SkillPedia Skills Encyclopedia
中文 EN
Today's updates 2026-11-17 UTC

No new commits yet today

Open the update feed

Auto-claude-code-research-in-sleepwanshuiyin/Auto-claude-code-research-in-sleep

Lets Claude Code run a full round of machine learning research unattended (e.g. overnight), from idea to draft.…

No ratings yet Rate this skill
Stars17.9k
Forks1.5k
Watchers17.9k
Open Issues74

InstallOne-line install

Unconfirmed

Whether this repository follows the Agent Skills spec (that is, whether it contains a SKILL.md) has not been verified yet. Until that is settled, clone it and use what you need:

git clone https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep.git

Where it runs

This skill has to be installed inside the client above before you can use it.

OverviewOverview

Key Features

Lets Claude Code run a full round of machine learning research unattended (e.g. overnight), from idea to draft. Key capabilities include: 1. Idea generation: automatically produces paper topics and novel ideas from a research direction, saving manual brainstorming time; 2. Literature survey and review: automatically retrieves and reads related papers, reviews and compares existing work, and outputs survey material; 3. Automatic experiment code writing and execution: generates experiment code from the chosen topic and actually runs it via Claude Code / Codex agents, then collects results; 4. Paper writing: organizes ideas, survey findings and experiment results into a paper draft, cutting repetitive work from experiment to write-up; 5. MCP and multi-agent orchestration: coordinates Claude Code, Codex, GPT and other models through an MCP server to chain the whole automated research pipeline.

Use Cases

machine learning topic survey, paper idea generation, literature review and paper review, automatic experiment code writing and running, paper draft writing, unattended overnight research automation pipeline.

Target Roles

AI / Algorithm Engineer, Data Analyst / Data Engineer, Product Manager (PM).

TopicsTopics

RatingUser ratings

Nobody has rated this skill yet. Yours would be the first on the site — your vote becomes the initial average.

Rate this skill

Fill it in to be included in the per-role averages below.

One vote per IP,and it cannot be changed after submitting, so choose carefully the first time. No account is collected and no sign-in is required.

RepositoryRepository

Skill ID93
Data sourceGitHub
Repositorywanshuiyin/Auto-claude-code-research-in-sleep
CategoryAI & Agents / Research Automation & Paper Writing
Primary languagePython
LicenseMIT License
Default branchmain
GitHub repository ID1177608268
Node IDR_kgDORjDgTA
Rank#79 (position within the source ranking)
Site-wide popularity rank#96 (computed live from Stars, across all 5833 entries)

GrowthStar / Fork growth

One snapshot per day, tracking how Stars and Forks changed

05k10k15k20k2026-10-102026-10-222026-10-10 · 17,2192026-10-14 · 17,2192026-10-16 · 17,2192026-10-22 · 17,890
  • Now17,890
  • Previous point · 10-16 17,219
  • vs previous point +671
  • 4 data points 12 days
05001k1.5k2026-10-102026-10-222026-10-10 · 1,4452026-10-14 · 1,4452026-10-16 · 1,4452026-10-22 · 1,477
  • Now1,477
  • Previous point · 10-16 1,445
  • vs previous point +32
  • 4 data points 12 days

TimelineTimeline

Repository created2026-03-10 07:31:458 months ago
Data last updated2026-10-26 11:49:3621 days ago
Last commit2026-10-22 06:23:1426 days ago

CommitLatest commit

committed by neverbiasu. Category: Bug Fixes & Stability Improvements. Commit message: fix(mermaid-diagram): don't print "Syntax valid" when the render comm….

26b95cf neverbiasu 2026-10-07

Next stepsNext steps