Anti-Autoresearch vs everything-claude-code

Side-by-side AI skills comparison

Anti-Autoresearch

wanshuiyin

everything-claude-code

affaan-m

Stars

185,940

Forks

28,768

View Anti-Autoresearch View everything-claude-code

Topics

ai-generated-contentai-researchai-scientistarisautoresearchclaudeclaude-codeclaude-code-skillscodexforensicsgptllmllm-agentsmachine-learningmcpml-researchopenaipaper-reviewpeer-reviewresearch-integrity

ai-agentsanthropicclaudeclaude-codedeveloper-toolsllm

Description

Don't trust an autoresearch paper at face value. Reviewer-side integrity forensics (self-consistency + fabrication), deterministic verdict. 61 signals: 46 integrity hack-patterns (families A–H, verdict-bearing) + 13 zero-weight AI writing-style impressions (AIS) + 2 advisory. Not an opaque AI-text classifier. The dual of ARIS.

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.