Chains five sub-skills into a single pipeline that takes a research narrative and outputs a submission-ready PDF with LaTeX source. Runs through outline generation, figure creation, section-by-section writing, compilation, and two rounds of automated review and polish. You can configure the target venue (ICLR, NeurIPS, IEEE, etc.), pass a style reference to match structural patterns from papers you like, and set an assurance level that gates the final output on passing proof checks and claim audits. The pipeline runs autonomously by default but you can pause between phases or flag human checkpoints in the review loop. Useful when you have experimental results documented and want to skip the manual LaTeX grinding, or when you need a solid first draft fast enough that you can spend your time on the science instead of wrestling with figure placement and bibliography formatting.

skills.sh installs
595
GitHub stars
18.9K
last updated
Aug 21, 2026

Install

$ npx -y skills add wanshuiyin/auto-claude-code-research-in-sleep --skill paper-writing --agent claude-code

Installs into .claude/skills of the current project.

Files

Workflow 3: Paper Writing Pipeline

Before each reviewer slot, follow Selectable Reviewers: resolve invocation → .aris/reviewer.json → Claude Code default (Codex MCP) with reviewer_route.py through the canonical helper resolver, preserving this slot's tier, fresh contexts, source/image inputs and deterministic gates. Codex examples/pins below apply only to backend=codex; other routes use their own first-call/reply contract. Save the route and actual returned identity; unavailable selections are REVIEW_UNAVAILABLE. Classify acceptance from actual families/completion/scope. Forward invocation reviewer/model/effort overrides to reviewer-bearing children. Writer selection is separate; follow the writing-worker guidance below when drafting or revising prose.

Orchestrate a complete paper writing workflow for: $ARGUMENTS

Overview

This skill chains five sub-skills into a single automated pipeline:

/paper-plan → /paper-figure → /paper-write → /paper-compile → /auto-paper-improvement-loop
  (outline)     (plots)        (LaTeX)        (build PDF)       (review & polish ×2)

Sponsors

Details

Repository
github.com/wanshuiyin/auto-claude-code-research-in-sleep
Categories
DevOps & CI/CD, Documentation, Data Science & ML, Automation & Workflows, Sales & Marketing, Office & Documents
First seen
Jun 3, 2026

More from wanshuiyin/auto-claude-code-research-in-sleep

All 41
1alirezarezvani avatarfree-tool-strategyalirezarezvani/claude-skillsWhen the user wants to build a free tool for marketing — lead generation, SEO value, or brand awareness. Use when they mention 'engineering as marketing,' 'free592skills.sh installs
2guia-matthieu avatarweb-scraperguia-matthieu/clawfu-skillsExtract structured data from websites. Use when: collecting competitor pricing; scraping product listings; extracting contact information; gathering research da590skills.sh installs
3star23 avatarus-market-sentimentstar23/day1global-skillsUS stock market sentiment monitoring and position recommendation system. Evaluates market sentiment by tracking 5 core indicators (NAAIM Exposure Index, Institu590skills.sh installs
4anthropics avatarinteractive-dashboard-builderanthropics/knowledge-work-pluginsBuild self-contained interactive HTML dashboards with Chart.js, dropdown filters, and professional styling. Use when creating dashboards, building interactive r586skills.sh installs
5alirezarezvani avatarculture-architectalirezarezvani/claude-skillsBuild, measure, and evolve company culture as operational behavior — not wall posters. Covers mission/vision/values workshops, values-to-behaviors translation, 584skills.sh installs
6bobmatnyc avatarfastifybobmatnyc/claude-mpm-skillsProduction Fastify (TypeScript) patterns: schema validation, plugins, typed routes, error handling, security hardening, logging, testing with inject, and gracef582skills.sh installs