# Paper Write

> Draft LaTeX paper section by section from an outline. Use when user says \"写论文\", \"write paper\", \"draft LaTeX\", \"开始写\", or wants to generate LaTeX content from a paper plan.

- **Type:** Skill
- **Install:** `agentstack add skill-wanshuiyin-auto-claude-code-research-in-sleep-paper-write`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [wanshuiyin](https://agentstack.voostack.com/s/wanshuiyin)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [wanshuiyin](https://github.com/wanshuiyin)
- **Source:** https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep/tree/main/skills/paper-write

## Install

```sh
agentstack add skill-wanshuiyin-auto-claude-code-research-in-sleep-paper-write
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Paper Write: Section-by-Section LaTeX Generation

Draft a LaTeX paper based on: **$ARGUMENTS**

## Constants

- **REVIEWER_MODEL = `gpt-5.5`** — Model used via Codex MCP for section review. Must be an OpenAI model.
- **TARGET_VENUE = `ICLR`** — Default venue. Supported: `ICLR`, `NeurIPS`, `ICML`, `CVPR` (also ICCV/ECCV), `ACL` (also EMNLP/NAACL), `AAAI`, `ACM` (ACM MM, SIGIR, KDD, CHI, etc.), `IEEE_JOURNAL` (IEEE Transactions / Letters, e.g., T-PAMI, JSAC, TWC, TCOM, TSP, TIP), `IEEE_CONF` (IEEE conferences, e.g., ICC, GLOBECOM, INFOCOM, ICASSP). Determines style file and formatting.
- **ANONYMOUS = true** — If true, use anonymous author block. Set `false` for camera-ready. Note: most IEEE venues do NOT use anonymous submission — set `false` for IEEE.
- **MAX_PAGES = 9** — Main body page limit. For ML conferences: counts from first page to end of Conclusion section, references and appendix NOT counted. **For IEEE venues: references ARE counted toward the page limit.** Typical limits: IEEE journal = no strict limit (but 12-14 pages typical for Transactions, 4-5 for Letters), IEEE conference = 5-8 pages including references.
- **DBLP_BIBTEX = true** — Fetch real BibTeX from DBLP/CrossRef instead of LLM-generated entries. Eliminates hallucinated citations. Zero install required. Set `false` to use legacy behavior (LLM search + `[VERIFY]` markers).

## Inputs

1. **PAPER_PLAN.md** — outline with claims-evidence matrix, section plan, figure plan (from `/paper-plan`)
2. **NARRATIVE_REPORT.md** — the research narrative (primary source of content)
3. **Generated figures** — PDF/PNG files in `figures/` (from `/paper-figure`)
4. **LaTeX includes** — `figures/latex_includes.tex` (from `/paper-figure`)
5. **Bibliography** — existing `.bib` file, or will create one

If no PAPER_PLAN.md exists, ask the user to run `/paper-plan` first or provide a brief outline.

## Orchestra-Guided Writing Overlay

Keep the existing `insleep` workflow, file layout, and defaults. Use the shared references below only when they improve writing quality:

- Read `../shared-references/writing-principles.md` before drafting the Abstract, Introduction, Related Work, or when prose feels generic.
- Read `../shared-references/venue-checklists.md` during the final write-up and submission-readiness pass.
- Read `../shared-references/citation-discipline.md` only when the built-in DBLP/CrossRef workflow is insufficient.

These references are support material, not extra workflow phases.

## Optional: Style reference (`— style-ref: `, opt-in)

Lets the user steer **structural** style (section ordering, theorem density, sentence cadence, figure density, bibliography style) toward a reference paper. **Default OFF — when the user does not pass `— style-ref`, do nothing differently from before.**

Only when `— style-ref: ` appears in `$ARGUMENTS`, run the helper FIRST, before drafting:

```bash
# Resolve $STYLE_HELPER via the canonical strict-safe chain (see
# shared-references/integration-contract.md §2). Policy A — gate:
# unresolved helper means --style-ref cannot be satisfied, so abort.
cd "$(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 $2; exit}' .aris/installed-skills.txt 2>/dev/null) || true
fi
STYLE_HELPER=".aris/tools/extract_paper_style.py"
[ -f "$STYLE_HELPER" ] || STYLE_HELPER="tools/extract_paper_style.py"
[ -f "$STYLE_HELPER" ] || { [ -n "${ARIS_REPO:-}" ] && STYLE_HELPER="$ARIS_REPO/tools/extract_paper_style.py"; }
[ -f "$STYLE_HELPER" ] || {
  echo "ERROR: extract_paper_style.py not resolved at .aris/tools/, tools/, or \$ARIS_REPO/tools/." >&2
  echo "       Fix: rerun bash tools/install_aris.sh, export ARIS_REPO, or copy the helper to tools/." >&2
  echo "       --style-ref cannot be satisfied; aborting." >&2
  exit 1
}
STYLE_STATUS=0
CACHE=$(python3 "$STYLE_HELPER" --source "") || STYLE_STATUS=$?
case "$STYLE_STATUS" in
  0) ;;                                       # use $CACHE/style_profile.md as structural guidance
  2) echo "warning: style-ref skipped (missing optional dep)" >&2 ;;
  3) echo "error: --style-ref source failed; aborting draft" >&2 ; exit 1 ;;
  *) echo "error: helper failed unexpectedly; aborting draft" >&2 ; exit 1 ;;
esac
```

Sources accepted: local TeX dir / file, local PDF, arXiv id (`2501.12345` or `arxiv:2501.12345`), http(s) URL. Overleaf URLs and project IDs are rejected — clone via `/overleaf-sync setup ` first and pass the local clone path.

**Strict rules** (full contract in `tools/extract_paper_style.py` docstring):

- Use `style_profile.md` as **structural** guidance only. Match section count, section ordering tendency, theorem-environment density, caption-length distribution, sentence cadence, math display ratio, citation style.
- **Never copy prose, claims, examples, or terminology** from anything reachable through the cache. The profile is intentionally aggregate; if you need substance, use the user's own outline.
- **Never pass `— style-ref` (or the cache contents) to reviewer / auditor sub-agents.** Cross-model review independence (`../shared-references/reviewer-independence.md`) requires reviewers see only the artifact and the user's prompt, not the author's stylistic context.

### `` markers (when `GAP_REPORT.md` exists)

If `/paper-plan` ran with `— style-ref:` it will have emitted `GAP_REPORT.md` alongside `PAPER_PLAN.md`. This file lists structural slots (ablation tables, scaling experiments, failure-case analyses, …) the exemplar implies but the user has **no evidence to fill**.

When `GAP_REPORT.md` is present and a section slot is classified as `status: missing`:

1. **Do not fabricate numerical results, figure references, or qualitative claims** to fill that slot.
2. Emit an HTML-comment placeholder at the exact location the missing content would go:

   ```latex
   
   ```

3. Slot ID and one-line description come straight from `GAP_REPORT.md`. **Never invent Slot IDs.** Never reword the description to be more confident than the report.
4. The marker is intentionally an HTML comment so it is invisible in the rendered PDF but **searchable via `grep -r "DATA_NEEDED" sec/`** for human triage / `/experiment-bridge` follow-up.
5. For `status: partial`, write what the user has and emit `` at the gap point in the same paragraph (do not split the section).

**Carve-out from "no placeholder" rule.** The default `/paper-write` discipline (no placeholders such as "see supplementary" or "TBD") still applies for everything **except** GAP_REPORT-listed missing slots. The marker is the principled way to surface genuine evidence deficits without compromising claim integrity.

Original idea: @zhangpelf in [#217](https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep/issues/217).

## Templates

### Venue-Specific Setup

The skill includes conference templates in `templates/`. Select based on TARGET_VENUE:

**ICLR:**
```latex
\documentclass{article}
\usepackage{iclr2026_conference,times}
% \iclrfinalcopy  % Uncomment for camera-ready
```

**NeurIPS:**
```latex
\documentclass{article}
\usepackage[preprint]{neurips_2025}
% \usepackage[final]{neurips_2025}  % Camera-ready
```

**ICML:**
```latex
\documentclass[accepted]{icml2025}
% Use [accepted] for camera-ready
```

**IEEE Journal** (Transactions, Letters):
```latex
\documentclass[journal]{IEEEtran}
\usepackage{cite}  % IEEE uses \cite{}, NOT natbib
% Author block uses \author{Name~\IEEEmembership{Member,~IEEE}}
```

**IEEE Conference** (ICC, GLOBECOM, INFOCOM, ICASSP, etc.):
```latex
\documentclass[conference]{IEEEtran}
\usepackage{cite}  % IEEE uses \cite{}, NOT natbib
% Author block uses \IEEEauthorblockN / \IEEEauthorblockA
```

### Project Structure

Generate this file structure:

```
paper/
├── main.tex                    # master file (includes sections)
├── iclr2026_conference.sty     # or neurips_2025.sty / icml2025.sty / IEEEtran.cls + IEEEtran.bst
├── math_commands.tex           # shared math macros
├── references.bib              # bibliography (filtered — only cited entries)
├── sections/
│   ├── 0_abstract.tex
│   ├── 1_introduction.tex
│   ├── 2_related_work.tex
│   ├── 3_method.tex            # or preliminaries, setup, etc.
│   ├── 4_experiments.tex
│   ├── 5_conclusion.tex
│   └── A_appendix.tex          # proof details, extra experiments
└── figures/                    # symlink or copy from project figures/
```

**Section files are FLEXIBLE**: If the paper plan has 6-8 sections, create corresponding files (e.g., `4_theory.tex`, `5_experiments.tex`, `6_analysis.tex`, `7_conclusion.tex`).

## Workflow

### Step 0: Backup and Clean

If `paper/` already exists, back up to `paper-backup-{timestamp}/` before overwriting. Never silently destroy existing work.

**CRITICAL: Clean stale files.** When changing section structure (e.g., 5 sections → 7 sections), delete section files that are no longer referenced by `main.tex`. Stale files (e.g., old `5_conclusion.tex` left behind when conclusion moved to `7_conclusion.tex`) cause confusion and waste space.

### Step 1: Initialize Project

1. Create `paper/` directory
2. Copy venue template from `templates/` — the template already includes:
   - All standard packages (amsmath, hyperref, cleveref, booktabs, etc.)
   - Theorem environments with `\crefname{assumption}` fix
   - Anonymous author block
3. Generate `math_commands.tex` with paper-specific notation
4. Create section files matching PAPER_PLAN structure

**Author block (anonymous mode):**
```latex
\author{Anonymous Authors}
```

### Step 2: Generate math_commands.tex

Create shared math macros based on the paper's notation:

```latex
% math_commands.tex — shared notation
\newcommand{\R}{\mathbb{R}}
\newcommand{\E}{\mathbb{E}}
\DeclareMathOperator*{\argmin}{arg\,min}
\DeclareMathOperator*{\argmax}{arg\,max}
% Add paper-specific notation here
```

### Step 3: Write Each Section

Process sections in order. For each section:

1. **Read the plan** — what claims, evidence, citations belong here
2. **Read NARRATIVE_REPORT.md** — extract relevant content, findings, and quantitative results
3. **Draft content** — write complete LaTeX (no fabricated placeholders). **Exception:** if `GAP_REPORT.md` exists and the section has slots with `status: missing`, emit `` at those points instead of inventing data — see the DATA_NEEDED markers subsection above.
4. **Insert figures/tables** — use snippets from `figures/latex_includes.tex`
5. **Add citations** — for ML conferences (ICLR/NeurIPS/ICML/CVPR/ACL/AAAI): use `\citep{}` / `\citet{}` (natbib). **For IEEE venues**: use `\cite{}` (numeric style via `cite` package). Never mix natbib and cite commands.

Before drafting the front matter, re-read the one-sentence contribution from `PAPER_PLAN.md`. The Abstract and Introduction should make that takeaway obvious before the reader reaches the full method.

#### Section-Specific Guidelines

**§0 Abstract:**
- Use the 5-part flow from `../shared-references/writing-principles.md`: what, why hard, how, evidence, strongest result
- Must be self-contained (understandable without reading the paper)
- Start with the paper's specific contribution, not generic field-level background
- Include one concrete quantitative result
- 150-250 words (check venue limit)
- No citations, no undefined acronyms
- No `\begin{abstract}` — that's in main.tex

**§1 Introduction:**
- Open with a compelling hook (1-2 sentences, problem motivation)
- State the gap clearly ("However, ...")
- Give a brief approach overview before the reader gets lost in details
- List 2-4 specific, falsifiable contributions as a numbered or bulleted list
- Preview the strongest result early instead of saving it for the experiments section
- End with a brief roadmap ("The rest of this paper is organized as...")
- Include the main result figure if space allows
- Target: 1-1.5 pages
- Methods should begin by page 2-3 at the latest

**§2 Related Work:**
- **MINIMUM 1 full page** (3-4 substantive paragraphs). Short related work sections are a common reviewer complaint.
- Organize by category using `\paragraph{Category Name.}`
- Organize methodologically, by assumption class, or by research question; do not write paper-by-paper mini-summaries
- Each category: 1 paragraph summarizing the line of work + 1-2 sentences positioning this paper
- Do NOT just list papers — synthesize and compare
- End each paragraph with how this paper relates/differs

**§3 Method / Preliminaries / Setup:**
- Define notation early (reference math_commands.tex)
- Use `\begin{definition}`, `\begin{theorem}` environments for formal statements
- For theory papers: include proof sketches of key results in main body, full proofs in appendix
- For theory papers: include a **comparison table** of prior bounds vs. this paper
- Include algorithm pseudocode if applicable (`algorithm2e` or `algorithmic`)
- Target: 1.5-2 pages

**§4 Experiments:**
- Start with experimental setup (datasets, baselines, metrics, implementation details)
- Main results table/figure first
- Then ablations and analysis
- Every claim from the introduction must have supporting evidence here
- For each major experiment, make explicit what claim it supports and what the reader should notice
- Target: 2.5-3 pages

**§5 Conclusion:**
- Summarize contributions (NOT copy-paste from intro — rephrase)
- Limitations (be honest — reviewers appreciate this)
- Future work (1-2 concrete directions)
- Ethics statement and reproducibility statement (if venue requires)
- Target: 0.5 pages

**Appendix:**
- Proof details (full proofs of main-body theorems)
- Additional experiments, ablations
- Implementation details, hyperparameter tables
- Additional visualizations

### Step 3.5: Theory Paper Consistency Pass (theory papers only)

Run this pass after drafting all sections and before building the bibliography.

**Trigger heuristic:** treat the paper as theory-heavy if `PAPER_PLAN.md` labels it as theory/analysis, or if the drafted sections contain 5 or more formal result environments (`\begin{theorem}`, `\begin{lemma}`, `\begin{proposition}`, `\begin{corollary}`).

**Proof source search:** search the workspace for any standalone full-proof source file whose name or contents indicate a canonical proof version (`proof`, `appendix`, `full`, `complete`, `supplement`, `supplementary`). If such a file exists, prompt the user exactly:

`Inline full proofs from {file}? [Y/n]`

Default to `Y`.

If the user accepts:
- import the full theorem/lemma statement plus proof block into the appendix source (`A_appendix.tex` or the appendix file named by the plan)
- use the main-body theorem statement as the canonical public statement; the appendix copy must match it unless the main-body statement is being revised in the same pass
- do **not** leave placeholders such as "see supplementary proof document" or "proof omitted for brevity"
- preserve theorem labels, equation labels, and proof structure exactly
- keep the main body proof sketches short, but never let the appendix be a sketch-only placeholder when a full proof source exists

If no standalone full-proof source exists:
- use proof sketches only when they are actually written as proof sketches, not placeholders
- do not fabricate an external proof document reference

**Restatement audit:**
- Compare every theorem/lemma/proposition statement that is restated in the appendix against the main-body version
- Do not diff proof bodies; only audit statements, hypotheses, case splits, quantifiers, domains, notation, variable names, and terminology for defined objects
- Treat `stationary` vs `terminal`, changed assumption names, or missing case splits as mismatches unless explicitly documented
- If the appendix needs different wording, add an explicit notation bridge instead of silently renaming concepts
- Resolve all mismatches before Step 4

**Empirical motivation:** in a real theory-paper run, the default behavior gen

…

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [wanshuiyin](https://github.com/wanshuiyin)
- **Source:** [wanshuiyin/Auto-claude-code-research-in-sleep](https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** yes
- **Filesystem access:** yes
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-wanshuiyin-auto-claude-code-research-in-sleep-paper-write
- Seller: https://agentstack.voostack.com/s/wanshuiyin
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.