A research toolkit for Claude Code that carries a scientific question through to a compiled LaTeX manuscript, with skills for publication-quality figures, narrative structure for reports, cross-project research memory, and friction sheets for computational physics and quantum tools.
@muuuunFriction sheets for field-standard computational tools and simulators (frictions, smoke tests, how to measure a saved model).…
@muuuunHybrid figure pipeline (Nano Banana raster + rembg background removal + TikZ vector assembly). Includes a TikZ template library…
@muuuunPublication-quality data plots via matplotlib with venue-specific styles. Use for generating your own figures (timelines,…
@muuuunCross-project research memory. Deep-dive past projects' notes and record corrections across all Luxas research projects.
@muuuunNarrative discipline for research reports — article-type templates (empirical / feasibility / comparison / policy-zh) and the…
@muuuunExtract figures from downloaded papers and include them in survey/review reports. Use when the report covers other groups' work…
@muuuunVerifier-in-the-loop CONSTRUCTION of quantum error-correcting codes with transversal non-Clifford gates (CCZ/T). Applies whenever…
@muuuunWrite domain-authentic review articles that synthesize rather than stack. Covers 10 scientific domains (physics, chemistry,…
@muuuunUnified academic paper search, citation chains, paper download (arXiv LaTeX/PDF, Sci-Hub), figure extraction from papers, LaTeX…
@muuuunPlan-time methodology contract for survey/review/report projects. Forces an audit-grade survey instead of a paper-trust summary.…
@muuuunVenue-specific formatting requirements for academic journals and conferences across all disciplines. Covers Nature, Science,…
@muuuunThe main research brain. Reads RESEARCH.md, surveys literature, decomposes the goal into experiments, delegates each to an…
@muuuunPre-finish contradiction sweep across the evidence store and the report. Extracts named physical quantities (same quantity, same…
@muuuunResearch experiment orchestrator. Receives a task from brain, designs what tools/computations the answer needs, spawns impl +…
@muuuunAdversarial per-experiment reviewer. Auto-spawned by the harness after an experiment agent completes. Reads the L2 section…
@muuuunReads rendered figures with a vision model that can actually see, AFTER the deterministic lint has run, and reports what a…
@muuuunLightweight LaTeX compile-error fixer. Uses haiku for fast, mechanical error diagnosis and single-edit fixes. The brain should…
@muuuunVisual designer with ZERO domain expertise. Two task patterns, inferred from the task text: (a) audit existing figures for style…
@muuuunMakes ONE figure from ONE brief. Data figures are figspec JSON (rendered by `figspec`), energy-level diagrams are levelspec JSON…
@muuuunSingle-pass writer that turns an experiment's computed facts (results.json + acceptance criterion + limitations) into the L2…
@muuuunMathematical derivation agent using OpenAI's flagship reasoning model (o3). Derives formulas, performs symbolic calculations,…
@muuuunSidecar research monitor. Runs as its own short-lived process next to a live (or paused) `luxas run`, driven from the studio's…
@muuuunPre-finish prior-art positioning for the report's contribution claims. Receives ONLY the contribution sentences (not brain's…
@muuuunIs this you? Claim your profilePut a plugin at the top of Plugins, from $9
