Home / wanshuiyin / anti-autoresearch · GitHub

eval-design-forensics SKILL.md skillA

eval-design-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/eval-design-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/eval-design-forensics/SKILL.md
Versions recorded: 5
Latest version: git:20260810.98a75fc, committed Aug 10, 2026
First version recorded: Jun 27, 2026
Size: 63,506 bytes
Repository stars: 179
License: MIT

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 / pretraining-contamination subtypes hand off as needs_external_check, naming but NEVER running…

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

# Eval-Design Forensics — does the evaluation measure what the paper claims?

Audit evaluation-design and reporting validity for: **$ARGUMENTS** (requires
`claims.json` from `/evidence-ledger`). Emit span-anchored
`eval-design-forensics.findings.json`. This skill computes **no 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 (or a repo arrives,
> raising the observability level), not with the clock. Schedule the *external wait
> that precedes it* — ledger built (or artifacts released → L2) → audit **once**.
> (Mirrors ARIS's external-cadence doctrine.)

> Adapted from the ML-evaluation-methodology literature — the leakage taxonomy of
> Kapoor & Narayanan (2023), the LLM-as-judge validity work (MT-Bench
> self-enhancement, self-preference, position bias), and the "Show Your Work" /
> reproducibility-checklist reporting norms — reframed to audit a **third party's**
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint

mdr add wanshuiyin/anti-autoresearch/eval-design-forensics@sha256:8c20d1e39a5e5417

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_ai2k2dpcjw5egloz.svg)](https://markdownregistry.com/a/art_ai2k2dpcjw5egloz)

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

Versions

The registry has recorded 5 versions of this file, between Jun 27, 2026 and Aug 10, 2026, about one every 11 days.

version	committed	commit	size	audit
git:20260810.98a75fc latest	2026-08-10	98a75fc	63,506 B	A	view · diff
git:20260710.16f7480	2026-07-10	16f7480	63,680 B	A	view · diff
git:20260710.a1a963f	2026-07-10	a1a963f	63,341 B	A	view · diff
git:20260628.b35080d	2026-06-28	b35080d	62,924 B	A	view · diff
git:20260627.c379c75	2026-06-27	c379c75	62,924 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 (63506 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_ai2k2dpcjw5egloz
GET https://markdownregistry.com/api/v1/resolve?ref=wanshuiyin/anti-autoresearch/eval-design-forensics
GET https://markdownregistry.com/api/v1/blob/8c20d1e39a5e5417d771604ecd8b0f081458feae840168ebc701be66afc04dd4

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.