- name
SKILL.md
技能檔案保留在發布者的儲存庫中。
在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add MiniMax-AI/mcode-stack --skill agent-brief -a cursor -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add MiniMax-AI/mcode-stack --skill agent-brief -a claude-code -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add MiniMax-AI/mcode-stack --skill agent-brief -a codex -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add MiniMax-AI/mcode-stack --skill agent-brief -a grok -y在 Grok Bot 聊天中傳送複製的訊息。Bot 會從 GitHub 取得這個 SKILL.md,並加入你所有 Bot 共用的技能中。
Install this skill: https://github.com/MiniMax-AI/mcode-stack/tree/HEAD/stacks/ronny/skills/agent-brief來自發布者
We delegate a lot. What we try not to delegate is knowing what we asked for. If we cannot write the task down in a few plain lines, the idea is not ready, and the agent will fill the gaps with defaults we never chose. Five minutes here saves a review that cannot tell right from plausible.
Decide how much of this skill to run.
evidence-first-review after.When unsure, ask: if this is quietly wrong, who finds out, and when?
One line on what we expect the answer or the fix to be, written before the agent starts. A wrong guess is fine. Its job is to give us something to compare against, so a polished answer does not become the default.
Hypothesis: the flaky
compaction.e2etest is a race between the summary write and the next turn, not a model issue.
If we get stuck writing this, we ask the agent to interview us first, or give it what we know and ask what we have not thought of. We do not ask it to write the brief for us.
Pick something we can check later, decided now so we cannot bend it to fit whatever comes back:
mcode -p "..." --json returns X);Give the agent the same means to check itself (test command, fixture, a running dev server), so it loops before we look.
Are we asking it to help us think, or to think for us? Both are fine. In the second case, we owe a stricter review, because we will not have the reasoning in our heads.
Paste this at the top of the task:
Stakes: low | high
Hypothesis: ...
Goal / users / out of scope: ...
Done = (tangible check): ...
Mode: think with me | do it for me
When done: show commands run and their output first, then the summary,
then the decisions and assumptions you made.
Write the brief before handing a non-trivial task to an agent or subagent, covering stakes, your own hypothesis, goal and scope in your words, what "verified" will mean, and whether the agent is think
---name: agent-briefdescription: Write the brief before handing a non-trivial task to an agent or subagent, covering stakes, your own…---# stacks/ronny/skills/agent-brief/SKILL.md總覽
Write the brief before handing a non-trivial task to an agent or subagent, covering stakes, your own hypothesis, goal and scope in your words, what "verified" will mean, and whether the agent is thinking with you or for you. Use before starting a MiniMax Code session, spawning a subagent, or delegating a PR, analysis or doc.
常見問題
從發布者下載 stacks/ronny/skills/agent-brief/SKILL.md,或複製路徑後開啟儲存庫。PlugMCP 只收錄這項技能,不代管檔案。
發布者將它存放在 https://github.com/MiniMax-AI/mcode-stack。
Claude、Cursor、Codex 和 Grok Build 可以讀取你從發布者儲存庫加入的 SKILL.md。在聊天中傳送技能的 GitHub 資料夾連結,Grok Bot 就會安裝它。