Screened · automated checks passed

auto-review-loop

from wanshuiyin/Auto-claude-code-research-in-sleep · ★ 13,472 on GitHub · found by our crawler 2026-07-07

What the author says it does

Autonomous multi-round research review loop. Repeatedly reviews via external reviewer backend (Codex or manual), implements fixes, and re-reviews until positive assessment or max rounds reached. Use when user says "auto review loop", "review until it passes", or wants autonomous iterative improvement.

Quoted from the skill's own SKILL.md trigger description — this is what tells Claude when to activate it. Not yet verified by us.

Automated screening

95/100 validator score

Scored by the same rules as our free SKILL.md validator: trigger description quality, body substance, structure. Automated — a human bench test is the next step in the pipeline.

Install (unverified — review first)

git clone https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep
# skill lives at: skills/auto-review-loop/SKILL.md

SkillProof status

This skill is in our test queue. We install every skill in a clean environment, run a trigger battery and score output against a baseline before it earns a catalog page — the full protocol is public. Until then, treat it like any unreviewed dependency: read the SKILL.md and any scripts before installing.

Already tested in Coding & Development

  • Pinme Auth ★ 10.0/10 TypeScript reference for PinMe Worker auth: create/verify/list Identity Platform users.
  • Code Health Check ★ 10.0/10 Read-only, sub-agent-forked code health scanner with a fixed severity-graded report format.
  • S&box ★ 10.0/10 Blocks Unity muscle memory when writing s&box (Source 2 / Facepunch) C# components, Razor UI, and networking.
  • Coding Agent Sessions ★ 10.0/10 Finds and reconstructs real coding-agent session transcripts across Claude, Codex, OpenCode, and more.

Top 10 Coding skills, ranked →