By QuantumBFS
Brainstorm and refine scientific research ideas by surveying literature, indexing papers, and drafting manuscripts with structured report generation.
Use when brainstorming research ideas — a research collaborator that understands your background, helps find interesting problems together, and shares relevant resources along the way
Use when analyzing conversation patterns — extracts dialog from Claude Code or Codex CLI history, classifies each user message across 6 academic dimensions (Bloom's cognitive level, Graesser question depth, Paul & Elder reasoning probe, Walton presupposition quality, Long & Sato discourse function, Graesser generation mechanism), and outputs tagged dialog reports
Use when adding one or many new references (arXiv ID or DOI) to a sci-brain knowledge base — `<project>/.knowledge/` by default, or `advisors/<slug>/.knowledge/` when invoked from an advisor flow. Fetches metadata via Semantic Scholar, downloads PDFs (with SciHub fallback), renders to markdown, regenerates `INDEX.md`, and appends to `ref.bib`. Handles both single refs and bulk-from-bib batches.
Use when reviewing the visual design/quality of a figure, plot, or diagram — "is this figure well-designed", "review my plot", "critique this figure's layout/colors", "does this figure have good taste". Judges alignment, proximity, color, typography, clarity, and scientific-plot conventions against an 18-rule rubric, renders the figure to look at it, reads its source when available, then prints a scorecard. Report-only (never edits) and terminal-first (saves a file only on request). Not for whether a figure is cited/discussed in a manuscript (use paper-reviewer) or for drafting figures (paper-writer's Figure Rulebook).
Use when attacking a single hard goal that resists a direct solution — runs an autonomous CDCL/DPLL-style search (decide → propagate → learn → backjump, with a meta-pivot when stuck), taking notes after every trial. Domain-agnostic (math, theory, design, debugging, strategy); optionally pulls facts from a project knowledge base. Not for open-ended research ideation (use brainstorm-ideas).
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.
⚠️ Breaking change in v0.3. The on-disk layout changed: knowledge bases now live at
<project>/.knowledge/withINDEX.md+<project>/ref.bib, replacing the old<registry-root>/<topic>/registries (summary.md+references.bib). SeeCLAUDE.md§ "Migrating from the pre-0.3 layout" formvcommands. Thefetch-papersskill was folded intodownload-ref --from-bib.
An AI-powered research brainstorming partner. Tell it a research topic — it helps you find good problems, think them through, and shape concrete research ideas together with you.
Works with Claude Code, Codex, and OpenCode. Skill question styles inspired by superpowers.
Open Claude Code/Codex/OpenCode and type:
Install the plugin/skills from https://github.com/QuantumBFS/sci-brain
Then invoke `brainstorm-ideas` skill to start talking.
/brainstorm-ideas skill do?You start a conversation. The agent asks about your background — you can describe yourself, or point it at your Zotero library or Google Scholar profile so it can learn from your papers directly. The better the agent understands you, the higher quality its recommendations are.
Then you pick a domain expert (distilled from real scientists' conversations with AI, see list) to assist you. Their profile is loaded into a subagent to help you ask the right questions.
/brainstorm-ideas searches the web as you talk, but if you want a thorough literature map before brainstorming, run /survey first. It searches in parallel across seven strategies — landscape mapping, adjacent fields, cross-vocabulary, cross-method, historical lineage, negative results, and benchmarks — and builds a knowledge base with verified BibTeX.
When you run /brainstorm-ideas afterward, it automatically picks up the survey results and uses them to ground the conversation.
/survey ← build a literature map
/brainstorm-ideas ← brainstorm with that literature loaded
<project>/.knowledge/ — papers, rendered markdown, INDEX.md, NOTES.md. Populated by /survey, /researchstyle, /download-ref.<project>/ref.bib — cite-key namespace, shared with any LaTeX in the project.advisors/<slug>/.knowledge/ and advisors/<slug>/ref.bib — per-advisor private cache, gitignored.docs/discussion/ — each session is a timestamped file; the next session picks up where you left off.articles/ in your current directory, with a matching .bib file.If you've used Claude Code or Codex for research conversations and want your thinking style captured as a reusable advisor profile, just run:
clone https://github.com/QuantumBFS/sci-brain,
invoke incarnate skill in the cloned repo to create my profile,
then submit a pr,
include all relevant chat history, interview output and the generated profile.
The whole process is interactive — you review everything before it's published, and you can decide to include the raw conversation data (for research purposes) in the pr or not.
Initiator: Lei Wang and Jin-Guo Liu
MIT. Feel free to adapt from the current codebase, BUT please acknowledge this package properly, thank you.
npx claudepluginhub quantumbfs/sci-brain --plugin sci-brainVerify and validate BibTeX references against CrossRef metadata. Finds uncited entries and flags discrepancies in title/author/journal/volume/pages/year.
Submit GPU compute jobs to a Slurm cluster: sbatch script generation, GPU type selection, log management.
Download academic papers as PDFs given a URL, DOI, title, or arXiv ID. Tries open web → Sci-Hub → arXiv.
Semi-automated research assistant for academic research and software development, with skills for literature review, experiments, analysis, writing, and project knowledge management
Academic research agents — hypothesis generation, experiment design, paper drafting, peer review simulation, and more.
PhD-level research capabilities: literature review, multi-source investigation, critical analysis, hypothesis-driven exploration, quantitative/qualitative methods, and lateral thinking
Scientific writing, citations, grants, posters, and academic career (13 skills)
Strategic research thinking agents — idea evaluation, project triage, and structured brainstorming inspired by Carlini's research methodology
Production-grade academic research pipeline for Claude Code: research → write → review → revise → finalize. 4 skills, 27 modes, 39-agent ensemble, v3.7.3 + v3.8 L3 claim-faithfulness gate, v3.9.0 cross-index triangulation, v3.10 triangulation policy layer, v3.11 deterministic citation verification gate (#182).