wanshuiyin/anti-autoresearch

13 agent markdown files indexed from wanshuiyin/anti-autoresearch. Install any of them pinned to an exact hash with mdr add wanshuiyin/anti-autoresearch/<name>.

DESIGN.md design
wanshuiyin/anti-autoresearch · DESIGN.md
git:20260810.98a75fc · audit A · 156 stars
adversarial-case-builder skill
wanshuiyin/anti-autoresearch · skills/adversarial-case-builder/SKILL.md · Synthesize the single strongest EVIDENCE-BOUND reviewer case to reject a paper, built ONLY from the evidence ledger…
git:20260810.98a75fc · audit A · 156 stars
ai-style-impressions skill
wanshuiyin/anti-autoresearch · skills/ai-style-impressions/SKILL.md · Transparent, itemized impressions of AI-generated WRITING STYLE — the repo's ONLY non-integrity track. Two passes: a…
git:20260810.98a75fc · audit A · 156 stars
baseline-comparison-audit skill
wanshuiyin/anti-autoresearch · skills/baseline-comparison-audit/SKILL.md · Audit whether a paper's baseline comparisons are COMPLETE, FAIR, and SIGNIFICANT: a required recent SOTA baseline is…
git:20260810.98a75fc · audit A · 156 stars
citation-forensics skill
wanshuiyin/anti-autoresearch · skills/citation-forensics/SKILL.md · Citation-integrity forensics: is every reference real, correctly attributed, and used in a context the cited work…
git:20260810.98a75fc · audit A · 156 stars
consistency-audit skill
wanshuiyin/anti-autoresearch · skills/consistency-audit/SKILL.md · Flagship intra-paper self-consistency forensics: does the paper contradict ITSELF across…
git:20260810.98a75fc · audit A · 156 stars
eval-design-forensics skill
wanshuiyin/anti-autoresearch · skills/eval-design-forensics/SKILL.md · Audit whether a paper's EVALUATION DESIGN actually measures what it claims and whether its reporting is complete — the…
git:20260810.98a75fc · audit A · 156 stars
evidence-ledger skill
wanshuiyin/anti-autoresearch · skills/evidence-ledger/SKILL.md · Build the deterministic evidence ledger (artifact_manifest.json + claims.json) that every other Anti-Autoresearch…
git:20260810.98a75fc · audit B · 156 stars
experiment-forensics skill
wanshuiyin/anti-autoresearch · skills/experiment-forensics/SKILL.md · Audit experiment integrity against the evidence ledger. At L2 (repo + result files present) a fresh cross-model…
git:20260810.98a75fc · audit A · 156 stars
novelty-duplication-advisory skill
wanshuiyin/anti-autoresearch · skills/novelty-duplication-advisory/SKILL.md · MEMO-ONLY prior-work overlap advisory: surfaces the two ADVISORY taxonomy signals neither a tool nor a model can decide…
git:20260810.98a75fc · audit A · 156 stars
presentation-signals skill
wanshuiyin/anti-autoresearch · skills/presentation-signals/SKILL.md · Checkable-ish surface presentation signals a reviewer notices first — duplicate/near-identical tables, leftover…
git:20260810.98a75fc · audit A · 156 stars
proof-derivation-forensics skill
wanshuiyin/anti-autoresearch · skills/proof-derivation-forensics/SKILL.md · Family-G proof & derivation integrity forensics: does a THIRD PARTY's written proof/derivation actually establish its…
git:20260810.98a75fc · audit A · 156 stars
anti-autoresearch skill
wanshuiyin/anti-autoresearch · workflows/anti-autoresearch/SKILL.md · End-to-end substantive-integrity forensic sweep of a research paper (especially autoresearch / AI-Scientist-style…
git:20260810.e3d0d7e · audit A · 156 stars

Source

github.com/wanshuiyin/anti-autoresearch · 156 stars · license MIT · pushed 2026-09-09