What is paper-compile?

A LaTeX-to-PDF compilation and checking workflow for research papers. LaTeX is a text-based system for formatting documents, and the workflow also checks requirements such as page limits, anonymous submissions, fonts, and unresolved markers.

Use it to compile paper/main.tex, repair missing packages or broken figure paths, count pages, check anonymity and font embedding, and create a submission checklist.

It helps find compilation errors and submission problems before a paper is sent to a venue, with optional fixes for common issues.

How skyllwt/AutoSci configures Claude Code

About the project

AutoSci is an AI research platform organized around a wiki, with an agent that supports stages of scientific work such as reading, experimentation, writing, and retaining knowledge across projects. It is for people building or using AI-assisted research workflows, with Claude Code, Codex, and OpenCode adaptations available. The catalogue add-ons extend those agent-specific workflows.

skyllwt/AutoSci · 1,661 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to skyllwt/AutoSci. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/skyllwt/AutoSci/main/.claude/skills/paper-compile/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/skyllwt/AutoSci

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/skyllwt/autosci/paper-compile.svg)](https://agentmods.dev/skills/skyllwt/autosci/paper-compile)

Your own site

<a href="https://agentmods.dev/skills/skyllwt/autosci/paper-compile"><img src="https://agentmods.dev/badge/skills/skyllwt/autosci/paper-compile.svg" alt="Measured on agentmods" height="20"></a>

Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,441 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 2 findings. 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.

Model	Per session	Once invoked
Fable 5.1	$0.00031	$0.02441
Opus 5	$0.00015	$0.01221
Sonnet 5	$0.00006	$0.00488
Haiku 4.5	$0.00003	$0.00244

Measured 7d ago against content hash aa9999c0a3a8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade B, and why

paper-compile scanned grade B with 2 findings 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 7d ago.

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.

- **latexmk not installed**: error; provide installation command (`sudo apt install texlive-full` or `brew install --cask mactex`)

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

result = subprocess.run(['pdfinfo', 'paper/main.pdf'], capture_output=True, text=True)

.claude/skills/paper-compile/SKILL.md · 244 lines

How it starts

The opening of the file, as written. The whole thing — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/paper-compile

Compile a LaTeX paper to PDF, auto-fix common errors, and verify submission requirements. Input: the paper/ directory generated by /paper-draft. Run latexmk compilation, parse errors and attempt auto-fix (missing packages, undefined references, figure paths). Verify page limit, anonymous compliance, font embedding, and clearance of [UNCONFIRMED] markers. Generate a submission checklist.

Inputs

paper_dir (optional, default paper/): LaTeX project directory containing main.tex
--fix (optional): enable auto-fix mode (automatically install missing packages, correct paths)
--checklist (optional): generate a detailed submission checklist (check only, no compilation)

Outputs

paper/main.pdf — compiled PDF
COMPILE_REPORT (printed to terminal) — compilation status, check results, submission checklist
If --fix: modified .tex files (auto-fixed)

Wiki Interaction

Reads

wiki/outputs/paper-plan-*.md — retrieve venue information (page limit, anonymity requirements)
.claude/skills/shared-references/citation-verification.md — [UNCONFIRMED] marker check rules

Writes

paper/main.pdf — compilation output
wiki/log.md — appended compilation log

Graph edges created

None

Workflow

Precondition: confirm paper/main.tex exists. Confirm latexmk is installed (which latexmk).

Step 1: Compile

First compilation:

cd paper/ && latexmk -pdf -interaction=nonstopmode main.tex 2>&1

Parse compilation output:
- Collect all errors (! ...)
- Collect all warnings (Warning: / Overfull / Underfull)
- Classify:
  - Missing package: ! LaTeX Error: File 'xxx.sty' not found
  - Undefined reference: LaTeX Warning: Reference 'xxx' on page N undefined
  - Undefined citation: LaTeX Warning: Citation 'xxx' on page N undefined
  - Missing figure: ! LaTeX Error: File 'figures/xxx' not found
  - Syntax error: other errors beginning with !
  - Overfull/Underfull: typesetting warnings (non-blocking)

Read the full file on GitHub · 244 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.

7d ago First seen · 244 lines · 31 tokens per session scan B aa9999c0a3a8

Subscribe to this mod's changes

paper-compile is a skill published in the GitHub repository skyllwt/AutoSci (1,661 stars, last pushed yesterday), licensed MIT. It adds 31 tokens to every session and 2,441 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 2 findings (asks for root, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Documents PDF

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

foundry-hosted-agent-validation

Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.

microsoft/agent-framework · 82 tokens

AutoSci: Skill for Claude Code