Analyze repositories, papers or drafts, and reference images into handoff-ready results. This skill does not write prompts or generate images.
Inspect the input first, then choose the path. Do not treat every URL as a repository: after opening the page or main text, determine whether it is a paper, a code repository, or an image.
When inspecting, look at these three things:
- Main text, sections, or LaTeX/Markdown structure → paper or draft
- Source code, README, dependencies, and entry scripts → repository
- The image itself, figure captions, or embedded figures in a PDF → reference image
Routing
Draft, outline, or full manuscript
Markdown, LaTeX, PDF main text, or the main text after a paper URL is opened, read references/paper.md, and produce Figure Plan v1.
- Notes, outlines, early drafts: plan only Figure 1 (Overall Framework); do not force in experimental figures.
- Full manuscript with experimental results: plan multiple figures according to the paper's claims.
- When the current environment cannot read a PDF or web page, report the limitation; do not fabricate section structure.
Repository
A local repository path, or a URL confirmed to be a code repository after opening, read references/repo.md, and produce Semantic Architecture Handoff v1. When the task or framework classification is uncertain, read references/keywords.md。
Paper plus repository
The paper and user intent determine the narrative and topology. The repository only verifies parameters, tensor dimensions, module names, and execution direction; it does not start a separate architecture.
Reference image
External style reference images, figures in a PDF, or images, read references/reference-figure.md, and produce ReferenceAnalysis v1.
- Use a PDF reader for the PDF main text and figure captions.
- Only run this when image candidates need to be extracted
scripts/extract_pdf_figures.py。 - This script only filters candidates by size; it is not a structure classifier. Keeping, discarding, or being uncertain is still determined by evidence.
When evidence is insufficient, read references/missing-info-policy.md. Mark missing items; do not invent modules, edges, or values.
Handoff
Fields and JSON shapes follow the definitions in the corresponding reference; the schema is not rewritten here:
- Semantic Architecture Handoff v1（
academic-figure/SemanticArchitecture@1）→references/repo.md - Figure Plan v1（
academic-figure/FigurePlan@1）→references/paper.md - ReferenceAnalysis v1（
academic-figure/ReferenceAnalysis@1）→references/reference-figure.md
When multiple inputs appear at the same time, follow each one's own reference, then merge according to 'the paper determines the narrative, the repository only verifies.' Do not change field names. Do not write labels, claims, or topology from reference images into a new method figure unless the user explicitly requests a faithful redraw.
Stop
Stop after the analysis results are delivered. When the user wants a prompt or an image, hand off to fig1-draw. Do not compile prompts or generate images in this skill.