novelty-duplication-advisory SKILL.md skillA

novelty-duplication-advisory from wanshuiyin/anti-autoresearch is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add wanshuiyin/anti-autoresearch/novelty-duplication-advisory@git:20260810.98a75fc

Pins git:20260810.98a75fc in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
wanshuiyin/anti-autoresearch
Path
skills/novelty-duplication-advisory/SKILL.md
Versions recorded
5
Latest version
git:20260810.98a75fc, committed Aug 10, 2026
First version recorded
Jun 28, 2026
Size
70,850 bytes
Repository stars
179
License
MIT

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 + contribution spans in the evidence ledger; TWO fresh cross-model codex reviewers (one per axis) LAY OUT the…

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Novelty & Duplication Advisory — the overlap a reviewer should weigh

Lay out, for **$ARGUMENTS** (a paper-dir or a `claims.json` from `/evidence-ledger`), the
candidate prior-work overlap a human reviewer should weigh for two reviewer-judgment signals
— **trivial combination** ("standard A+B+C") and **duplicate publication** ("repackaged prior
work"). Retrieve candidates, map them side-by-side against the paper's ledger-anchored
contribution, and emit `novelty-duplication-advisory.memo.md`. Run AFTER `/evidence-ledger`
(so `claims.json` exists). This skill **decides nothing** — it never rules "trivial" or
"duplicate", and the deterministic adjudicator caps it at `info`.

> 🔒 **Do not wrap this skill in `/loop`, `/schedule`, or `CronCreate`.** It retrieves
> external prior work once and synthesizes it into one advisory memo. Even though it is
> **memo-only** (the adjudicator caps it at `info`, so it adds no verdict weight), the
> no-new-signal cadence rule still applies: its output changes only when the **ledger / the
> paper / the literature** change, never with the wall clock. It is tempting to re-fire on a
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add wanshuiyin/anti-autoresearch/novelty-duplication-advisory@sha256:fe335ab9fec290ec

The line at the top of this page pins the label git:20260810.98a75fc, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_a5lhjw77ki62poth.svg)](https://markdownregistry.com/a/art_a5lhjw77ki62poth)

4 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 5 versions of this file, between Jun 28, 2026 and Aug 10, 2026, about one every 11 days.

versioncommittedcommitsizeaudit
git:20260810.98a75fc latest2026-08-10 98a75fc 70,850 BA view · diff
git:20260810.94439ad2026-08-10 94439ad 70,822 BA view · diff
git:20260710.a1a963f2026-07-10 a1a963f 70,817 BA view · diff
git:20260628.b35080d2026-06-28 b35080d 70,496 BA view · diff
git:20260628.21beec62026-06-28 21beec6 70,496 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (70850 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

wanshuiyin/anti-autoresearch · 179 stars · license MIT · pushed 2026-10-30 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_a5lhjw77ki62poth
GET https://markdownregistry.com/api/v1/resolve?ref=wanshuiyin/anti-autoresearch/novelty-duplication-advisory
GET https://markdownregistry.com/api/v1/blob/fe335ab9fec290ecb84ee4b02cca63a362d5906f59549f080affb42ee112f518

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from wanshuiyin/anti-autoresearch

DESIGN.md DESIGN.md file
wanshuiyin/anti-autoresearch · DESIGN.md
git:20260810.98a75fc · audit A · 179 stars
adversarial-case-builder SKILL.md 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 · 179 stars
ai-style-impressions SKILL.md 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 · 179 stars
baseline-comparison-audit SKILL.md 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 · 179 stars
citation-forensics SKILL.md 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 · 179 stars
consistency-audit SKILL.md 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 · 179 stars
eval-design-forensics SKILL.md 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 · 179 stars
evidence-ledger SKILL.md 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 · 179 stars
experiment-forensics SKILL.md 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 · 179 stars
presentation-signals SKILL.md 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 · 179 stars
proof-derivation-forensics SKILL.md 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 · 179 stars
anti-autoresearch SKILL.md 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 · 179 stars

Every file in wanshuiyin/anti-autoresearch

Browse by kind, by grade A, or by owner.