Home / wanshuiyin / anti-autoresearch · GitHub

proof-derivation-forensics SKILL.md skillA

proof-derivation-forensics 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/proof-derivation-forensics@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/proof-derivation-forensics/SKILL.md
Versions recorded: 5
Latest version: git:20260810.98a75fc, committed Aug 10, 2026
First version recorded: Jun 28, 2026
Size: 54,047 bytes
Repository stars: 179
License: MIT

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.…

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

# Proof & Derivation Forensics — does the written proof hold?

Audit family **G (proof & derivation integrity)** for: **$ARGUMENTS** (requires
`claims.json` from `/evidence-ledger`). A fresh cross-model reviewer reads each
theorem/proof and proposes span-anchored findings; this skill writes
`proof-derivation-forensics.findings.json`. The deterministic adjudicator — not this
skill — computes the verdict.

> 🔒 **Do not wrap this skill in `/loop`, `/schedule`, or `CronCreate`.** It is
> verdict-bearing input — it proposes the findings the deterministic adjudicator
> turns into the report. Re-firing it on a wall-clock timer adds no signal: its
> output changes only when the **paper / ledger** changes, not with the clock.
> Schedule the *external wait that precedes it* — ledger built → audit **once**.
> (Mirrors ARIS's external-cadence doctrine.)

> Broken math is the single most-cited "obviously machine-written" tell in real
> reviews ("过不去的步骤用文字糊弄", "车轱辘话复述当证明", "关键公式符号用反"). Unlike the
> surface signals of family F, family-G flaws are **substantive** and **can be
> critical**: a theorem whose proof is circular, skips a load-bearing obligation, or
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint

mdr add wanshuiyin/anti-autoresearch/proof-derivation-forensics@sha256:ab47d5d0483c7c84

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](https://markdownregistry.com/badge/art_s4wmyli4ert2di5n.svg)](https://markdownregistry.com/a/art_s4wmyli4ert2di5n)

3 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.

version	committed	commit	size	audit
git:20260810.98a75fc latest	2026-08-10	98a75fc	54,047 B	A	view · diff
git:20260710.16f7480	2026-07-10	16f7480	53,943 B	A	view · diff
git:20260710.a1a963f	2026-07-10	a1a963f	53,603 B	A	view · diff
git:20260628.b35080d	2026-06-28	b35080d	53,171 B	A	view · diff
git:20260628.21beec6	2026-06-28	21beec6	53,171 B	A	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 (54047 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_s4wmyli4ert2di5n
GET https://markdownregistry.com/api/v1/resolve?ref=wanshuiyin/anti-autoresearch/proof-derivation-forensics
GET https://markdownregistry.com/api/v1/blob/ab47d5d0483c7c84d72de1fdf3c53ffb07346693fd42b4bc1b1d9d655a626c73

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.