Skip to content
Agentmart
Submit a tool

airesearchorchestrator:paper-write

Plan paper structure and generate LaTeX sections following IMRAD structure.

Skill by jacazjx

IndexedMIT★ 1
Write a review

Chalk Labs

Need help deploying airesearchorchestrator:paper-write?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/jacazjx-airesearchorchestrator-paper-write

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Plan paper structure and generate LaTeX sections following IMRAD structure. Covers outlining (Claims-Evidence Matrix, section plan) and drafting. Use when user says "write paper", "写论文", "generate LaTeX", "draft manuscript", "paper outline", "论文大纲".

Use cases: documents, writing, research

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/airesearchorchestrator-paper-write

Tools it pre-approves 7

From allowed-tools in SKILL.md: the agent may use these without asking you each time.

  • Bash(*),
  • Read,
  • Write,
  • Edit,
  • Grep,
  • Glob,
  • mcp__codex__codex

What's inside

Skill name
airesearchorchestrator:paper-write
Description
Plan paper structure and generate LaTeX sections following IMRAD structure. Covers outlining (Claims-Evidence Matrix, section plan) and drafting. Use when user says "write paper", "写论文", "generate LaTeX", "draft manuscript", "paper outline", "论文大纲".
License
MIT
Allowed tools
Bash(*),, Read,, Write,, Edit,, Grep,, Glob,, mcp__codex__codex
Instructions
161 lines in SKILL.md · view on GitHub

Before installing

  • Pre-approves some shell commands

Agent Skills spec issues

  • name: only lowercase letters, digits and single hyphens allowed
  • name: "airesearchorchestrator:paper-write" does not match folder "paper-write"
  • files: referenced but missing: references/citation-standards.md, references/venue-requirements.md

Files (4)

  • SKILL.md
  • academic_writing_style.md · references/
  • figure_table_guidelines.md · references/
  • imrad_structure.md · references/

SKILL.md (first lines)

## Purpose

Plan paper structure and generate LaTeX sections following IMRAD structure. This skill covers both outlining (Claims-Evidence Matrix, section planning) and section-by-section drafting.

## Workflow

### Phase 0: Paper Planning

Before writing, create the structural outline. If `paper/paper-plan.md` does not exist, create it.

1. **Parse research narrative** from experiment evidence package and prior phase deliverables
2. **Build Claims-Evidence Matrix** -- map each claim to its supporting evidence
3. **Design section structure** (5-8 sections following IMRAD)
4. **Plan figure/table placement** -- assign figures and tables to sections
5. **Scaffold citation structure** -- identify where key citations belong

Save to `paper/paper-plan.md`:
- Title proposal
- Section plan with key points per section
- Claims-Evidence Matrix
- Figure/table placement plan
- Citation scaffolding

### Phase 1: Preparation

1. **Read paper plan** from `paper/paper-plan.md`
2. **Review evidence package** from `docs/experiments/evidence-package-index.md`
3. **Check citation library** from `paper/references.bib`
4. **Review figures and tables** from `paper/figures/` and `paper/tables/`

### Phase 2: Section-by-Section Writing

Follow IMRAD structure. See `references/imrad_structure.md` for detailed section guidelines.

### Phase 3: LaTeX Compilation and Polish

1. **Clean stale files**: Remove old .aux, .log, .bbl files
2. **Compile**: pdflatex/bibtex cycle (3x for references)
3. **De-AI Polish**: Remove AI-typical phrases:
   - "delve", "pivotal", "crucial", "paramount"
   - "It is worth noting that..."
   - "In order to..." (use "to...")
4. **Check venue compliance**: Format, length, required sections

## LaTeX Templates

### Main Document Structure

```latex
\documentclass{article}  % or venue-specific class
\input{math_commands.tex}

\title{...}
\author{...}

\begin{document}
\maketitle
\begin{abstract} ... \end{abstract}

\input{sections/introduction}
\input{sections/related_work}
\input{sections/method}
\input{sections/experiments}
\input{sections/conclusion}

\bibliographystyle{plain}  % venue-specific
\bibliography{references}
\end{document}
```

### Algorithm Environment

```latex
\usepackage{algorithm}
\usepackage{algorithmic}

\begin{algorithm}[t]
\caption{Algorithm Name}
\label{alg:name}
\begin{algorithmic}[1]
\REQUIRE Input description
\ENSURE Output description
\STATE Step 1
\FOR{$i = 1$ to $N$}
  \STATE Step in loop
\ENDFOR
\RETURN result
\end{algorithmic}
\end{algorithm}
```

### Results Table

```latex
\begin{table}[t]
\centering
\caption{Main results. Best in \textbf{bold}. $\uparrow$ = higher is better.}
\label{tab:main}
\begin{tabular}{lcc}
\toprule
Method & Metric 1 $\uparrow$ & Metric 2 $\uparrow$ \\
\midrule
Baseline A & 85.2 $\pm$ 0.3 & 72.1 $\pm$ 0.5 \\
Baseline B & 87.4 $\pm$ 0.4 & 74.3 $\pm$ 0.6 \\
\textbf{Ours} & \textbf{92.3 $\pm$ 0.4} & \textbf{78.9 $\pm$ 0.3} \\
\bottomrule
\end{tabular}
\end{table}
```

### Figure Environment

```latex
\begin{figure}[t]
\centering
\includegraphics[width=\linewidth]{figures/figure_name.pdf}
\caption{Self-contained caption describing the figure.}
\label{fig:name}
\end{figure}
```

From jacazjx/AI-Research-Orchestrator, MIT.

More from jacazjx/AI-Research-Orchestrator

Signals

Stars
1
Forks
0
Open issues
0
Last commit (this folder)
Mar 22, 2026 (7 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from jacazjx

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get airesearchorchestrator:paper-write running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying airesearchorchestrator:paper-write?

CallGet help
Cite this page

airesearchorchestrator:paper-write skill. Agent Mart. https://agentmart.dev/skills/jacazjx-airesearchorchestrator-paper-write (last updated 2026-10-24)