AutoResearch-SibylSystem: Skill for Claude Code

.claude/skills/sibyl-latex-writer/SKILL.md

sibyl-latex-writer is a skill for Claude Code from Sibyl-Research-Team/AutoResearch-SibylSystem. It costs 32 tokens per session (245 once invoked), scanned A, original, no licence file.

A paper-formatting assistant that converts papers to NeurIPS LaTeX format and compiles them. LaTeX is a text-based system for producing structured documents, and NeurIPS is a major machine-learning research conference.

In plain words
What is it for?
It is for formatting and compiling research papers using the NeurIPS LaTeX template.
Why use it?
It reduces manual formatting work when preparing a paper for NeurIPS submission.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: agent in frontmatter.

This is Sibyl-Research-Team/AutoResearch-SibylSystem's own configuration. It tells Claude Code how to work on AutoResearch-SibylSystem itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything AutoResearch-SibylSystem configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Sibyl-Research-Team/AutoResearch-SibylSystem. 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/Sibyl-Research-Team/AutoResearch-SibylSystem/main/.claude/skills/sibyl-latex-writer/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Sibyl-Research-Team/AutoResearch-SibylSystem

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.

agentmods badge for sibyl-latex-writer

README.md
[![agentmods](https://agentmods.dev/badge/skills/sibyl-research-team/autoresearch-sibylsystem/sibyl-latex-writer/github.svg)](https://agentmods.dev/skills/sibyl-research-team/autoresearch-sibylsystem/sibyl-latex-writer)
Your own site
<a href="https://agentmods.dev/skills/sibyl-research-team/autoresearch-sibylsystem/sibyl-latex-writer"><img src="https://agentmods.dev/badge/skills/sibyl-research-team/autoresearch-sibylsystem/sibyl-latex-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 sibyl-latex-writer

Your own site · 80×15
<a href="https://agentmods.dev/skills/sibyl-research-team/autoresearch-sibylsystem/sibyl-latex-writer"><img src="https://agentmods.dev/badge/skills/sibyl-research-team/autoresearch-sibylsystem/sibyl-latex-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 245 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin unknown 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 $0.00032 $0.00245
Opus 5 $0.00016 $0.00122
Sonnet 5 $0.00006 $0.00049
Haiku 4.5 $0.00003 $0.00024

Measured 12d ago against content hash 262edab33a22, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

sibyl-latex-writer scanned grade A with 0 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 12d 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/sibyl-latex-writer/SKILL.md · 19 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

Read it on GitHub

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. 12d ago First seen · 19 lines · 32 tokens per session scan A 262edab33a22

Subscribe to this mod's changes

sibyl-latex-writer is a skill published in the GitHub repository Sibyl-Research-Team/AutoResearch-SibylSystem (277 stars, last pushed 5mo ago), with no licence file. It adds 32 tokens to every session and 245 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. 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

literature-survey

Use when the user wants a comprehensive literature survey on a specific research topic. Outputs a complete PDF survey (6–20 pages, 60+ real citations, 100+ recommended) with LaTeX source, topic-specific publication figures, and a classified literature table. Single-stage, no Python runtime.

ai4s-research/ai4s-skills · 66 tokens

traceability-review

Use when the user asks to review, verify, or audit a report, manuscript, or analysis in the workspace for traceability — resolving citations, flagging numbers with no source, and checking figures against the code that generated them. Emits a structured review block the app renders as reviewer findings. Verifies…

ai4s-research/open-science · 72 tokens

paper-slides

A workflow for turning a completed research paper into conference slides, an editable PowerPoint file, speaker notes, and a full talk script.

AI4Scientist/nano-scientist · 81 tokens

paper-talk

A workflow for turning a research paper into a conference talk, including slide plans, editable presentation files, page checks, and a final report.

AI4Scientist/nano-scientist · 113 tokens

jurisdiction-format

A patent-document formatting workflow that compiles an application into filing formats for China, the United States, or Europe.

AI4Scientist/nano-scientist · 47 tokens

paper-poster

A workflow for turning a completed research paper into a large conference poster, with PDF, editable PowerPoint, and SVG exports. An SVG is an image format that stays editable when resized.

AI4Scientist/nano-scientist · 76 tokens