/paper-figures
Extract figures from downloaded papers and include them in survey/review reports. Use when the report covers other groups' work and benefits from their architecture diagrams, experimental plots, or system schematics. Your brain prompt supplies the absolute path to the
$ npx -y skills add Muuuun/luxas --skill paper-figures --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/paper-figures
Context preview
The summary Claude sees to decide when to auto-load this skill.
Extract figures from downloaded papers and include them in survey/review reports. Use when the report covers other groups' work and benefits from their architecture diagrams, experimental plots, or system schematics. Your brain prompt supplies the absolute path to the
SKILL.md
paper-figures.SKILL.mdname: paper-figures
description: Extract figures from downloaded papers and include them in survey/review reports. Use when the report covers other groups' work and benefits from their architecture diagrams, experimental plots, or system schematics. Your brain prompt supplies the absolute path to the extract-figures script as {{EXTRACT_FIGURES}} — use that value wherever this skill writes `extract-figures`.Paper Figures Skill
Figures are information. A survey/review report covering downloaded papers MUST include key figures — architecture diagrams, experimental results, comparisons. Do NOT write a text-only survey when figures are available.
3-step workflow
Step 1 — Extract figures from downloaded papers
Your brain prompt supplies the script's absolute path as `{{EXTRACT_FIGURES}}`. Invoke it once per paper:
{{EXTRACT_FIGURES}} data/papers/<paper-id>.pdf # single PDF
{{EXTRACT_FIGURES}} data/papers/<arxiv-id> # arXiv source directoryThis creates `data/papers/<id>_figures/` with extracted images and a `manifest.json` listing each figure with caption and page number.
Step 2 — Review captions and classify every figure
Read every manifest:
cat data/papers/*_figures/manifest.json
Record your decisions in `notes/memory.md` under a `## Figure Review` section. Every figure must end up in one of three states:
- **USE** — essential for understanding the topic; will be included in the report
- **SKIP** — irrelevant, redundant, or low quality
- **UNREVIEWED** — caption not yet read (only acceptable as a transient state)
Select figures that are:
- Essential for understanding the topic (architecture diagrams, system schematics)
- Key experimental results that support your narrative
- Useful comparisons across methods, systems, or time periods
- Visually informative (not just tables rendered as images)
Step 3 — Include `USE` figures in the report
For each figure marked `USE`, embed it directly in LaTeX:
\begin{figure}[t]
\centering
\includegraphics[width=\linewidth]{../data/papers/<id>_figures/<filename>}
\caption{<Your caption describing the figure in the context of your survey>. Adapted from \cite{<key>}.}
\label{fig:<label>}
\end{figure}Rules
- **Coverage**: survey/review reports include at least 3-5 `USE` figures from downloaded papers, in addition to any figures you generate yourself.
- **Captions**: write your OWN caption in the context of the survey narrative — do not copy the original caption.
- **Attribution**: always cite the source paper with `\cite{}`.
- **No skipping the review step**: every extracted figure must be classified before writing the report.
- **Complementary**: you may also generate your own figures (see `skills/matplotlib-figures/SKILL.md`) for data summaries, timelines, or cross-paper comparisons not found in existing figures.
Read more
name: paper-figures
description: Extract figures from downloaded papers and include them in survey/review reports. Use when the report covers other groups' work and benefits from their architecture diagrams, experimental plots, or system schematics. Your brain prompt supplies the absolute path to the extract-figures script as {{EXTRACT_FIGURES}} — use that value wherever this skill writes `extract-figures`.Paper Figures Skill
Figures are information. A survey/review report covering downloaded papers MUST include key figures — architecture diagrams, experimental results, comparisons. Do NOT write a text-only survey when figures are available.
3-step workflow
Step 1 — Extract figures from downloaded papers
Your brain prompt supplies the script's absolute path as `{{EXTRACT_FIGURES}}`. Invoke it once per paper:
{{EXTRACT_FIGURES}} data/papers/<paper-id>.pdf # single PDF
{{EXTRACT_FIGURES}} data/papers/<arxiv-id> # arXiv source directoryThis creates `data/papers/<id>_figures/` with extracted images and a `manifest.json` listing each figure with caption and page number.
Step 2 — Review captions and classify every figure
Read every manifest:
cat data/papers/*_figures/manifest.json
Record your decisions in `notes/memory.md` under a `## Figure Review` section. Every figure must end up in one of three states:
- **USE** — essential for understanding the topic; will be included in the report
- **SKIP** — irrelevant, redundant, or low quality
- **UNREVIEWED** — caption not yet read (only acceptable as a transient state)
Select figures that are:
- Essential for understanding the topic (architecture diagrams, system schematics)
- Key experimental results that support your narrative
- Useful comparisons across methods, systems, or time periods
- Visually informative (not just tables rendered as images)
Step 3 — Include `USE` figures in the report
For each figure marked `USE`, embed it directly in LaTeX:
\begin{figure}[t]
\centering
\includegraphics[width=\linewidth]{../data/papers/<id>_figures/<filename>}
\caption{<Your caption describing the figure in the context of your survey>. Adapted from \cite{<key>}.}
\label{fig:<label>}
\end{figure}Rules
- **Coverage**: survey/review reports include at least 3-5 `USE` figures from downloaded papers, in addition to any figures you generate yourself.
- **Captions**: write your OWN caption in the context of the survey narrative — do not copy the original caption.
- **Attribution**: always cite the source paper with `\cite{}`.
- **No skipping the review step**: every extracted figure must be classified before writing the report.
- **Complementary**: you may also generate your own figures (see `skills/matplotlib-figures/SKILL.md`) for data summaries, timelines, or cross-paper comparisons not found in existing figures.
An autonomous research colleague — from a question to a compiled manuscript, while you sleep.
Repo: Muuuun/luxas
Other skills on luxas.
- /figure
Hybrid figure pipeline (Nano Banana raster + rembg background removal + TikZ vector assembly). Includes a TikZ template library covering quantum circuits (quantikz), Feynman diagrams (tikz-feynman), circuits (circuitikz), molecules (chemfig), 2D/3D plots (pgfplots), energy-level
Open skill - /matplotlib-figures
Publication-quality data plots via matplotlib with venue-specific styles. Use for generating your own figures (timelines, comparison charts, data summaries, heatmaps) that you add to the LaTeX report. Your brain prompt supplies the venue-specific style directory as
Open skill - /memory
Cross-project research memory. Deep-dive past projects' notes, record corrections, and save cross-project insights across all Luxas research projects.
Open skill - /narrative
Narrative discipline for research reports — article-type templates (empirical / feasibility / comparison / policy-zh) and the feedback revision protocol that keeps outline, prose, and figures coherent across many feedback rounds.
Open skill - /qec-construct
Verifier-in-the-loop CONSTRUCTION of quantum error-correcting codes with transversal non-Clifford gates (CCZ/T). Use when the task is to INVENT or improve a code/construction (not merely search a known family). Provides a sound, cheap algebraic verifier (qverify, "QEC's Lean")
Open skill - /review
Write domain-authentic review articles that synthesize rather than stack. Covers 10 scientific domains (physics, chemistry, biology, medicine, mathematics, computer_science, earth_environment, astronomy, economics, materials) with per-domain style guides mined from landmark
Open skill

