Skip to content
Data
Skill

/adopt

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

From plugin
magi
78 skills1 hook
Install
$ npx -y skills add Misaka16384/Wikify --skill adopt --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.
  • Slash command/adopt

Context preview

The summary Claude sees to decide when to auto-load this skill.

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

SKILL.md

adopt.SKILL.md
name: adopt
description: "Take a folder that already holds research — papers, notes, code, half-written drafts — into MAGI, without breaking what is already there."
commands:
  adopt: "Bring an existing research folder into MAGI."
origin: magi

adopt

When to use

A folder with work already in it and no `threads/`. A project MAGI itself made is `magi migrate`, not this.

Method

1. `magi adopt survey .` — read the folder first. It also pulls every arXiv id and DOI out of the prose, which is where most of the sources already are. 2. Collect what this conversation says about the work: papers named, claims made. Nothing there is a normal result — say "0 from the conversation". 3. `magi init` in place. It only adds; it touches nothing already there. 4. Write `{"moves": [{"from": "x", "to": "drafts/x"}]}` — others' material to `raw/`, the human's own working out to `drafts/`, code and data left alone. Shape it to MAGI: the references between the files are repaired for you. 5. Show the human the plan, then `magi adopt apply plan.json --dry-run`, then for real. `magi adopt undo` puts the files *and* the edited text back. 6. `magi ingest url <the ids>`, `magi ingest batch-run`, then `ingest`. 7. What matters: open what the material claims. Worked out already, it is a **finding**, no bet to ask: `magi thread new <slug> --kind proposition --title '<claim>' --purpose '<why now>' --found <date> --derivation <draft>`. Only an open conjecture takes `--bet unknown`. A plan index and a status board are lines and propositions already. 8. `magi index`, then `magi next`. Still "no propositions" means the folder was tidied, not adopted.

Rules

  • **Never** move anything the human has not seen listed in the plan first.
  • **Never** put the human's own writing in `raw/`: it is re-ingested and never

hand-edited, so a draft filed there can never be worked on again.

  • A claim made in conversation is not evidence; it opens at `--bet unknown`.
  • Two projects' material in one folder is ordinary. If it splits, ask which

project this is — that one is not yours to decide.

  • Say what is **partial**: "3 of 5 placed" beats a summary that looks whole.
Read more
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

Get the whole plugin
Stats
7
Stars
1
Forks
Active
Maintenance
Python
Language
12d ago
Last commit
3mo ago
Created

Repo: Misaka16384/Wikify

Other skills on magi.

research
Skill

research

Investigate a question across the project from several angles at once, verify what comes back, and land it as propositions plus at most one synthesis.