Anti-Autoresearch

In the author's own words, from each skill's SKILL.md.

• adversarial-case-builder

  Synthesize the single strongest EVIDENCE-BOUND reviewer case to reject a paper, built ONLY from the evidence ledger (claims.json) + the other auditors' confirmed findings — never free-floating LLM critique. Two fresh cross-model codex threads: an attack writes the ~200-word rejection paragraph (every accusation tagged to an existing claim_id/finding_id), a defense decomposes it and rules each poi…

  skills/adversarial-case-builder/SKILL.md on GitHub (opens in a new tab)

• ai-style-impressions

  Transparent, itemized impressions of AI-generated WRITING STYLE — the repo's ONLY non-integrity track. Two passes: a deterministic defensive-hedge density screen (tools/check_ai_style.py, AIS-DEFENSIVE-HEDGE) plus a fresh cross-model GROSS-cases-only semantic pass over the 13 AIS-* style tells (broken narrative arc, LLM phrase tics, jargon-stuffing, invented codenames, clause/formula walls, gratu…

  skills/ai-style-impressions/SKILL.md on GitHub (opens in a new tab)

• baseline-comparison-audit

  Audit whether a paper's baseline comparisons are COMPLETE, FAIR, and SIGNIFICANT: a required recent SOTA baseline is missing while 'best/SOTA' is claimed (HP-MISSING-BASELINE); a baseline is undertuned / given less compute-tuning-data, run at a mismatched config, or the equal-budget ablation-as-baseline is absent (HP-WEAK-BASELINE); 'outperforms' is asserted over overlapping error bars or with no…

  skills/baseline-comparison-audit/SKILL.md on GitHub (opens in a new tab)

• citation-forensics

  Citation-integrity forensics: is every reference real, correctly attributed, and used in a context the cited work actually supports? Catches hallucinated references (no paper at the claimed arXiv id/DOI/venue, fabricated authors/year), metadata drift (wrong year/venue/version), and wrong-context citations (a real paper cited for a claim it never makes — or argues against). A hot zone for machine-…

  skills/citation-forensics/SKILL.md on GitHub (opens in a new tab)

• consistency-audit

  Flagship intra-paper self-consistency forensics: does the paper contradict ITSELF across abstract/intro/tables/body/appendix, and does the method DESCRIBED match the method EVALUATED? Needs no external ground truth — works PDF-only (L0). Runs a deterministic arithmetic pass + a fresh cross-model semantic pass, every finding span-anchored to the evidence ledger (claims.json), reviewer≠adjudicator.…

  skills/consistency-audit/SKILL.md on GitHub (opens in a new tab)

• eval-design-forensics

  Audit whether a paper's EVALUATION DESIGN actually measures what it claims and whether its reporting is complete — the validity layer family D (experiment-forensics) cannot reach. Three patterns: train/test leakage means the reported score may not measure generalization (HP-EVAL-LEAKAGE — adopts the Kapoor & Narayanan 8-type / 3-category leakage taxonomy; the illegitimate-proxy / sampling-bias /…

  skills/eval-design-forensics/SKILL.md on GitHub (opens in a new tab)

• evidence-ledger

  Build the deterministic evidence ledger (artifact_manifest.json + claims.json) that every other Anti-Autoresearch auditor reads. One pass inventories artifacts, derives the observability level (L0 PDF-only / L1 +LaTeX / L2 +repo+results) by fixed rule, and extracts span-anchored, hashed, checkable claims (numbers, comparisons, scope, method, baselines, citations, captions, table cells) into claim…

  skills/evidence-ledger/SKILL.md on GitHub (opens in a new tab)

• experiment-forensics

  Audit experiment integrity against the evidence ledger. At L2 (repo + result files present) a fresh cross-model reviewer reads the eval code line-by-line for fake/derived ground truth, score self-normalization, phantom results (a paper number with no backing file/key), dead/uncalled metric code, verified-scope inflation, method-described ≠ method-evaluated drift, synthesized-looking results, plac…

  skills/experiment-forensics/SKILL.md on GitHub (opens in a new tab)

• novelty-duplication-advisory

  MEMO-ONLY prior-work overlap advisory: surfaces the two ADVISORY taxonomy signals neither a tool nor a model can decide from the paper alone — ADV-TRIVIAL-COMBINATION (standard A+B+C / 缝合 stapling) and ADV-DUPLICATE-PUBLICATION (repackaged / duplicate submission). The executor RETRIEVES candidate prior work (DBLP fuzzy-title + boolean · WebSearch · WebFetch) from the paper's own title + contribut…

  skills/novelty-duplication-advisory/SKILL.md on GitHub (opens in a new tab)

• presentation-signals

  Checkable-ish surface presentation signals a reviewer notices first — duplicate/near-identical tables, leftover pipeline/template strings, too-few or LLM-looking figures, and page-padding. AUXILIARY ONLY and weak by design: a deterministic pass (tools/check_presentation.py — dup-table + pipeline-artifact) plus a fresh cross-model GROSS-cases-only semantic pass (thin-float, LLM-figure, page-paddin…

  skills/presentation-signals/SKILL.md on GitHub (opens in a new tab)

• proof-derivation-forensics

  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…

  skills/proof-derivation-forensics/SKILL.md on GitHub (opens in a new tab)

• anti-autoresearch

  End-to-end substantive-integrity forensic sweep of a research paper (especially autoresearch / AI-Scientist-style output). Orchestrates the whole pipeline: ingest (arxiv-id | pdf | dir → working dir + pdftotext for L0) → /evidence-ledger (artifact manifest + observability level L0/L1/L2 + span-anchored claims.json) → fan out the integrity auditor skills (consistency, citation, baseline, experimen…

  workflows/anti-autoresearch/SKILL.md on GitHub (opens in a new tab)

No skill matches that filter.

Similar skills

• Auto-claude-code-research-in-sleepby wanshuiyin ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, a… 17.5k stars · 30 skills
• academic-research-skillsby Imbad0202 Academic Research Skills for Claude Code: research → write → review → revise → finalize 52.3k stars · 4 skills
• scientific-agent-skillsby K-Dense-AI Turn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 250,000+ scientists worldwide. 177 ready-to-use va… 50.5k stars · 30 skills
• AI-Research-SKILLsby Orchestra-Research Comprehensive open-source library of AI research and engineering skills for any AI model. Package the skills and your claude code/codex/gem… 13.6k stars · 30 skills
• autoresearchby uditgoenka Claude Autoresearch Skill — Autonomous goal-directed iteration for Claude Code. Inspired by Karpathy's autoresearch. Modify → Verify → Keep… 6.6k stars · 1 skill
• ECCby affaan-m The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Cod… 280k stars · 30 skills