By chenpg2
Orchestrates a problem-driven research methodology: decompose ideas into structural problems, map to first-principles from literature, and synthesize design-space maps with gap analysis via layered paper-to-principle extraction.
Distills a Layer-1 paper reading into abstract, transferable Layer-2 principle records (first-principles), capturing problem-signature ↔ mechanism ↔ rationale.
Acquires ONE paper PDF into paper/<id>.pdf via a robust multi-source open-access fallback chain, validates it is a real PDF, and registers a pending index entry. Use to fetch a paper before kw-reader reads it. Never reads/abstracts the paper.
Faithfully reads one paper PDF into a Layer-1 structured reading per the memory contract. Use to extract (not abstract) a paper.
Cross-paper Layer-3 synthesis — clusters principles into a design-space map, surfaces contradictions and gaps. Run periodically (Loop 1 re-synthesis).
Independent quality/integrity reviewer for memory records. Checks SCHEMA invariants, provenance resolution, L1 faithfulness, L2 abstraction. Never produces records — review lane only.
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".
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.
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.
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Stop re-reading papers. Start reusing the why.
A methodology evolution engine: it distills transferable problem-solving principles from literature, so when you hit a new problem you search by its structure and get back a mechanism that works — plus the reason it works and when it breaks.
You drive it by talking to Claude Code. No file editing, no commands.
English · 简体中文
You read a paper, extract a clever trick, and forget it. Six months later you face a problem the same trick would solve — but it was in another field, used different words, and your notes are a pile of PDFs. Your bottleneck was never finding papers. It was reusing the underlying method across domains.
kw-engine treats that as the actual problem.
It distills literature through three layers, stripping the domain and keeping the transferable logic:
Paper PDF
│
├─ L1 faithful extraction what the paper says, with section locators — no interpretation
│
├─ L2 abstraction strip the domain, keep the transferable core:
│ problem-signature · WHEN it applies (problem structure)
│ ↔ mechanism + math · WHAT to do
│ ↔ rationale · WHY structure ↔ mechanism holds
│
└─ L3 synthesis cluster principles into a design-space map; surface
contradictions and GAPS — your next reading list
Then the payoff:
New problem → search by its structure → matched mechanism + rationale + when-it-breaks
It's not a search index over text. It's a compiler from empirical results to reusable problem-solving strategies. (The math of why this works is at the end.)
| What it retrieves | Indexed by | |
|---|---|---|
| RAG / vector search | text chunks | surface semantics |
| Zotero / citation managers | references & PDFs | metadata, tags |
| Skill libraries (e.g. Voyager) | executable task code | task name |
| kw-engine | mechanism + why-it-works + when-it-fails | problem structure |
kw-engine runs inside Claude Code. Install it once, then you just talk to Claude about your papers.
Brand-new to all this? Follow the step-by-step beginner tutorial — it assumes zero terminal experience and walks through a full case. Also available in 中文.
Four lines in your terminal — the only commands you'll ever need:
curl -LsSf https://astral.sh/uv/install.sh | sh # install uv (skip if you have it)
uv tool install git+https://github.com/chenpg2/kw-engine # the engine
claude plugins marketplace add chenpg2/kw-engine # the Claude Code plugin…
claude plugins install kw-engine@kw-engine # …skills + agents that drive it
Windows: replace the first line with
powershell -c "irm https://astral.sh/uv/install.ps1 | iex"
After this, everything happens in conversation.
No Claude subscription? Use Kimi or DeepSeek. Claude Code can run on any Anthropic-compatible backend. Point it at your provider with two env vars in
~/.claude/settings.jsonand everything below works identically:
- Kimi:
ANTHROPIC_BASE_URL=https://api.moonshot.cn/anthropic,ANTHROPIC_AUTH_TOKEN=<your Kimi key>- DeepSeek:
ANTHROPIC_BASE_URL=https://api.deepseek.com/anthropic,ANTHROPIC_AUTH_TOKEN=<your DeepSeek key>(it even maps strong/cheap models, so the read-cheap/distill-strong split is preserved)
Open Claude Code in any folder and say what you want. Claude uses the engine for you and shows you the results — you never touch a file or a command.
npx claudepluginhub chenpg2/kw-engine --plugin kw-engineComplete creative writing suite with 10 specialized agents covering the full writing process: research gathering, character development, story architecture, world-building, dialogue coaching, editing/review, outlining, content strategy, believability auditing, and prose style/voice analysis. Includes genre-specific guides, templates, and quality checklists.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Comprehensive startup business analysis with market sizing (TAM/SAM/SOM), financial modeling, team planning, and strategic research
v9.44.1 — Patch release for Gemini environment/version detection and qwen auth gating. Run /octo:setup.
Comprehensive .NET development skills for modern C#, ASP.NET, MAUI, Blazor, Aspire, EF Core, Native AOT, testing, security, performance optimization, CI/CD, and cloud-native applications
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.