메뉴
Scaffold a new knowledge engine workspace OR link to an existing shared knowledge base. Use when starting a new knowledge base or connecting a project to an existing one.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
Problem-driven research loop — start from YOUR project or idea plus a pile of papers (even if insufficient), decompose it into a problem structure, map it onto the principle library, fill the gaps with targeted reading, and assemble a principle-grounded design. Iterates as you read more. Use when the user has a research problem or project to push forward — not just papers to absorb. Triggers: "improve my project", "I have an idea and some papers", "help me design X", "用这些论文迭代我的项目", "推进我的研究".
Sharpen a vague idea, a literature gap, or a stalled project into a GOOD research question — consequential, specific, falsifiable, feasible — BEFORE committing to a technical route. Produces a structured Question Card, then optionally hands off to /kw-explore to form the technical route. Triggers: "is this a good research question", "help me sharpen my question", "我这个想法值得做吗", "把想法变成研究问题", "问题挖掘 / 具象化", "帮我磨一下研究问题".
Single entry for the knowledge engine. Detects state and offers choices — fetch papers by id/DOI/title, absorb all new papers (L1→L2), run L3 synthesis. Use when the user says "process the knowledge base", "/kw", "fetch this paper", or drops new papers.
SOC 직업 분류 기준
| name | kw-init |
| description | Scaffold a new knowledge engine workspace OR link to an existing shared knowledge base. Use when starting a new knowledge base or connecting a project to an existing one. |
Two modes:
If a shared knowledge base already exists (e.g. ~/Downloads/soft/knowledge_wiki/memory/),
link this project to it instead of creating a new one:
kw link ~/Downloads/soft/knowledge_wiki/memory/
This creates .kw/config.yaml with paths.memory pointing to the shared library.
All kw commands (search, verify, status, etc.) now use the shared knowledge.
Run this once in any repo to set up a fresh, empty knowledge engine.
<project-root>/
├── .kw/
│ └── config.yaml # Engine config (model routing, fetch policy)
├── memory/
│ ├── SCHEMA.md # Data structure contract
│ ├── index.json # Central index (starts empty)
│ ├── papers/ # L1 faithful readings
│ ├── principles/ # L2 abstract principles
│ ├── synthesis/ # L3 design-space, contradictions, gaps
│ └── golden/ # Exemplar records for quality reference
├── paper/ # Raw PDFs (gitignored)
├── process/
│ ├── extract-template.md # L1 extraction rubric
│ └── distill-rubric.md # L2 distillation rubric
└── problems/ # Use-case pointers
memory/SCHEMA.md already exists. If yes, report "Already initialized" and STOP..kw/config.yaml from the template below.memory/SCHEMA.md from the kw-engine package's canonical schema.memory/index.json with the empty initial state.process/extract-template.md and process/distill-rubric.md.paper/*.pdf and .kw/index.db to .gitignore if not already present./kw to start ingesting papers."version: 1
paths:
papers_src: paper/
memory: memory/
index: memory/index.json
process: process/
problems: problems/
logs: .kw/logs/
loop1:
synthesize_after_n_papers: 5
process_versions:
extract_template: extract-template@v1
distill_rubric: distill-rubric@v1
model_routing:
kw-fetcher: sonnet
kw-reader: sonnet
kw-distiller: opus
kw-synthesizer: opus
kw-verifier: sonnet
fetch:
fallback_order: [with_fallback, arxiv, biorxiv, medrxiv, pubmed, crossref, openalex, semantic, curl_oa]
validate:
magic_bytes: "%PDF-"
min_bytes: 10240
max_bytes: 52428800
scihub: false
paywalled_via_browse: true
idempotent: true
active_expansion:
enabled: false
{
"version": 1,
"counters": { "principle": 0 },
"papers": [],
"principles": [],
"synthesis": { "last_run": null, "n_principles_at_last_run": 0 }
}