Claude MarketplacesSubmit
wanshuiyin avatar

Research Pipeline

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

This is the full autonomous research loop: you give it a research direction, and it runs idea discovery with literature review and novelty checking, picks the top idea (or waits for your approval), spins up experiments with optional code review, runs iterative auto-review loops until claims are solid, then generates a narrative report and optionally a formatted paper. It's resumable if it crashes mid-run, which matters because this thing can run overnight. The constants let you dial how adversarial the reviews are (medium to nightmare), whether to auto-proceed through gates, and whether to pull a base repo or start from scratch. Most useful when you actually want to walk away and let it cook through the entire pipeline, though you can checkpoint at stages if you want to steer. Ships with the standard research workflow assumptions baked in.

skills.sh installs
594
GitHub stars
18.9K
last updated
Aug 21, 2026
View on GitHub

Install

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

Installs into .claude/skills of the current project.

Files

Full Research Pipeline: Idea → Experiments → Submission

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. Generation workers are unchanged.

SKILL.md on GitHub

Sponsors

Promote your product hereReach 125k+ visitors monthlyPromote your product hereReach 125k+ visitors monthlyAgent CaffeineSponsoredClose your lid, come back to finished workSnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthlyWaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthlyknobsSponsoredSee your site on any phone, any day, in any language

Details

Repository
github.com/wanshuiyin/auto-claude-code-research-in-sleep
Categories
DevOps & CI/CD, Git & Pull Requests, Code Review & Quality, 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

Recommended

More DevOps & CI/CD
1aradotso avatarmarketing-pipeline-auto-contentaradotso/marketing-skillsmarketing pipeline auto content590skills.sh installs
2firecrawl avatarfirecrawl-build-crawlfirecrawl/skillsIntegrate Firecrawl `/crawl` into product code for bulk extraction across a site or site section. Use when a feature needs many related pages, such as documenta554skills.sh installs
3firecrawl avatarfirecrawl-build-mapfirecrawl/skillsIntegrate Firecrawl `/map` into product code for URL discovery on a known site. Use when a feature needs to find pages before scraping or crawling, especially o554skills.sh installs
4personamanagmentlayer avataransible-expertpersonamanagmentlayer/pclExpert-level Ansible for configuration management, automation, and infrastructure as code554skills.sh installs
5mohitmishra786 avatarzig-build-systemmohitmishra786/low-level-dev-skillsZig build system skill for multi-file Zig projects. Use when writing or debugging build.zig files, adding executables or libraries, integrating C source files, 552skills.sh installs
6wanshuiyin avatarmonitor-experimentwanshuiyin/auto-claude-code-research-in-sleepMonitor running experiments, check progress, collect results. Use when user says "check results", "is it done", "monitor", or wants experiment output.547skills.sh installs