A figure-making workflow that combines AI-rendered visual elements with TikZ, a code-based system for precise diagrams and labels. It supports figures such as plots, quantum circuits, electronic circuits, molecules, and scientific schematics.

Use it to create publication-quality scientific figures, including data plots, technical diagrams, and hybrid illustrations.

It separates textured or realistic artwork from exact symbols, equations, arrows, and layout.

figure — Skill for Claude Code by Muuuun/luxas

About the project

Luxas is an open-source multi-agent research system that takes a research topic through literature searches, experiments, reviews, and LaTeX manuscript compilation. It is intended for autonomous scientific research, using separate agents to read papers, run tests, create figures, and write reports. The catalogue lists skills associated with this workflow.

Muuuun/luxas · 1,169 stars · on GitHub · luxas.im

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add Muuuun/luxas --skill figure

Clone the repo

git clone --depth 1 https://github.com/Muuuun/luxas

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/muuuun/luxas/figure/github.svg)](https://agentmods.dev/skills/muuuun/luxas/figure)

Your own site

<a href="https://agentmods.dev/skills/muuuun/luxas/figure"><img src="https://agentmods.dev/badge/skills/muuuun/luxas/figure/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/muuuun/luxas/figure"><img src="https://agentmods.dev/badge/skills/muuuun/luxas/figure.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 104 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,146 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00104	$0.01146
Opus 5.5	$0.00042	$0.00458
Sonnet 5.5	$0.00021	$0.00229
Haiku 4.5	$0.00010	$0.00115

Measured 1mo ago against content hash 5670a4730ca4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

figure scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/hybrid_gen.py, scripts/sync_style_guides.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/figure/SKILL.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Figure Skill

Publication-quality figures via the hybrid pipeline: let Gemini (Nano Banana) render photorealistic / textured / 3D components, let TikZ own all symbols, arrows, labels, equations, and layout. You get the visual richness of AI rendering AND the precision of code.

When to use which backend

┌─────────────────────────────────────────────────────────────────┐
│  What are you drawing?                          │ Backend       │
├─────────────────────────────────────────────────┼───────────────┤
│  Data plot (lines, bars, heatmaps from data)    │ pgfplots      │
│  Quantum circuit (Hadamard, CNOT, measure)      │ quantikz      │
│  Feynman diagram                                │ feynman       │
│  Molecule / Lewis structure                     │ chemfig       │
│  Electronic circuit (op-amp, RLC)               │ circuitikz    │
│  Atomic energy levels + transitions             │ energy_levels │
│  Phase-space trajectory                         │ phase_space   │
│  Pulse sequence (NMR / qubit timing)            │ pulse_sequence│
│  Optical bench cartoon (2D, flat)               │ optical_setup │
│  Concept schematic with textured 3D objects     │ HYBRID        │
│    (Paul trap, cavity, apparatus, animal etc.)  │               │
└─────────────────────────────────────────────────────────────────┘

For HYBRID, pick raster components sparingly: only for textured / 3D / glossy objects where TikZ would take 50+ lines of patches. Everything else → TikZ.

The hybrid pipeline

1. decide which elements are raster (3D/textured/glossy) vs vector (everything else)
2. for each raster element:
     python skills/figure/scripts/hybrid_gen.py \
       --name <outName>  --prompt "<object spec>"  --style "<style suffix>" \
       --out assets/<outName>.png
   → generates isolated-object PNG on white bg, then rembg → transparent PNG
3. write figure_X.tex starting from skills/figure/templates/<best>.tex
     - \includegraphics{assets/<outName>.png} for raster slots
     - TikZ \draw \node for all labels, arrows, equations
4. compile:    pdflatex figure_X.tex
   preview:    pdftoppm -r 200 figure_X.pdf preview -png
5. Read preview-1.png (vision) → find issues → edit .tex → recompile (≤3 iters)
6. final output: figures/figure_X.{tex,pdf}

Read the full file on GitHub · 98 lines

Files

What ships with it

29 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

1mo ago First seen · 98 lines · 104 tokens per session scan A 5670a4730ca4

Subscribe to this mod's changes

figure is a skill published in the GitHub repository Muuuun/luxas (1,169 stars, last pushed 2d ago), licensed MIT. It adds 104 tokens to every session and 1,146 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Creative and media LaTeX Scientific agentic-ai autonomous-agent claude multi-agent-system research-agent

research-rigor

A structured method for doing research and analysis with explicit assumptions, evidence checks, scoring criteria, independent review, and later accuracy checks. The description is mainly in Chinese and does not define a specific software integration.

LiHongwei-cn/lihongwei-cn · 175 tokens

nature-academic-search

Multi-source literature search, citation verification, MeSH search strategy, citation file management (.nbib/.ris/.bib conversion), and reference management (BibTeX, related articles, ID conversion) via MCP tools (PubMed, CrossRef, arXiv). Use when the user needs coordinated multi-step literature workflows beyond a…

LiHongwei-cn/lihongwei-cn · 74 tokens

ml-paper-writing

Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use when drafting papers from research repos, structuring arguments, verifying citations, or preparing camera-ready submissions. Includes LaTeX templates, reviewer guidelines, and citation verification workflows.

raphaelmansuy/edgecrab · 65 tokens

neuroskill-bci

Connect to a running NeuroSkill instance and incorporate the user's real-time cognitive and emotional state (focus, relaxation, mood, cognitive load, drowsiness, heart rate, HRV, sleep staging, and 40+ derived EXG scores) into responses. Requires a BCI wearable (Muse 2/S or OpenBCI) and the NeuroSkill desktop app…

raphaelmansuy/edgecrab · 82 tokens

sparse-autoencoder-training

Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.

raphaelmansuy/edgecrab · 58 tokens

distributed-llm-pretraining-torchtitan

Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or custom models at scale from 8 to 512+ GPUs with Float8, torch.compile, and distributed checkpointing.

raphaelmansuy/edgecrab · 83 tokens