• VENUE =

  ICLR

  — Target venue. Options:

  ICLR

  ,

  NeurIPS

  ,

  ICML

  . Affects style file, page limit, citation format.
• MAX_IMPROVEMENT_ROUNDS = 2 — Number of review→fix→recompile rounds in the improvement loop.
• REVIEWER_MODEL =

  gpt-5.4

  — Model used via Codex MCP for plan review, figure review, writing review, and improvement loop.
• AUTO_PROCEED = true — Auto-continue between phases. Set

  false

  to pause and wait for user approval after each phase.
• HUMAN_CHECKPOINT = false — When

  true

  , the improvement loop (Phase 5) pauses after each round's review to let you see the score and provide custom modification instructions. When

  false

  (default), the loop runs fully autonomously. Passed through to

  /auto-paper-improvement-loop

  .
• ILLUSTRATION =

  gemini

  — AI illustration mode:

  gemini

  (default, needs

  GEMINI_API_KEY

  ),

  mermaid

  (free, no API key), or

  false

  (skip, manual only).

Override inline:

/paper-writing "NARRATIVE_REPORT.md" — venue: NeurIPS, illustration: mermaid

1. NARRATIVE_REPORT.md

   (best) — structured research narrative with claims, experiments, results, figures
2. Research direction + experiment results — the skill will help draft the narrative first
3. Existing

   PAPER_PLAN.md

   — skip Phase 1, start from Phase 2

/paper-plan

/paper-plan "$ARGUMENTS"

• Parse NARRATIVE_REPORT.md for claims, evidence, and figure descriptions
• Build a Claims-Evidence Matrix — every claim maps to evidence, every experiment supports a claim
• Design section structure (5-8 sections depending on paper type)
• Plan figure/table placement with data sources
• Scaffold citation structure
• GPT-5.4 reviews the plan for completeness

PAPER_PLAN.md

📐 Paper plan complete:
- Title: [proposed title]
- Sections: [N] ([list])
- Figures: [N] auto-generated + [M] manual
- Target: [VENUE], [PAGE_LIMIT] pages

Shall I proceed with figure generation?

• User approves (or AUTO_PROCEED=true) → proceed to Phase 2.
• User requests changes → adjust plan and re-present.

/paper-figure

/paper-figure "PAPER_PLAN.md"

• Read figure plan from PAPER_PLAN.md
• Generate matplotlib/seaborn plots from JSON/CSV data
• Generate LaTeX comparison tables
• Create

  figures/latex_includes.tex

  for easy insertion
• GPT-5.4 reviews figure quality and captions

figures/

illustration

false

illustration: gemini

/paper-illustration

/paper-illustration "[method description from PAPER_PLAN.md or NARRATIVE_REPORT.md]"

• Claude plans → Gemini optimizes → Nano Banana Pro renders → Claude reviews (score ≥ 9)
• Output:

  figures/ai_generated/*.png

• Requires

  GEMINI_API_KEY

  environment variable

illustration: mermaid

/mermaid-diagram

/mermaid-diagram "[method description from PAPER_PLAN.md]"

• Generates Mermaid syntax diagrams (flowchart, sequence, class, etc.)
• Output:

  figures/*.mmd

  +

  figures/*.png

• Free, no API key needed

illustration: false

📊 Figures complete:
- Data plots (auto): [list]
- AI illustrations (auto): [list, if illustration ≠ false]
- Manual (need your input): [list]
- LaTeX snippets: figures/latex_includes.tex

[If manual figures needed]: Please add them to figures/ before I proceed.
[If all auto]: Shall I proceed with LaTeX writing?

/paper-write

/paper-write "PAPER_PLAN.md"

• Write each section following the plan, with proper LaTeX formatting
• Insert figure/table references from

  figures/latex_includes.tex

• Build

  references.bib

  from citation scaffolding
• Clean stale files from previous section structures
• Automated bib cleaning (remove uncited entries)
• De-AI polish (remove "delve", "pivotal", "landscape"...)
• GPT-5.4 reviews each section for quality

paper/

main.tex

sections/*.tex

references.bib

math_commands.tex

✍️ LaTeX writing complete:
- Sections: [N] written ([list])
- Citations: [N] unique keys in references.bib
- Stale files cleaned: [list, if any]

Shall I proceed with compilation?

/paper-compile

/paper-compile "paper/"

• latexmk -pdf

  with automatic multi-pass compilation
• Auto-fix common errors (missing packages, undefined refs, BibTeX syntax)
• Up to 3 compilation attempts
• Post-compilation checks: undefined refs, page count, font embedding
• Precise page verification via

  pdftotext

• Stale file detection

paper/main.pdf

🔨 Compilation complete:
- Status: SUCCESS
- Pages: [X] (main body) + [Y] (references) + [Z] (appendix)
- Within page limit: YES/NO
- Undefined references: 0
- Undefined citations: 0

Shall I proceed with the improvement loop?

/auto-paper-improvement-loop

/auto-paper-improvement-loop "paper/"

main_round1.pdf

main_round2.pdf

• Fix assumption-model mismatches
• Soften overclaims to match evidence
• Add missing interpretations and notation
• Strengthen limitations section
• Add theory-aligned experiments if needed

PAPER_IMPROVEMENT_LOG.md

• paper/main.pdf — Final polished paper
• paper/main_round0_original.pdf — Before improvement
• paper/main_round1.pdf — After round 1
• paper/main_round2.pdf — After round 2
• paper/PAPER_IMPROVEMENT_LOG.md — Full review log

• [items from final review that weren't addressed]

• Visual inspection of PDF
• Add any missing manual figures
• Submit to [venue] via OpenReview / CMT / HotCRP

undefined

• 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.
• Don't skip phases. Each phase builds on the previous one — skipping leads to errors.
• Checkpoint between phases when AUTO_PROCEED=false. Present results and wait for approval.
• Manual figures first. If the paper needs architecture diagrams or qualitative results, the user must provide them before Phase 3.
• Compilation must succeed before entering the improvement loop. Fix all errors first.
• Preserve all PDFs. The user needs round0/round1/round2 for comparison.
• Document everything. The pipeline report should be self-contained.
• Respect page limits. If the paper exceeds the venue limit, suggest specific cuts before the improvement loop.