Paper Illustration Image2

Generate publication-quality paper figures using Claude as the planner/reviewer and a local Codex app-server MCP bridge as the raster renderer.

Core Design Philosophy

┌──────────────────────────────────────────────────────────────────────────┐
│                    MULTI-STAGE ITERATIVE WORKFLOW                        │
├──────────────────────────────────────────────────────────────────────────┤
│                                                                          │
│   User Request                                                           │
│       │                                                                  │
│       ▼                                                                  │
│   ┌─────────────┐                                                        │
│   │   Claude    │ ◄─── Step 1: Parse request, create initial prompt     │
│   │  (Planner)  │      - Extract components, labels, and data flow       │
│   │             │      - Write a paper-ready figure brief                │
│   └──────┬──────┘                                                        │
│          │                                                               │
│          ▼                                                               │
│   ┌─────────────┐                                                        │
│   │Claude/Codex │ ◄─── Step 2: Optimize layout description               │
│   │   Layout    │      - Refine component positioning                    │
│   │   Review    │      - Optimize spacing and grouping                   │
│   └──────┬──────┘                                                        │
│          │                                                               │
│          ▼                                                               │
│   ┌─────────────┐                                                        │
│   │Claude/Codex │ ◄─── Step 3: CVPR/NeurIPS style verification           │
│   │   Style     │      - Check palette, arrows, and label standards      │
│   │   Check     │      - Tighten the prompt before rendering             │
│   └──────┬──────┘                                                        │
│          │                                                               │
│          ▼                                                               │
│   ┌─────────────┐                                                        │
│   │ codex-image2│ ◄─── Step 4: Native image generation via bridge        │
│   │ MCP bridge  │      - Call generate_start / generate_status           │
│   │ + app-server│      - Accept only native imageGeneration output       │
│   └──────┬──────┘                                                        │
│          │                                                               │
│          ▼                                                               │
│   ┌─────────────┐                                                        │
│   │   Claude    │ ◄─── Step 5: STRICT visual review + SCORE (1-10)      │
│   │  (Reviewer) │      - Verify logic, labels, arrows, and aesthetics    │
│   │   STRICT!   │      - Reject unclear or non-paper-ready figures       │
│   └──────┬──────┘                                                        │
│          │                                                               │
│          ▼                                                               │
│   Score ≥ 9? ──YES──► Accept & Output                                    │
│          │                                                               │
│          NO                                                              │
│          │                                                               │
│          ▼                                                               │
│   Generate SPECIFIC improvement feedback ──► Loop back to Step 2        │
│                                                                          │
└──────────────────────────────────────────────────────────────────────────┘

Constants

• RENDERER = codex-image2 — Native image generation bridge exposed through local Codex app-server

• OPTIONAL_TEXT_CRITIC = mcp__codex__codex — Optional text-only second opinion for layout/style checks

• MAX_ITERATIONS = 5 — Maximum refinement rounds

• TARGET_SCORE = 9 — Minimum acceptable score (1-10)

• OUTPUT_DIR = figures/ai_generated/ — Output directory

• TEXT_LANGUAGE = English — Default figure text language unless the user requests otherwise

• NATIVE_IMAGE_REQUIREMENT = strict — Accept only native imageGeneration output; reject shell/Python fallbacks

• IMAGE2_HELPER — canonical name paper_illustration_image2.py, resolved per shared-references/integration-contract.md §2 (Policy A — skill-local gate). Phase 3.2 (Arch C) moved the canonical implementation into skills/paper-illustration-image2/scripts/; tools/paper_illustration_image2.py remains as an os.execv shim so legacy resolver layers keep working without a re-install. Resolve via:

  # Layer 0: self-contained (CC 1.0+ exposes $CLAUDE_SKILL_DIR).
  IMAGE2_HELPER=""
  if [ -n "${CLAUDE_SKILL_DIR:-}" ] && [ -f "$CLAUDE_SKILL_DIR/scripts/paper_illustration_image2.py" ]; then
    IMAGE2_HELPER="$CLAUDE_SKILL_DIR/scripts/paper_illustration_image2.py"
  fi
  # Layers 1-3: shared-runtime chain via shim at tools/paper_illustration_image2.py.
  if [ -z "$IMAGE2_HELPER" ]; then
    cd "$(git rev-parse --show-toplevel 2>/dev/null || pwd)" || exit 1
    if [ -z "${ARIS_REPO:-}" ] && [ -f .aris/installed-skills.txt ]; then
        ARIS_REPO=$(awk -F'\t' '$1=="repo_root"{print $2; exit}' .aris/installed-skills.txt 2>/dev/null) || true
    fi
    IMAGE2_HELPER=".aris/tools/paper_illustration_image2.py"
    [ -f "$IMAGE2_HELPER" ] || IMAGE2_HELPER="tools/paper_illustration_image2.py"
    [ -f "$IMAGE2_HELPER" ] || { [ -n "${ARIS_REPO:-}" ] && IMAGE2_HELPER="$ARIS_REPO/tools/paper_illustration_image2.py"; }
    [ -f "$IMAGE2_HELPER" ] || IMAGE2_HELPER=""
  fi
  [ -z "$IMAGE2_HELPER" ] && {
    echo "ERROR: paper_illustration_image2.py not resolved (layer 0: \$CLAUDE_SKILL_DIR/scripts/; layers 1-3: .aris/tools/, tools/, \$ARIS_REPO/tools/)." >&2
    echo "       /paper-illustration-image2 cannot proceed. Fix: rerun bash tools/install_aris.sh, or copy the canonical script from \$ARIS_REPO/skills/paper-illustration-image2/scripts/." >&2
    exit 1
  }
  

  All invocations below use python3 "$IMAGE2_HELPER" <subcommand>.

CVPR/ICLR/NeurIPS Top-Tier Conference Style Guide

What "CVPR Style" Actually Means:

Visual Standards

• Clean white background — No decorative patterns or gradients unless extremely subtle
• Sans-serif fonts — Arial, Helvetica, or similarly clean paper-friendly typography
• Subtle color palette — Use 3-5 coordinated colors, not rainbow colors
• Print-friendly — Must remain understandable in grayscale
• Professional borders — Thin to medium, clean, and consistent

Layout Standards

• Horizontal flow — Left-to-right is the default for pipelines
• Clear grouping — Use spacing or subtle grouping boxes for related modules
• Consistent sizing — Similar components should have similar sizes
• Balanced whitespace — Avoid both cramped and overly sparse layouts

Arrow Standards (MOST CRITICAL)

• Thick strokes — Arrows must remain visible after paper scaling
• Clear arrowheads — Large, unmistakable arrowheads
• Dark colors — Prefer black or dark gray arrows
• Labeled — Important arrows should show what flows through them
• No crossings — Reorganize the figure to avoid crossings where possible
• CORRECT DIRECTION — Arrows must point to the right target

Visual Appeal (Academic Professional Style)

目标：既不保守也不花哨，找到平衡点

✅ Should have

• Subtle gradients — Gentle same-family gradients are a