chenpg2

23 mods across 2 repositories, 13 stars between them.

kw-engine

01

chenpg2/kw-engine

Plugin Claude Code

Methodology evolution engine — distill transferable principles from literature, search by problem structure.

11 2mo ago A tokens not measured original MIT

kw-engine

02

chenpg2/kw-engine

Plugin Claude Code

Methodology evolution engine — distill transferable principles from literature, search by problem structure.

11 2mo ago A tokens not measured original MIT

kw-engine AGENTS.md

03

chenpg2/kw-engine

Instructions file CodexOpenCode

Instructions for chenpg2/kw-engine, covering agents.md, commands and conventions.

11 2mo ago A 188 tokens original MIT

kw-engine CLAUDE.md

04

chenpg2/kw-engine

Instructions file

Instructions for chenpg2/kw-engine, covering claude.md, commands and conventions.

11 2mo ago A 189 tokens copy · 95% MIT

kw-distiller

05

chenpg2/kw-engine

Agent

Distills a Layer-1 paper reading into abstract, transferable Layer-2 principle records (first-principles), capturing problem-signature ↔ mechanism ↔ rationale.

11 2mo ago A 38 tokens original MIT

kw-fetcher

06

chenpg2/kw-engine

Agent

Acquires ONE paper PDF into paper/ .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.

11 2mo ago A 58 tokens original MIT

kw-reader

07

chenpg2/kw-engine

Agent

Faithfully reads one paper PDF into a Layer-1 structured reading per the memory contract. Use to extract (not abstract) a paper.

11 2mo ago A 31 tokens original MIT

kw-synthesizer

08

chenpg2/kw-engine

Agent

Cross-paper Layer-3 synthesis — clusters principles into a design-space map, surfaces contradictions and gaps. Run periodically (Loop 1 re-synthesis).

11 2mo ago A 36 tokens original MIT

kw-verifier

09

chenpg2/kw-engine

Agent

Independent quality/integrity reviewer for memory records. Checks SCHEMA invariants, provenance resolution, L1 faithfulness, L2 abstraction. Never produces records — review lane only.

11 2mo ago A 40 tokens original MIT

kw-explore

10

chenpg2/kw-engine

Skill Claude CodeCodex

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…

11 2mo ago A 121 tokens original MIT

kw-init

11

chenpg2/kw-engine

Skill Claude CodeCodex

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.

11 2mo ago A 35 tokens original MIT

kw-question

12

chenpg2/kw-engine

Skill Claude CodeCodex

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…

11 2mo ago A 117 tokens original MIT

kw

13

chenpg2/kw-engine

Skill Claude CodeCodex

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.

11 2mo ago A 65 tokens original MIT

genius

15

chenpg2/genius-plugin

Plugin Claude Code

GENIUS (Grounded Evolutionary Novelty for Ideation, Understanding & Science) — the bridge from a scientific problem to an openevolve run: Claude+Codex+Kimi debate an idea (or a local sub-problem in an existing project) into grounded, novel, computable candidates, then a human freeze-gate hands a ready evolve-dir to…

2 2mo ago A tokens not measured

genius-focus

17

chenpg2/genius-plugin

Command

Break a local sub-problem (principle/formula/math/method) inside the current project.

2 2mo ago A 20 tokens

genius

19

chenpg2/genius-plugin

Command

Run the GENIUS multi-agent idea→portfolio pipeline on a research idea.

2 2mo ago A 16 tokens

genius-evolve

20

chenpg2/genius-plugin

Skill Claude CodeCodex

Use when the user runs /genius-evolve or asks to run the EVOLVE engine on an already-prepared evolve-dir (initialprogram.py + frozen evaluator.py + frozen.lock).

2 2mo ago A 42 tokens

genius-focus

21

chenpg2/genius-plugin

Skill Claude CodeCodex

Use when the user runs /genius-focus or asks GENIUS to break a local sub-problem (a principle/formula/math/method) inside an EXISTING project. Auto-understands the project, surfaces candidate sub-problems, user picks one, then runs a scoped axioms-grounded debate (+gated EVOLVE).

2 2mo ago A 71 tokens

genius-understand

22

chenpg2/genius-plugin

Skill Claude CodeCodex

Use when the user runs /genius-understand or asks GENIUS to map/diagnose the current project. Runs the bundled understand workflow and presents the grounded map. Persists understand-map.md and understand-map.json to the runDir immediately after the workflow returns.

2 2mo ago A 59 tokens

genius

23

chenpg2/genius-plugin

Skill Claude CodeCodex

Use when the user runs /genius or asks to run the GENIUS multi-agent idea→portfolio pipeline. Computes the run directory and launches the bundled debate-engine workflow.

2 2mo ago A 38 tokens