latex-paper-writer

latex-paper-writer is a skill for Claude Code, Codex from jimezsa/opencolab. It costs 90 tokens per session (2,076 once invoked), scanned B, original, MIT.

A workflow for creating and maintaining scientific papers, technical reports, and research-based PDF summaries in LaTeX, a system for typesetting structured documents. It supports venue-specific templates, figures, experiment tables, citations, version control, PDF compilation, and validation.

In plain words
What is it for?
Use it to write or edit research papers and reports, prepare experiment tables and figures, compile LaTeX sources, validate the resulting PDF, and package the final document.
Why use it?
It organizes the many steps of paper production in one workspace, from document structure and grounded claims to a checked final PDF. It also preserves meaningful changes with Git, a version-control system.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to write or edit research papers and reports, prepare experiment tables and figures, compile LaTeX sources, validate the resulting PDF, and package the final document.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jimezsa/opencolab/latex-paper-writer
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add jimezsa/opencolab --skill latex-paper-writer
Clone the repo
git clone --depth 1 https://github.com/jimezsa/opencolab

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for latex-paper-writer

README.md
[![agentmods](https://agentmods.dev/badge/skills/jimezsa/opencolab/latex-paper-writer/github.svg)](https://agentmods.dev/skills/jimezsa/opencolab/latex-paper-writer)
Your own site
<a href="https://agentmods.dev/skills/jimezsa/opencolab/latex-paper-writer"><img src="https://agentmods.dev/badge/skills/jimezsa/opencolab/latex-paper-writer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for latex-paper-writer

Your own site · 80×15
<a href="https://agentmods.dev/skills/jimezsa/opencolab/latex-paper-writer"><img src="https://agentmods.dev/badge/skills/jimezsa/opencolab/latex-paper-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 90 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,076 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00090 $0.02076
Opus 5 $0.00045 $0.01038
Sonnet 5 $0.00018 $0.00415
Haiku 4.5 $0.00009 $0.00208

Measured 11d ago against content hash 85d883ecd69f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade B, and why

latex-paper-writer scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

The scan reads SKILL.md. This mod also ships 5 executable files (scripts/build_pdf.sh, scripts/git_checkpoint.py, scripts/init_paper_workspace.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

script: "brew install --cask basictex && sudo tlmgr update --self && sudo tlmgr install latexmk"
projects/SKILLS/latex-paper-writer/SKILL.md · 229 lines

How it starts

The opening of the file, as written. The whole thing — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LaTeX Paper Writer Skill

Use this skill when the user wants a scientific paper, survey, technical report, research-derived PDF summary, LaTeX experiment table, or edits to an existing LaTeX document.

This is the canonical OpenColab path for paper production. Research, grounding, figure extraction, and architecture diagrams stay delegated to the existing shared skills; this skill owns the LaTeX workspace, document structure, template selection, scoped Git version control, PDF compilation, validation, and final delivery packaging.

Mission

Given source material for a scientific document:

  1. Select or preserve the right LaTeX template.
  2. Create or reuse a Git-controlled paper workspace.
  3. Draft or edit the LaTeX sources with grounded claims and citations.
  4. Generate experiment tables when useful.
  5. Add user-supplied, extracted, or generated figures when they clarify the paper.
  6. Build and validate the PDF.
  7. Create scoped Git checkpoints when the paper has meaningful changes.
  8. Return the final PDF path, and emit a raw Telegram file directive when needed.

Prerequisites

  • git is installed and available in PATH.
  • python3 is installed and available in PATH.
  • latexmk is preferred for PDF builds:
latexmk -v

If latexmk is missing, read references/document-types.md for install guidance and do not claim that compilation succeeded. Only run install commands after the user explicitly approves installing system packages.

Hard Requirements

  • Read references/conference-map.md before choosing a venue template.
  • Read references/citation-policy.md before writing claims from papers.
  • Read references/deep-research-integration.md when converting research outputs into a PDF summary or survey.
  • Read references/experiment-tables.md before generating result tables.
  • Use the existing paper's template and macros when editing an existing paper.
  • Treat ICLR as the canonical venue name; infer it from near misses such as ICRL only when context makes that clear, and mention the correction briefly.
  • Do not claim official venue-template compliance unless the official template is bundled, user-supplied, or otherwise verified.
  • Keep every generated or managed paper workspace under Git version control.
  • Never stage or commit unrelated files outside the paper workspace.
  • Inspect git status before editing an existing paper repository.
  • Use pdf-figure-extract for figures from already-downloaded local PDFs.
  • Use block-diagram for synthesized architecture, taxonomy, pipeline, or literature-map diagrams.
  • Use pageindex-grounded for exact local evidence checks over downloaded papers when a technical claim needs verification.
  • Do not fabricate citations, metadata, benchmark values, or architecture details.
  • When sending a PDF through Telegram, emit a raw @telegram-file {"kind":"document","file":"<path>","caption":"optional"} line on its own line with no code fence. Keep the JSON on one line, keep kind as document, and on Windows write the path with forward slashes.

Read the full file on GitHub · 229 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 229 lines · 90 tokens per session scan B 85d883ecd69f

Subscribe to this mod's changes

latex-paper-writer is a skill published in the GitHub repository jimezsa/opencolab (11 stars, last pushed 28d ago), licensed MIT. It adds 90 tokens to every session and 2,076 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

taxonomy-vto

A reference guide for diagnosing visual problems in LaTeX research papers. It defines categories such as wasted page space, misplaced figures, inconsistent formatting, overflow, alignment, and template-migration issues.

OpenRaiser/PaperFit · 0 tokens

academic-paper-to-chinese-insight-pdf

Turn an academic paper PDF into a high-quality Chinese insight report and export it as a polished Chinese PDF. Use when asked to read a paper, translate or summarize a paper into Chinese, extract the paper's core ideas, produce original insights/opinions, explain the paper in simpler language, or deliver a Chinese PDF…

davidtoby/agent-skills · 113 tokens

chinese-pdf-document-workflows

Class-level workflow for extracting, converting, editing, and producing polished Chinese PDFs and document reports from PDFs, papers, webpages, markdown, and video transcripts. Use when asked to create Chinese PDF reports, fix Chinese font/glyph rendering, summarize academic papers into Chinese insight reports…

davidtoby/agent-skills · 83 tokens

autoreport

Use when generating a physics or engineering experiment report from measured data and reference materials — orchestrates Theory, Data Analysis, Plotting, and Report sub-agents to produce a compiled LaTeX PDF. Also use for any sub-task in that pipeline: deriving formulas, analyzing lab data, plotting measurements with…

xjsongphy/skills · 74 tokens

pydicom

Use pydicom to read, inspect, write, transform, and safely preflight local DICOM datasets and pixel data. Applies to DICOM metadata, transfer syntaxes, compression plugins, frames, private elements, JSON, and bounded de-identification review.

K-Dense-AI/scientific-agent-skills · 56 tokens

hive.pdf

Read, write, merge, split, rotate, watermark, encrypt, and OCR PDF files using Python (pypdf, pdfplumber, reportlab, pypdfium2) and command-line tools (poppler-utils, qpdf). Use when the user asks to extract text/tables/images from a PDF, create or modify a PDF, combine or split PDFs, OCR a scanned PDF…

aden-hive/hive · 98 tokens