面。登入後請回到此處,再次點擊所選的驗證按鈕。
在專案資料夾中執行 /nomorevibe verify,即可驗證所有權並自行管理介紹。
一分鐘完成驗證A second opinion on your decisions, from a different AI company than the one you think with.
翻譯準備中
取自儲存庫 README
正在載入完整 README。 以下為已儲存的摘錄。
A second opinion on your decisions, from a different AI company than the one you think with.
Tell the assistant you think with, "grill this": Claude, ChatGPT, Copilot, Gemini, Grok or Muse. It writes up your decision, and you check it. Then an outside judge, a model from a different company, argues the strongest case against it. It names the cheapest test that would settle each doubt, and gives a verdict. Before you decide, you write what you expect, how sure you are, and what would prove you wrong. You can look back later from a record you keep. Grill does not store it.檢視完整 README ↗Hear the strongest case against your plan, then decide for yourself.
Setup guide: grillyour.ai See it first: four made-up decisions, grilled
Tell the assistant you think with, "grill this": Claude, ChatGPT, Copilot, Gemini, Grok or Muse. It sends the decision as you said it. An outside judge, a model from a different company, comes back with a short note: one verdict line, then one short line naming the question that would change the call, then the sharpest point and one cheap test. The verdict, the point and the test stay within about 50 words. The extra line is at most about 25 words, and it never comes before the verdict. Say more, options, or your call when you want the rest. A thin line gets a quick take and one question, not a refusal. A record is written only after you answer, and a percent is optional. Grill does not store it on the installed tool.
Verdict: shaky. The plan assumes customers stay at the new price, and nothing in it tests that. Falsifier: show the new price to one in ten new signups for two weeks, and compare how many start paying.
The verdict never becomes the decision. You decide. Your values and judgment calls are yours: each verdict lists what the judge checked for you separately from what is your call. The judge is a model from a different company. Grill uses OpenRouter's Auto Router, and it does not pin models. Only the write-up you approve leaves your machine. Every promise, and the code and test that enforce it: docs/PRINCIPLES.md.
Claude Desktop and Claude Code enforce that in code. The copy-and-paste routes check it and warn you. Who to paste into is in the table below.
The extension reads GRILL_API_KEY. OPENROUTER_API_KEY works when that is unset.
mtangoz/grill.Want it in one step? Use Claude Desktop, above.
| You think with | Judge with |
|---|---|
| ChatGPT | Claude, Gemini or Grok |
| Copilot | Gemini, because Copilot can run OpenAI, Anthropic or xAI models |
| Gemini | Claude, ChatGPT or Grok |
| Grok or GrokBot | Claude, ChatGPT or Gemini |
| Muse | Claude, ChatGPT or Gemini |
https://grillyour.ai/mcpRNdHSHmWCRJO40vd. Same for everyone. No secret.npx -y grillyour --set-key # once: paste your key, Enter, then Ctrl-D
Then add a server named grill that runs npx -y grillyour. The config holds no key. Each app's config, and one-click installs for Cursor and VS Code, are in docs/ANY-APP.md. A Grill Pro key works here too.
/plugin marketplace add mtangoz/grill
/plugin install grill@grill
It asks for your model router key. Grill reads GRILL_API_KEY first. OPENROUTER_API_KEY works when that is unset. Or save the key once for every app on this computer with npx -y grillyour --set-key. It goes in ~/.config/grill/key, outside any project's .env.
When Claude Code shows you a plan to approve, Grill adds one line, once a session: want an outside judge on this plan first? Keep planning and say "grill this plan". Claude Code hands the hook the plan, and the hook ignores it: it sends nothing and keeps nothing of the plan. To ask once, it keeps an empty marker file per session in the plugin's data folder, and removes markers older than two days the next time it runs. Turn it off with GRILL_PLAN_OFFER=off.
Claude Code's advisor (/advisor) has a stronger Claude look over the work. That is a second opinion from the same company. Grill's judge is from a different one. Use both.
Invite-only. The steps are at grillyour.ai/start. Use the same email each time, the email your invite went to, every time.
https://grillyour.ai/mcp, name it Grill, then sign in.https://grillyour.ai/mcp, choose OAuth. Click I understand and want to continue, then Create. Install it, then sign in.Add this MCP server: https://grillyour.ai/mcp, then sign in when asked.https://grillyour.ai/mcp, Next, then sign in.Setup for the owner is in docs/HOSTED.md.
Grill is free. On your own key a grill costs about a cent or two. Copy and paste uses the assistants you already have.
Coming later: an optional Pro plan with saved decision history and look-back reminders. The free tool stays free and account-free. Hear when it's ready.
GRILL_NEWS=off. It stops on its own.What we will and won't do with your data, and how we build: docs/PRINCIPLES.md.
Leave them off and the tool does not call Grill. To opt in:
/plugin → Configure options, the same switch.GRILL_USAGE_STATS=on.Turn them off in the same place, or set GRILL_PING=off. DO_NOT_TRACK=1 also disables the ping. The paste route does not send it.
Details: docs/PRIVACY.md.
Optional, in Claude, when you keep your own decision log: docs/WEEKLY-REVIEW.md.
MIT. See LICENSE. The code that handles your decision stays MIT for good (docs/PRINCIPLES.md). The name and logo are not part of the license: TRADEMARKS.md.