Skip to content
Data
Skill

/ingest

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

From plugin
magi
78 skills1 hook
Install
$ npx -y skills add Misaka16384/Wikify --skill ingest --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/ingest

Context preview

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

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

SKILL.md

ingest.SKILL.md
name: ingest
description: "Turn whatever the human has — a PDF, a link, a DOI, a screenshot of a citation — into raw/ sources this project can compile."
commands:
  ingest: "Ingest papers, articles and notes into raw/."
origin: magi

ingest

When to use

Anything new is arriving: files in `inbox/`, a link or DOI in the chat, a citation the human read out.

Method

1. Files already in `inbox/`, or a path you were given: `magi ingest auto` — it routes by type and finalizes. Stop here unless it refuses. (A run that skipped cleanup: `magi ingest finalize <the file> --project-dir .`.) 2. A link, DOI, arXiv id or citation: identify it first — that is the step that needs you, not the pipeline. An id you typed from memory goes in as `magi ingest url "<id>" --expect "<title fragment>"`; then `magi ingest batch-run`. 3. `magi ingest review` lists what is waiting. Show its findings to the human before committing — surface `identity-mismatch`, `figure-count-mismatch` and `image-path-not-portable` every time: the file is not what its name says. `math-damage` counts formulas that will fail `magi math check`: say the number. 4. Once the human has seen the list: `magi ingest review --approve-all` (or `--item <id> --decision approve` per row), then `magi ingest review --commit`. 5. After a batch: `magi math check --json` — a `$$` that lost its pair swallows the paragraph after it and is still valid LaTeX. Work the list with `tidy`; papers from an older arXiv-HTML ingest first get `magi math repair --dry-run`.

Rules

  • **Never** transcribe pages through vision because a converter failed: it costs

one sub-agent call per page. Not until a person has said yes; 10 at once.

  • **Never** commit a batch the human has not seen the findings for.
  • A converter that exits non-zero: report its stderr and stop. An unreadable

file: name it and carry on. Report **partial** work as partial — "9 of 12".

  • Which project a source belongs to is never your guess: when it is

ambiguous, stop and ask. Collect the questions the work you delegated could not ask (Invariant 4) and put them all at once.

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
11d ago
Last commit
3mo ago
Created

Repo: Misaka16384/Wikify

Other skills on magi.

adopt
Skill

adopt

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

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.