ai-style-impressions
FeaturedTransparent, 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, gratuitous pseudocode, bullet overuse, bold-module spam, restatement loops, focus drift, single-style figures, appendix dumping). Every finding is named, LOCATED, span-anchored to the evidence ledger (claims.json), carries not_integrity_finding:true + false_positive_risk:high + an fp_case, and gets ZERO verdict weight: the adjudicator forces it to info, excludes it from overall_verdict, and renders it in a SEPARATE report section. NOT an AI-text classifier — no scores, no "this is AI-written", no authorship probability; a paper can be CLEAN_GIVEN_EVIDENCE and still list many. Emits ai-style-impressions.findings.json; compu
Install
Quality Score: 90/100
Skill Content
Details
- Author
- wanshuiyin
- Repository
- wanshuiyin/Anti-Autoresearch
- Created
- 2 months ago
- Last Updated
- 2 days ago
- Language
- Python
- License
- MIT
Integrates with
Similar Skills
Semantically similar based on skill content — not just same category
signs-of-ai
Detect and remove the tells of AI-generated writing in BOTH English and Spanish, and read back the evidence honestly. Use when the user asks to "de-AI" / "humanize" / "un-slop" a draft, to examine whether text carries the tells (delve, tapestry, "it's not just X, it's Y", "here's the thing", em-dash overuse, an assistant's own closing line left in the document), to compare documents for overlap, or mentions signs-of-ai / SignsOfAI. Backed by the SignsOfAI engine — for a measured 0–100 score, sentence-rhythm burstiness, originality, citations, a writer baseline or perplexity, hand off to that engine (web app, CLI or MCP server) as described below. It cannot determine who wrote a text and must never imply that it can.
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, experiment, presentation, proof-derivation, eval-design — each reads the ledger, emits span-anchored findings) + the zero-verdict-weight AIS writing-style track → advisory memos (/adversarial-case-builder + /novelty-duplication-advisory, no verdict weight) → deterministic tools/adjudicate_findings.py (--ledger REQUIRED) → reviewer-ready Integrity Forensics Report. Cross-model (fresh codex per dimension) and reviewer≠adjudicator: the model proposes findings, the deterministic adjudicator decides the verdict. Observability-aware, detect-only, never an opaque AI-text classifier (a separate zero-weight AIS section lists AI writing
ai-writing-audit
Audit and repair text that reads as machine written. Any length, any format: a two line direct message, an automated message sequence, an objection reply, a caption, a carousel slide, a spoken script, a landing page, an essay. Runs two layers, surface tells and discourse tells, behind a false positive gate, and returns findings with a repair for each. Use on an existing draft. Do not use to compose a first draft.