Claude Skills · Documents & Spreadsheets

Proof Derivation Forensics

wanshuiyin/Anti-Autoresearch

Family-G proof & derivation integrity forensics: does a THIRD PARTY's written proof/derivation actually establish its theorem, or does it skip an obligation, assume its own conclusion, take an invalid step, drift a symbol's meaning, or smuggle an unstated assumption? Decides from the WRITTEN proof/derivation — verdict-bearing at L1 (the LaTeX source; PDF-extracted math is unreliable, so an L0 PDF-only run surfaces info only) — never asserts 'fabricated', only that the step shown does not hold. A fresh cross-model reviewer reads the theorem/proof + an extraction-only obligation scaffold and pro...

★ 149 Synced 4 hours ago View SKILL.md

At a glance

Documents & Spreadsheets Manual install Python Actively maintained

This skill is for Documents & Spreadsheets and helps you audit proof validity in written arguments, identify logical gaps in derivations, and verify mathematical reasoning steps.

Install git clone --depth 1 https://github.com/wanshuiyin/Anti-Autoresearch cp -r Anti-Autoresearch/skills/proof-derivation-forensics ~/.claude/skills/proof-derivation-forensics
Can use BashReadWriteMCP

Setup, runtime and requirements describe wanshuiyin/Anti-Autoresearch, the repo this skill ships in.

Mathematical LogicProof VerificationForensic AnalysislatexFormal Reasoning

Also in wanshuiyin/Anti-Autoresearch

View the repo
Adversarial Case Builder Code Review & Testing

Synthesize the single strongest EVIDENCE-BOUND reviewer case to reject a paper, built ONLY from the evidence ledger (claims.json) + the othe...

AI Style Impressions Code Review & Testing

Transparent, itemized impressions of AI-generated WRITING STYLE — the repo's ONLY non-integrity track. Two passes: a deterministic defensive...

Anti Autoresearch Presentations

End-to-end substantive-integrity forensic sweep of a research paper (especially autoresearch / AI-Scientist-style output). Orchestrates the...

Audit whether a paper's baseline comparisons are COMPLETE, FAIR, and SIGNIFICANT: a required recent SOTA baseline is missing while 'best/SOT...

Citation Forensics Code Review & Testing

Citation-integrity forensics: is every reference real, correctly attributed, and used in a context the cited work actually supports? Catches...

Consistency Audit Documents & Spreadsheets

Flagship intra-paper self-consistency forensics: does the paper contradict ITSELF across abstract/intro/tables/body/appendix, and does the m...

Eval Design Forensics Code Review & Testing

Audit whether a paper's EVALUATION DESIGN actually measures what it claims and whether its reporting is complete — the validity layer family...

Evidence Ledger Documents & Spreadsheets

Build the deterministic evidence ledger (artifact_manifest.json + claims.json) that every other Anti-Autoresearch auditor reads. One pass in...

Experiment Forensics Code Review & Testing

Audit experiment integrity against the evidence ledger. At L2 (repo + result files present) a fresh cross-model reviewer reads the eval code...

MEMO-ONLY prior-work overlap advisory: surfaces the two ADVISORY taxonomy signals neither a tool nor a model can decide from the paper alone...

Presentation Signals Presentations

Checkable-ish surface presentation signals a reviewer notices first — duplicate/near-identical tables, leftover pipeline/template strings, t...

Other Documents & Spreadsheets skills

PDF anthropics/skills

Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining o...

Canvas Design anthropics/skills

Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a pos...

DOCX anthropics/skills

Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or Word templates (.dotx files). Tr...

XLSX anthropics/skills

Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or...

To Spec mattpocock/skills

Turn the current conversation into a spec and publish it to the project issue tracker — no interview, just synthesis of what you've already...

Handoff mattpocock/skills

Compact the current conversation into a handoff document for another agent to pick up.