Skip to content
Data
Skill

/magi

Entry point for a MAGI research project: run magi next, do what it says, and call the skill it names.

From plugin
magi
711 skills1 hook

Claude Code

$ npx -y skills add misaka16384/magi --skill magi --agent claude-code

SKILL.md

magi.SKILL.md
name: magi
description: "Entry point for a MAGI research project: run magi next, do what it says, and call the skill it names."
commands:
  magi: "Work out what this research project needs next, and do it."
origin: magi

magi — the entry

When to use

Any turn in a MAGI project where you do not already know what you are doing.

Method

1. `magi next` — it reads the notes and ranks what is owed. It never acts. 2. Do the first item, unless the human just asked for something else: their sentence outranks the list. Everything under **"For the person"** goes to them in **one message**, and **asking for a prediction means showing the claim** — `next` prints it under the item, `--json` has it in `bets_waiting`. A slug is not a question anybody can answer. 3. When an item names a skill, call it. When it names a command, run it. 4. A result that came before its note is a finding: open it with `--found`, or mark an existing one `magi thread found <slug>`. Neither is asked to bet. A reviewer's `restate` is yours: fix the words as its post says, then `magi thread status <slug> supported --text '<what changed>'`. 5. Anything the human says in passing worth keeping goes into `inbox/notes.md`, one line, untidied; a later `magi next` files it. 6. Before stopping: `magi sync --close`. It refuses while something happened that nobody wrote down — clear each with `magi thread post <slug> --text '<what happened>' --host human` or `magi decide --about <slug> --text '<their words>'`, then close again.

Rules

  • **Never** invent a next step while `magi next` has one. That list is derived

from the notes; a step you made up is derived from nothing.

  • **Never** edit a status in `threads/` by hand. `magi thread status <slug>

<status> --text '<why>'` writes the flip and its reason together, or neither.

  • Closing a **line** and leaving `disputed` or `conflict` are a person's call:

`magi close <line>`, or `magi decide --about <slug> --text '<their words>'`. **Never** redo such a flip unsigned to pass the close gate; each unsigned repeat is one more signature owed.

  • Read the `magi:begin` block in `AGENTS.md` once per session; those invariants

are not advice. Stuck: `magi guide --search "<the error>"`, never a guessed flag.

Read more
@misaka16384
Ships withmagi

MAGI 是一个 agent-native 的科研工作环境:人是驾驶员,LLM agent 是机体,确定性的 magi CLI 是拘束具——三者同步率越高,科研越快。它把学术论文(PDF/LaTeX)摄入、编译为 Obsidian 兼容的概念卡片项目,并用三核架构管理完整的科研状态: 进入任意项目先跑 magi sync——它输出同步率、三核状态和逐条可执行的修复提示。magi radar 是文献雷达:定时发现相关新论文,并侦察"知识上应引用我方论文却未引用"的候选。同一份 skills 通吃 Claude

Stars on GitHub

Momentum

stars in total
7
Star history of Misaka16384/Wikify on GitHub, a chart by star-history.com

Other skills on magi.

adopt

adopt

Take a folder that already holds research — papers, notes, code, half-written drafts — into MAGI, without breaking what is…

@misaka16384@misaka16384Install Skill
ask

ask

Answer a question from this project's own knowledge — retrieved, read and cited, never from memory.

@misaka16384@misaka16384Install Skill
brief

brief

Write the one thing a person reads after an unattended run — its report — and the lecture notes that prepare them for it, in…

@misaka16384@misaka16384Install Skill
compile

compile

Compile raw sources into dense, interlinked reference and concept cards, and mine the concepts a compiled card left implicit.

@misaka16384@misaka16384Install Skill
discuss

discuss

Talk a run over with the person until it can be written down — motivation, directions, what is not worth it, when to stop, their…

@misaka16384@misaka16384Install Skill
ingest

ingest

Turn whatever the human has — a PDF, a link, a DOI, a screenshot of a citation — into raw/ sources this project can compile.

@misaka16384@misaka16384Install Skill

More skills from other plugins.

context-loader
Auto-invoked

context-loader

Search memories from earlier Pi sessions in this repository. Use it when earlier work may already explain the code, error,…

mem04d69k
@mem0ai@mem0aiInstall Skill
analyzing-ai-citations

analyzing-ai-citations

Answer AI citation and answer engine optimization (AEO) questions in PostHog: whether AI answer engines (ChatGPT, Claude, and an…

posthog11d41k
@posthog@posthogInstall Skill

Questions about magi.

Which coding agents can use magi?
magi installs in Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf with the skills CLI, using each agent's flag shown on this page. Flowy's auto-invocation, which fires a skill when your prompt matches, runs in Claude Code only.