dsh-aris-panel 0.1.0

package/skills/skills-codex-claude-review/paper-figure/SKILL.md

@@ -0,0 +1,319 @@
+---
+name: "paper-figure"
+description: "Generate publication-quality figures and tables from experiment results. Use when user says \"画图\", \"作图\", \"generate figures\", \"paper figures\", or needs plots for a paper."
+---
+
+> Override for Codex users who want **Claude Code**, not a second Codex agent, to act as the reviewer. Install this package **after** `skills/skills-codex/*`.
+>
+> This reviewer is a different model family from the Codex executor. Every overlay trace/audit records:
+>
+> ```yaml
+> review_independence: cross-family
+> acceptance_status: accepted
+> ```
+
+# Paper Figure: Publication-Quality Plots from Experiment Data
+
+Generate all figures and tables for a paper based on: **$ARGUMENTS**
+
+## Scope: What This Skill Can and Cannot Do
+
+| Category | Can auto-generate? | Examples |
+|----------|-------------------|----------|
+| **Data-driven plots** | ✅ Yes | Line plots (training curves), bar charts (method comparison), scatter plots, heatmaps, box/violin plots |
+| **Comparison tables** | ✅ Yes | LaTeX tables comparing prior bounds, method features, ablation results |
+| **Multi-panel figures** | ✅ Yes | Subfigure grids combining multiple plots (e.g., 3×3 dataset × method) |
+| **Architecture/pipeline diagrams** | ❌ No — manual | Model architecture, data flow diagrams, system overviews. At best can generate a rough TikZ skeleton, but **expect to draw these yourself** using tools like draw.io, Figma, or TikZ |
+| **Generated image grids** | ❌ No — manual | Grids of generated samples (e.g., GAN/diffusion outputs). These come from running your model, not from this skill |
+| **Photographs / screenshots** | ❌ No — manual | Real-world images, UI screenshots, qualitative examples |
+
+**In practice:** For a typical ML paper, this skill handles ~60% of figures (all data plots + tables). The remaining ~40% (hero figure, architecture diagram, qualitative results) need to be created manually and placed in `figures/` before running `/paper-write`. The skill will detect these as "existing figures" and preserve them.
+
+## Constants
+
+- **STYLE = `publication`** — Visual style preset. Options: `publication` (default, clean for print), `poster` (larger fonts), `slide` (bold colors)
+- **DPI = 300** — Output resolution
+- **FORMAT = `pdf`** — Output format. Options: `pdf` (vector, best for LaTeX), `png` (raster fallback)
+- **COLOR_PALETTE = `tab10`** — Default matplotlib color cycle. Options: `tab10`, `Set2`, `colorblind` (deuteranopia-safe)
+- **FONT_SIZE = 10** — Base font size (matches typical conference body text)
+- **FIG_DIR = `figures/`** — Output directory for generated figures
+- **REVIEWER_MODEL = `claude-review`** — Claude reviewer invoked through the local `claude-review` MCP bridge. Set `CLAUDE_REVIEW_MODEL` if you need a specific Claude model override.
+
+## Inputs
+
+1. **PAPER_PLAN.md** — figure plan table (from `/paper-plan`)
+2. **Experiment data** — JSON files, CSV files, or screen logs in `figures/` or project root
+3. **Existing figures** — any manually created figures to preserve
+
+If no PAPER_PLAN.md exists, scan for data files and ask the user which figures to generate.
+
+## Workflow
+
+### Step 1: Read Figure Plan
+
+Parse the Figure Plan table from PAPER_PLAN.md:
+
+```markdown
+| ID | Type | Description | Data Source | Priority |
+|----|------|-------------|-------------|----------|
+| Fig 1 | Architecture | ... | manual | HIGH |
+| Fig 2 | Line plot | ... | figures/exp.json | HIGH |
+```
+
+Identify:
+- Which figures can be auto-generated from data
+- Which need manual creation (architecture diagrams, etc.)
+- Which are comparison tables (generate as LaTeX)
+
+### Step 2: Set Up Plotting Environment
+
+Create a shared style configuration script:
+
+```python
+# paper_plot_style.py — shared across all figure scripts
+import matplotlib.pyplot as plt
+import matplotlib
+matplotlib.rcParams.update({
+    'font.size': FONT_SIZE,
+    'font.family': 'serif',
+    'font.serif': ['Times New Roman', 'Times', 'DejaVu Serif'],
+    'axes.labelsize': FONT_SIZE,
+    'axes.titlesize': FONT_SIZE + 1,
+    'xtick.labelsize': FONT_SIZE - 1,
+    'ytick.labelsize': FONT_SIZE - 1,
+    'legend.fontsize': FONT_SIZE - 1,
+    'figure.dpi': DPI,
+    'savefig.dpi': DPI,
+    'savefig.bbox': 'tight',
+    'savefig.pad_inches': 0.05,
+    'axes.grid': False,
+    'axes.spines.top': False,
+    'axes.spines.right': False,
+    'text.usetex': False,  # set True if LaTeX is available
+    'mathtext.fontset': 'stix',
+})
+
+# Color palette
+COLORS = plt.cm.tab10.colors  # or Set2, or colorblind-safe
+
+def save_fig(fig, name, fmt=FORMAT):
+    """Save figure to FIG_DIR with consistent naming."""
+    fig.savefig(f'{FIG_DIR}/{name}.{fmt}')
+    print(f'Saved: {FIG_DIR}/{name}.{fmt}')
+```
+
+### Step 3: Auto-Select Figure Type
+
+Use this decision tree for data-driven figures (inspired by Imbad0202/academic-research-skills):
+
+| Data Pattern | Recommended Type | Size |
+|-------------|-----------------|------|
+| X=time/steps, Y=metric | Line plot | 0.48\textwidth |
+| Methods × 1 metric | Bar chart | 0.48\textwidth |
+| Methods × multiple metrics | Grouped bar / radar | 0.95\textwidth |
+| Two continuous variables | Scatter plot | 0.48\textwidth |
+| Matrix / grid values | Heatmap | 0.48\textwidth |
+| Distribution comparison | Box/violin plot | 0.48\textwidth |
+| Multi-dataset results | Multi-panel (subfigure) | 0.95\textwidth |
+| Prior work comparison | LaTeX table | — |
+
+### Step 4: Generate Each Figure
+
+For each figure in the plan, create a standalone Python script:
+
+**Line plots** (training curves, scaling):
+```python
+# gen_fig2_training_curves.py
+from paper_plot_style import *
+import json
+
+with open('figures/exp_results.json') as f:
+    data = json.load(f)
+
+fig, ax = plt.subplots(1, 1, figsize=(5, 3.5))
+ax.plot(data['steps'], data['fac_loss'], label='Factorized', color=COLORS[0])
+ax.plot(data['steps'], data['crf_loss'], label='CRF-LR', color=COLORS[1])
+ax.set_xlabel('Training Steps')
+ax.set_ylabel('Cross-Entropy Loss')
+ax.legend(frameon=False)
+save_fig(fig, 'fig2_training_curves')
+```
+
+**Bar charts** (comparison, ablation):
+```python
+fig, ax = plt.subplots(1, 1, figsize=(5, 3))
+methods = ['Baseline', 'Method A', 'Method B', 'Ours']
+values = [82.3, 85.1, 86.7, 89.2]
+bars = ax.bar(methods, values, color=[COLORS[i] for i in range(len(methods))])
+ax.set_ylabel('Accuracy (%)')
+# Add value labels on bars
+for bar, val in zip(bars, values):
+    ax.text(bar.get_x() + bar.get_width()/2, bar.get_height() + 0.3,
+            f'{val:.1f}', ha='center', va='bottom', fontsize=FONT_SIZE-1)
+save_fig(fig, 'fig3_comparison')
+```
+
+**Comparison tables** (LaTeX, for theory papers):
+```latex
+\begin{table}[t]
+\centering
+\caption{Comparison of estimation error bounds. $n$: sample size, $D$: ambient dim, $d$: latent dim, $K$: subspaces, $n_k$: modes.}
+\label{tab:bounds}
+\begin{tabular}{lccc}
+\toprule
+Method & Rate & Depends on $D$? & Multi-modal? \\
+\midrule
+\citet{MinimaxOkoAS23} & $n^{-s'/D}$ & Yes (curse) & No \\
+\citet{ScoreMatchingdistributionrecovery} & $n^{-2/d}$ & No & No \\
+\textbf{Ours} & $\sqrt{\sum n_k d_k / n}$ & No & Yes \\
+\bottomrule
+\end{tabular}
+\end{table}
+```
+
+**Architecture/pipeline diagrams** (MANUAL — outside this skill's scope):
+- These require manual creation using draw.io, Figma, Keynote, or TikZ
+- This skill can generate a rough TikZ skeleton as a starting point, but **do not expect publication-quality results**
+- If the figure already exists in `figures/`, preserve it and generate only the LaTeX `\includegraphics` snippet
+- Flag as `[MANUAL]` in the figure plan and `latex_includes.tex`
+
+### Step 5: Run All Scripts
+
+```bash
+# Run all figure generation scripts
+for script in gen_fig*.py; do
+    python "$script"
+done
+```
+
+Verify all output files exist and are non-empty. Then **render-then-verify**:
+re-open each RENDERED PDF/PNG (not the script) and self-check — no clipped
+labels, no legend covering data, every number/label readable at final print
+size. This self-check happens BEFORE the Step 7 review, so the reviewer's
+budget goes to substance, not to catching clipped axes.
+
+### Step 6: Generate LaTeX Include Snippets
+
+For each figure, output the LaTeX code to include it:
+
+```latex
+% === Fig 2: Training Curves ===
+\begin{figure}[t]
+    \centering
+    \includegraphics[width=0.48\textwidth]{figures/fig2_training_curves.pdf}
+    \caption{Training curves comparing factorized and CRF-LR denoising.}
+    \label{fig:training_curves}
+\end{figure}
+```
+
+Save all snippets to `figures/latex_includes.tex` for easy copy-paste into the paper.
+
+### Step 7: Figure Quality Review with REVIEWER_MODEL
+
+Send figure descriptions and captions to Claude for review:
+
+```
+mcp__claude-review__review_start:
+  prompt: |
+    Review these figure/table plans for a [VENUE] submission.
+
+    For each figure:
+    1. Is the caption informative and self-contained?
+    2. Does the figure type match the data being shown?
+    3. Is the comparison fair and clear?
+    4. Any missing baselines or ablations?
+    5. Would a different visualization be more effective?
+
+    [list all figures with captions and descriptions]
+```
+
+After this start call, immediately save the returned `jobId` and poll `mcp__claude-review__review_status` with a bounded `waitSeconds` until `done=true`. Treat the completed status payload's `response` as the reviewer output, and save the completed `threadId` for any follow-up round.
+
+### Step 8: Quality Checklist
+
+The checklist is PARTITIONED (pattern from Anthropic's Claude Science
+`figure-style` skill, Apache-2.0): **correctness rules always bind** — they are
+about whether the figure tells the truth, have no aesthetic content, and no
+style choice may override them; **guidance rules are defaults** — they produce
+a clean result, but a deliberate, stated alternative may override them.
+
+**Correctness — always binds, verify against the DATA before the render:**
+
+- [ ] **Excluded data never enters summaries** — a row excluded/flagged in the
+      source either disappears entirely or is drawn visibly distinct (open /
+      hatched marker, named in the key); it never feeds a mean/CI plotted
+      alongside included rows
+- [ ] **Captions and any claim-like title text are tested against EVERY plotted
+      row** — if one category contradicts the claim, qualify it ("on 3 of 4
+      benchmarks") or downgrade to a description; a figure that overclaims is
+      wrong even if it renders beautifully
+- [ ] **Comparable conditions only** — arms measured under different N / budget
+      / protocol are not drawn as visual peers; separate them or mark the
+      difference in the caption
+- [ ] **State n and what was held fixed** — every panel with a summary mark
+      says n and the unit of replication (panel or caption)
+- [ ] **Render-then-verify** — the Step-5 self-check on the RENDERED PDF/PNG
+      (not the script) actually happened: no clipped labels, no legend covering
+      data, every number/label readable at final print size
+
+**Guidance — strong defaults (from pedrohcgs/claude-code-my-workflow), a
+deliberate stated alternative may override — EXCEPT items that Key Rules below
+make hard (vector-PDF output and no-titles-inside-figures are Key Rules: treat
+those two as binding, not overridable):**
+
+- [ ] Font size readable at printed paper size (not too small)
+- [ ] Colors distinguishable in grayscale (print-friendly)
+- [ ] **No title inside figures** — titles go only in LaTeX `\caption{}` (from pedrohcgs)
+- [ ] Legend does not overlap data
+- [ ] Axis labels have units where applicable
+- [ ] Axis labels are publication-quality (not variable names like `emp_rate`)
+- [ ] Figure width fits single column (0.48\textwidth) or full width (0.95\textwidth)
+- [ ] PDF output is vector (not rasterized text)
+- [ ] No matplotlib default title (remove `plt.title` for publications)
+- [ ] Serif font matches paper body text (Times / Computer Modern)
+- [ ] Colorblind-accessible (if using colorblind palette)
+
+## Output
+
+```
+figures/
+├── paper_plot_style.py          # shared style config
+├── gen_fig1_architecture.py     # per-figure scripts
+├── gen_fig2_training_curves.py
+├── gen_fig3_comparison.py
+├── fig1_architecture.pdf        # generated figures
+├── fig2_training_curves.pdf
+├── fig3_comparison.pdf
+├── latex_includes.tex           # LaTeX snippets for all figures
+└── TABLE_*.tex                  # standalone table LaTeX files
+```
+
+## Key Rules
+
+- **Every figure must be reproducible** — save the generation script alongside the output
+- **Do NOT hardcode data** — always read from JSON/CSV files
+- **Use vector format (PDF)** for all plots — PNG only as fallback
+- **No decorative elements** — no background colors, no 3D effects, no chart junk
+- **Consistent style across all figures** — same fonts, colors, line widths
+- **Colorblind-safe** — verify with https://davidmathlogic.com/colorblind/ if needed
+- **One script per figure** — easy to re-run individual figures when data changes
+- **No titles inside figures** — captions are in LaTeX only
+- **Comparison tables count as figures** — generate them as standalone .tex files
+
+## Figure Type Reference
+
+| Type | When to Use | Typical Size |
+|------|------------|--------------|
+| Line plot | Training curves, scaling trends | 0.48\textwidth |
+| Bar chart | Method comparison, ablation | 0.48\textwidth |
+| Grouped bar | Multi-metric comparison | 0.95\textwidth |
+| Scatter plot | Correlation analysis | 0.48\textwidth |
+| Heatmap | Attention, confusion matrix | 0.48\textwidth |
+| Box/violin | Distribution comparison | 0.48\textwidth |
+| Architecture | System overview | 0.95\textwidth |
+| Multi-panel | Combined results (subfigures) | 0.95\textwidth |
+| Comparison table | Prior bounds vs. ours (theory) | full width |
+
+## Acknowledgements
+
+Design pattern (type × style matrix) inspired by [baoyu-skills](https://github.com/jimliu/baoyu-skills). Publication style defaults and figure rules from [pedrohcgs/claude-code-my-workflow](https://github.com/pedrohcgs/claude-code-my-workflow). Visualization decision tree from [Imbad0202/academic-research-skills](https://github.com/Imbad0202/academic-research-skills).

package/skills/skills-codex-claude-review/paper-plan/SKILL.md

@@ -0,0 +1,287 @@
+---
+name: "paper-plan"
+description: "Generate a structured paper outline from review conclusions and experiment results. Use when user says \"写大纲\", \"paper outline\", \"plan the paper\", \"论文规划\", or wants to create a paper plan before writing."
+---
+
+> Override for Codex users who want **Claude Code**, not a second Codex agent, to act as the reviewer. Install this package **after** `skills/skills-codex/*`.
+>
+> This reviewer is a different model family from the Codex executor. Every overlay trace/audit records:
+>
+> ```yaml
+> review_independence: cross-family
+> acceptance_status: accepted
+> ```
+
+# Paper Plan: From Review Conclusions to Paper Outline
+
+Generate a structured, section-by-section paper outline from: **$ARGUMENTS**
+
+## Constants
+
+- **REVIEWER_MODEL = `claude-review`** — Claude reviewer invoked through the local `claude-review` MCP bridge. Set `CLAUDE_REVIEW_MODEL` if you need a specific Claude model override.
+- **TARGET_VENUE = `ICLR`** — Default venue. User can override (e.g., `/paper-plan "topic" — venue: NeurIPS`). Supported: `ICLR`, `NeurIPS`, `ICML`, `CVPR`, `ACL`, `AAAI`, `ACM`, `IEEE_JOURNAL` (IEEE Transactions / Letters), `IEEE_CONF` (IEEE conferences).
+- **MAX_PAGES** — Page limit. For ML conferences: main body to Conclusion end (excluding references, appendix). ICLR=9, NeurIPS=9, ICML=8, AAAI=7 technical-content pages plus references unless the current AAAI CFP says otherwise. **For IEEE venues: references ARE included in page count.** IEEE journal Transactions ≈ 12-14 pages total, Letters ≈ 4-5 pages total; IEEE conference ≈ 5-8 pages total (including references).
+
+## Inputs
+
+The skill expects one or more of these in the project directory:
+
+1. **NARRATIVE_REPORT.md** or **STORY.md** — research narrative with claims and evidence
+2. **review-stage/AUTO_REVIEW.md** — auto-review loop conclusions *(fall back to `./AUTO_REVIEW.md` if not found)*
+3. **Experiment results** — JSON files in `figures/`, screen logs, tables
+4. **idea-stage/IDEA_REPORT.md** — from idea-discovery pipeline (if applicable) *(fall back to `./IDEA_REPORT.md` if not found)*
+5. **CLAIMS_FROM_RESULTS.md** — structured claim judgment from `/result-to-claim` (preferred if available)
+
+If none exist, ask the user to describe the paper's contribution in 3-5 sentences.
+
+## Orchestra-Guided Writing Overlay
+
+Keep the existing workflow and outputs, but use the shared references below to improve the quality of the story and outline:
+
+- Read `../shared-references/writing-principles.md` when framing the Abstract, Introduction, Related Work, or hero figure
+- Read `../shared-references/venue-checklists.md` before freezing the outline for a specific venue
+- Load these references only when they help; they are support material, not a new workflow phase
+
+## Workflow
+
+### Step 1: Extract Claims and Evidence
+
+**First check for `CLAIMS_FROM_RESULTS.md`** — if its first line is `verdict: REVIEW_UNAVAILABLE`, treat the file as ABSENT for claim extraction (fall through to the narrative documents below) and then: under `— assurance: submission` (`shared-references/assurance-contract.md`; implied by `— effort: max|beast`) STOP — the claims were never adjudicated, rerun `/result-to-claim` first; under `assurance: draft` continue but tag every claim `[unadjudicated]`. Otherwise, if it exists, use it as the starting point for claims and merge it with any additional evidence from the narrative documents below.
+
+Read all available narrative documents and extract:
+
+1. **Core claims** (3-5 main contributions)
+2. **Evidence** for each claim (which experiments, which metrics, which figures)
+3. **Known weaknesses** (from reviewer feedback)
+4. **Suggested framing** (from review conclusions)
+
+Build a **Claims-Evidence Matrix**:
+
+```markdown
+| Claim | Evidence | Status | Section |
+|-------|----------|--------|---------|
+| [claim 1] | [exp A, metric B] | Supported | §3.2 |
+| [claim 2] | [exp C] | Partially supported | §4.1 |
+```
+
+### Step 2: Determine Paper Type and Structure
+
+Based on TARGET_VENUE and paper content, classify and select structure.
+
+Before committing to a structure, apply the narrative principle from `../shared-references/writing-principles.md`:
+
+- The paper should tell one coherent technical story
+- By the end of the Introduction, the outline should make the **What**, **Why**, and **So What** explicit
+- Front-load the most important material: title, abstract, introduction, and hero figure
+
+**IMPORTANT**: The section count is FLEXIBLE (5-8 sections). Choose what fits the content best. The templates below are starting points, not rigid constraints.
+
+**Empirical/Diagnostic paper:**
+```
+1. Introduction (1.5 pages)
+2. Related Work (1 page)
+3. Method / Setup (1.5 pages)
+4. Experiments (3 pages)
+5. Analysis / Discussion (1 page)
+6. Conclusion (0.5 pages)
+```
+
+**Theory + Experiments paper:**
+```
+1. Introduction (1.5 pages)
+2. Related Work (1 page)
+3. Preliminaries & Modeling (1.5 pages)
+4. Experiments (1.5 pages)
+5. Theory Part A (1.5 pages)
+6. Theory Part B (1.5 pages)
+7. Conclusion (0.5 pages)
+— Total: 9 pages
+```
+Theory papers often need 7 sections (splitting theory into estimation + optimization, or setup + analysis). The total page budget MUST sum to MAX_PAGES.
+
+Theory papers should:
+- Include **proof sketch** locations (not just theorem statements)
+- Plan a **comparison table** of prior theoretical bounds vs. this paper's bounds
+- Identify which proofs go in appendix vs. main body
+
+**Method paper:**
+```
+1. Introduction (1.5 pages)
+2. Related Work (1 page)
+3. Method (2 pages)
+4. Experiments (2.5 pages)
+5. Ablation / Analysis (1 page)
+6. Conclusion (0.5 pages)
+```
+
+### Step 3: Section-by-Section Planning
+
+For each section, specify:
+
+```markdown
+### §0 Abstract
+- **One-sentence problem**: [what gap this paper addresses]
+- **Approach**: [what we do, in one sentence]
+- **Key result**: [most compelling quantitative finding]
+- **Implication**: [why it matters]
+- **Estimated length**: 150-250 words
+- **Self-contained check**: can a reader understand this without the paper?
+
+### §1 Introduction
+- **Opening hook**: [1-2 sentences that motivate the problem]
+- **Gap**: [what's missing in prior work]
+- **Key questions**: [the research questions this paper answers]
+- **Contributions**: [numbered list, matching Claims-Evidence Matrix]
+- **Hero figure**: [describe what Figure 1 should show — MUST include clear comparison if applicable]
+- **Estimated length**: 1.5 pages
+- **Key citations**: [3-5 papers to cite here]
+
+### §2 Related Work
+- **Subtopics**: [2-4 categories of related work]
+- **Positioning**: [how this paper differs from each category]
+- **Minimum length**: 1 full page (at least 3-4 paragraphs with substantive synthesis)
+- **Must NOT be just a list** — synthesize, compare, and position
+
+### §3 Method / Setup / Preliminaries
+- **Notation**: [key symbols and their meanings]
+- **Problem formulation**: [formal setup]
+- **Method description**: [algorithm, model, or experimental design]
+- **Formal statements**: [theorems, propositions if applicable]
+- **Proof sketch locations**: [which key steps appear here vs. appendix]
+- **Estimated length**: 1.5-2 pages
+
+### §4 Experiments / Main Results
+- **Figures planned**:
+  - Fig 1: [description, type: bar/line/table/architecture, WHAT COMPARISON it shows]
+  - Fig 2: [description]
+  - Table 1: [what it shows, which methods/baselines compared]
+- **Data source**: [which JSON files / experiment results]
+
+### §5 Conclusion
+- **Restatement**: [contributions rephrased, not copy-pasted from intro]
+- **Limitations**: [honest assessment — reviewers value this]
+- **Future work**: [1-2 concrete directions]
+- **Estimated length**: 0.5 pages
+```
+
+### Step 4: Figure Plan
+
+List every figure and table:
+
+```markdown
+## Figure Plan
+
+| ID | Type | Description | Data Source | Priority |
+|----|------|-------------|-------------|----------|
+| Fig 1 | Hero/Architecture | System overview + comparison | manual | HIGH |
+| Fig 2 | Line plot | Training curves comparison | figures/exp_A.json | HIGH |
+| Fig 3 | Bar chart | Ablation results | figures/ablation.json | MEDIUM |
+| Table 1 | Comparison table | Main results vs. baselines | figures/main_results.json | HIGH |
+| Table 2 | Theory comparison | Prior bounds vs. ours | manual | HIGH (theory papers) |
+```
+
+**CRITICAL for Figure 1 / Hero Figure**: Describe in detail what the figure should contain, including:
+- Which methods are being compared
+- What the visual difference should demonstrate
+- Caption draft that clearly states the comparison
+
+### Step 5: Citation Scaffolding
+
+For each section, list required citations:
+
+```markdown
+## Citation Plan
+- §1 Intro: [paper1], [paper2], [paper3] (problem motivation)
+- §2 Related: [paper4]-[paper10] (categorized by subtopic)
+- §3 Method: [paper11] (baseline), [paper12] (technique we build on)
+```
+
+**Citation rules** (from claude-scholar + Imbad0202/academic-research-skills):
+1. NEVER generate BibTeX from memory — always verify via search or existing .bib files
+2. Every citation must be verified: correct authors, year, venue
+3. Flag any citation you're unsure about with `[VERIFY]`
+4. Prefer published versions over arXiv preprints when available
+
+### Step 6: Cross-Review with REVIEWER_MODEL
+
+Send the complete outline to Claude review for feedback:
+
+```
+mcp__claude-review__review_start:
+  prompt: |
+    Review this paper outline for a [VENUE] submission.
+    [full outline including Claims-Evidence Matrix]
+
+    Score 1-10 on:
+    1. Logical flow — does the story build naturally?
+    2. Claim-evidence alignment — every claim backed?
+    3. Missing experiments or analysis
+    4. Positioning relative to prior work
+    5. Page budget feasibility (MAX_PAGES = main body to Conclusion end, excluding refs/appendix)
+
+    For each weakness, suggest the MINIMUM fix.
+    Be specific and actionable — "add X" not "consider more experiments".
+```
+
+After this start call, immediately save the returned `jobId` and poll `mcp__claude-review__review_status` with a bounded `waitSeconds` until `done=true`. Treat the completed status payload's `response` as the reviewer output, and save the completed `threadId` for any follow-up round.
+
+Apply feedback before finalizing.
+
+### Step 7: Output
+
+Save the final outline to `PAPER_PLAN.md` in the project root:
+
+```markdown
+# Paper Plan
+
+**Title**: [working title]
+**Venue**: [target venue]
+**Type**: [empirical/theory/method]
+**Date**: [today]
+**Page budget**: [MAX_PAGES] pages (main body to Conclusion end, excluding references & appendix)
+**Section count**: [N] (must match the number of section files that will be created)
+
+## Claims-Evidence Matrix
+[from Step 1]
+
+## Structure
+[from Step 2-3, section by section]
+
+## Figure Plan
+[from Step 4, with detailed hero figure description]
+
+## Citation Plan
+[from Step 5]
+
+## Reviewer Feedback
+[from Step 6, summarized]
+
+## Next Steps
+- [ ] /paper-figure to generate all figures
+- [ ] /paper-write to draft LaTeX
+- [ ] /paper-compile to build PDF
+```
+
+## Key Rules
+
+- **Large file handling**: If the Write tool fails due to file size, immediately retry using Bash (`cat << 'EOF' > file`) to write in chunks. Do NOT ask the user for permission — just do it silently.
+
+- **Do NOT generate author information** — leave author block as placeholder or anonymous
+- **Be honest about evidence gaps** — mark claims as "needs experiment" rather than overclaiming
+- **Page budget is hard** — if content exceeds MAX_PAGES, suggest what to move to appendix
+- **MAX_PAGES counting differs by venue** — ML conferences: main body to Conclusion end, references/appendix NOT counted; AAAI main track is typically 7 technical-content pages plus references. **IEEE venues: references ARE counted toward the page limit.**
+- **Venue-specific norms** — ML conferences (ICLR/NeurIPS/ICML) use `natbib` (`\citep`/`\citet`); **IEEE venues use `cite` package (`\cite{}`, numeric style)**
+- **Claims-Evidence Matrix is the backbone** — every claim must map to evidence, every experiment must support a claim
+- **Figures need detailed descriptions** — especially the hero figure, which must clearly specify comparisons and visual expectations
+- **Section count is flexible** — 5-8 sections depending on paper type. Don't force content into a rigid 5-section template.
+
+## Acknowledgements
+
+Outline methodology inspired by [Research-Paper-Writing-Skills](https://github.com/Master-cai/Research-Paper-Writing-Skills) (claim-evidence mapping), [claude-scholar](https://github.com/Galaxy-Dawn/claude-scholar) (citation verification), and [Imbad0202/academic-research-skills](https://github.com/Imbad0202/academic-research-skills) (claim verification protocol).
+
+## Output Protocols
+
+> Follow these shared protocols for all output files:
+> - **[Output Versioning Protocol](../../shared-references/output-versioning.md)** — write timestamped file first, then copy to fixed name
+> - **[Output Manifest Protocol](../../shared-references/output-manifest.md)** — log every output to MANIFEST.md
+> - **[Output Language Protocol](../../shared-references/output-language.md)** — respect the project's language setting