adopt
Take a folder that already holds research — papers, notes, code, half-written drafts — into MAGI, without breaking what is already there.
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.
$ npx -y skills add Misaka16384/Wikify --skill research --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/researchContext preview
The summary Claude sees to decide when to auto-load this skill.
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.
name: research description: "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." commands: research: "Investigate a question from several angles and land the findings." origin: magi
A question worth more than one search — including "find what contradicts what", which is this skill with an adversarial brief, not a separate one.
1. Decompose the question into 3–6 angles that would disagree with each other. Say how many sub-agents that is before starting; 10 concurrent is the ceiling. 2. Each sub-agent searches the project only and returns findings in the block form `CLAIM: / EVIDENCE: "<quote>" / SOURCE_TYPE: / SOURCE:`, one per finding, `SOURCE` pointing into `raw/`. 3. Collect into `scratch/`, then `magi verify <the scratch/ file you just wrote> --project-dir . --json`. Unverified findings are reported as unverified, in their own section — never merged into the rest. 4. Every finding that has a truth value becomes a proposition: `magi thread new <slug> --kind proposition --title "<name>" --claim "<statement>" --purpose "<why>"`. A contradiction is one proposition with both sources posted to it, which puts it on the decision queue where a person will see it. 5. At most one long-form output: `wiki/topics/<slug>.md` with `type: synthesis`. If there is nothing to synthesise, the propositions are the result. 6. `magi validate <the synthesis>`, then `magi lint --fix`.
Name the angle that came back empty; a **partial** sweep read as whole is the failure this whole pipeline is arranged against.
only source; a finding with no `SOURCE:` in `raw/` is not a finding.
human once, at the end. Asking for a prediction means quoting the **claim**, what evidence already exists, and what would falsify it — never a bare slug.
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
Repo: Misaka16384/Wikify
Take a folder that already holds research — papers, notes, code, half-written drafts — into MAGI, without breaking what is already there.
Answer a question from this project's own knowledge — retrieved, read and cited, never from memory.
Compile raw sources into dense, interlinked reference and concept cards, and mine the concepts a compiled card left implicit.
Turn whatever the human has — a PDF, a link, a DOI, a screenshot of a citation — into raw/ sources this project can compile.
Entry point for a MAGI research project: run magi next, do what it says, and call the skill it names.
Triage a literature-radar digest: judge each candidate against what this project is actually doing, and queue only what earns it.