Academic Draft and Paper Analyzer (Figure Planner)

Produce a human-readable figure strategy and a machine-readable Figure Plan v1. Plan figures around the paper's claims and reader questions, not around a fixed count or a generic pipeline template.

Read references/missing-info-policy.md when the paper is incomplete. If a repository handoff or extracted reference-style profile exists, carry it forward without renaming fields.

Dual-Track Planning Workflow

The analyzer operates in one of two modes depending on the input:

1. Draft-to-Figure Fast-Track (草稿敏捷直出):
   • Trigger: Input is notes, an outline, or an early draft (Markdown, text, or draft sections) without complete experimental/analysis results.
   • Target: Focus exclusively on Figure 1: Overall Framework / Methodology Overview.
   • Policy: Do NOT force a multi-figure plan (ablation/data behavior). Do NOT warn about missing experimental/analysis sections.
2. Camera-Ready Multi-Figure Plan (完整定稿多图规划):
   • Trigger: Input is a complete manuscript with experimental results (Markdown, LaTeX, PDF, or full text).
   • Target: Systematically plan the multi-figure suite with claim verification and publication constraints.

Input contract