What did Hlido score wanshuiyin/Auto-claude-code-research-in-sleep?

wanshuiyin/Auto-claude-code-research-in-sleep scored 82/100 (STEADY) in Hlido's independent, hands-on review.

How much does wanshuiyin/Auto-claude-code-research-in-sleep cost?

Hlido recorded the pricing model as: Open source. Derived from evidence Hlido holds, not vendor-supplied; verify current prices on the vendor's pricing page.

Does any vendor pay Hlido for placement?

No. Hlido takes no money from the agents it rates — scoring weights stay private and the evidence behind every verdict is public.

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

Name: wanshuiyin/Auto-claude-code-research-in-sleep review
Item: wanshuiyin/Auto-claude-code-research-in-sleep
Rating: 82
Author: Hlido Editor

Research · tested 2026-09-30 · by the Hlido desk, not the vendor

In short: Very high-traction, framework-free ML-research skill pack (ARIS) for autonomous overnight research loops — clean checklist, portable across agents.

10 PASS · 0 FAIL of 10 public-surface claims

Visit wanshuiyin/Auto-claude-code-research-in-sleep → scorecard.json

Quick answer

wanshuiyin/Auto-claude-code-research-in-sleep scores 82/100 (STEADY) on Hlido’s independent, hands-on test (reviewed 2026-09-30). STEADY (82) — a perfect checklist on the repo-surface track (every item passes) plus exceptional community traction. Pricing: Open source (free entry point documented).

Hlido Editor · 2026-09-30

ARIS (Auto-Research-In-Sleep) is a set of lightweight, Markdown-only skills for autonomous ML research — cross-model review loops, idea discovery and experiment automation — deliberately built with no framework and no lock-in so it runs under Claude Code, Codex, OpenClaw or any capable LLM agent. On measured signals it is the standout of this batch: 13,480 stars and 1,216 forks is exceptional traction, and it passes every checklist item we test on the surface track, including agent-consumable. The Markdown-only, framework-free design is a genuine strength for the agent-to-agent world we care about — there is nothing to install and nothing to break, so portability is close to free. What the surface track cannot tell us is whether the 'research in sleep' loops actually produce sound results or simply run unattended; overnight autonomy amplifies both good and bad reasoning, and we have not run it. Treat the star count as evidence of strong developer interest in the pattern, not as proof the outputs are trustworthy. As a portable skill layer to study and adapt, it is a strong pick; as an unattended research pipeline, supervise the first several runs.

Why STEADY

STEADY (82) — a perfect checklist on the repo-surface track (every item passes) plus exceptional community traction. Capped below VITAL only by the repo-surface ceiling: we have not hands-on verified that the autonomous loops produce sound research, which overnight autonomy makes the central question.

Public-surface checklist

PASS Repo reachable (required) — GH API 200 for wanshuiyin/Auto-claude-code-research-in-sleep
PASS Readme present (required) — README length 192363
PASS License present (required) — MIT
PASS Install documented (required) — install/usage section found in README
PASS Active 12mo (required) — last push 2d ago
PASS Releases present — latest v0.4.22
PASS Community traction — 13480 stars
PASS Ci or tests — 4 workflow file(s)
PASS Recent commit 90d — last push 2d ago
PASS Agent consumable — MCP server markers in README

What we saw

1 screenshot captured by the Hlido engine during the reviewed run (run-8b3ddac650e1987c-github-com). Our own captures — not vendor marketing material.

wanshuiyin/Auto-claude-code-research-in-sleep — run screenshot 1 (home.png) — home.png

What it does well

Passes every checklist item we test on the surface track, including agent-consumable
Exceptional traction — 13,480 stars, 1,216 forks
Framework-free, Markdown-only: portable across Claude Code, Codex and other agents with nothing to install
MIT-licensed with releases — clear terms and versioned artefacts

What it fails at

Not hands-on tested — whether the autonomous loops produce sound research is unverified
Unattended overnight autonomy amplifies bad reasoning as readily as good; no guardrail evidence on the surface
Star count signals interest in the pattern, not validated output quality

Best for

Researchers wanting a portable, lock-in-free skill layer to adapt
Multi-agent setups (Claude Code / Codex) that value drop-in Markdown skills
Teams comfortable supervising early autonomous runs before trusting them

Not recommended for

Anyone expecting validated, hands-off research output out of the box
Environments that cannot supervise unattended autonomous loops
Buyers who read a high star count as a quality guarantee

Pricing & access

ModelOpen source
Free entry pointYes — a free tier or open-source edition is documented

Derived from Hlido-held evidence only (engine checklist + editorial text); quotes are verbatim from the scorecard; not vendor-supplied; re-derived daily. Verify current prices on the vendor's pricing page. Last verified 2026-07-16.

Related agents

Agent relevance

No programmatic surfaces

Agentic-Commerce Readiness 44/100 · SURFACE-ONLY

Independent readiness for agent delegation & transaction. How it’s scored · check live

Dropped in as Markdown skills that any capable LLM agent (Claude Code, Codex, etc.) reads and executes. No install, no framework — maximally agent-portable.

Agent-friendly score: 8/10

Evidence

— source
— source
— source

scorecard.json · transparency passport · registry · methodology

More: compare agents · best of · developer tools · incident registry

Verdict by Hlido Editor, our automated editorial system · Method: repo-surface-signals+editorial-narrative-v2 · Methodology version 2026.05 ·

How this page was produced. The scores, claim verdicts and evidence come from automated hands-on testing of the product’s public surface. The written analysis is drafted by an AI system, and pages publish without a person reviewing each one. Hlido publishes this record and answers for it — tell us if anything here is wrong and we will correct it.

Embed this trust badge

Live, always-current independent score — free to embed on your site or README. No vendor pays for placement.

Markdown

[![Hlido trust score](https://hlido.eu/badge/wanshuiyin-auto-claude-code-research-in-sleep.svg)](https://hlido.eu/check/?agent=wanshuiyin-auto-claude-code-research-in-sleep)

HTML

<a href="https://hlido.eu/check/?agent=wanshuiyin-auto-claude-code-research-in-sleep"><img src="https://hlido.eu/badge/wanshuiyin-auto-claude-code-research-in-sleep.svg" alt="Hlido trust score"></a>