Home / adilshamim8 / claude-research-excellence · GitHub

06_quality_fortress SKILL.md skillC

06_quality_fortress from adilshamim8/claude-research-excellence is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned

mdr add adilshamim8/claude-research-excellence/06_quality_fortress@git:20261030.3e9f75f

Pins git:20261030.3e9f75f in mdr.lock. Pin the fingerprint instead.

Audit grade: C, 14 of 17 checks passed
Kind: SKILL.md skill
Repository: adilshamim8/claude-research-excellence
Path: skills/06_quality_fortress/SKILL.md
Versions recorded: 4
Latest version: git:20261030.3e9f75f, committed Oct 30, 2026
First version recorded: Jun 9, 2026
Size: 11,724 bytes
Repository stars: 9
License: none declared

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

# Skill 06: Quality Fortress (Conference-Grade Expert Peer Review)

## Identity
You are the **Quality Fortress Specialist** — an elite, conference-grade peer reviewer and meta-reviewer engineered to evaluate manuscripts at the level of senior area chairs and editorial boards (*Nature*, *Science*, *NeurIPS*, *ICML*, *ICLR*, *IEEE*, *ACM*, *AAAI*). 

You deploy a multi-agent adversarial panel across **11 technical dimensions** grounded in real-world peer review datasets (**PeerRead corpus: 14,784 paper drafts with 10.7K human expert reviews**, **PeerRead 100-pool benchmark with 83.8% pairwise accuracy**, **AAAI 2026 reverse-prompting calibration**, **OpenReview venue pools**, **VLM multi-modal visual inspection**, **NeurIPS Reproducibility Benchmark**). No flaw survives. Every claim must have an empirical evidence anchor, every figure is audited for aesthetic legibility, every notation is checked for collisions, and every puffery claim is challenged.

---

## Activation Triggers

You can activate the Quality Fortress engine with any of the following standard triggers across Claude Desktop, Cursor, Copilot, or Antigravity:

```
ACTIVATE: QUALITY
review my paper
审稿
@ai-review
```

---
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint

mdr add adilshamim8/claude-research-excellence/06_quality_fortress@sha256:1c84677e6b5e78ed

The line at the top of this page pins the label git:20261030.3e9f75f, 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_63a4kttpo55y6hi4.svg)](https://markdownregistry.com/a/art_63a4kttpo55y6hi4)

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

Versions

The registry has recorded 4 versions of this file, between Jun 9, 2026 and Oct 30, 2026, about one every 48 days.

version	committed	commit	size	audit
git:20261030.3e9f75f latest	2026-10-30	3e9f75f	11,724 B	C	view · diff
git:20260923.bd53285	2026-09-23	bd53285	11,518 B	C	view · diff
git:20260923.6800f56	2026-09-23	6800f56	9,693 B	C	view · diff
git:20260609.deb30f6	2026-06-09	deb30f6	15,115 B	C	view

Audit of the latest version

C 14 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.

fail: Frontmatter block present
fail: Frontmatter declares a name
fail: Frontmatter declares a description
pass: Size between 200 bytes and 200 KB (11724 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

Starting a new one? Use a template for SKILL.md on mdpantry, which passes every one of these checks and says what to change in it.

Source

GitHub

adilshamim8/claude-research-excellence · 9 stars · license none declared · pushed 2026-11-05 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_63a4kttpo55y6hi4
GET https://markdownregistry.com/api/v1/resolve?ref=adilshamim8/claude-research-excellence/06_quality_fortress
GET https://markdownregistry.com/api/v1/blob/1c84677e6b5e78ed98c527ad6edd1492523c020cb9326fde17647c71768d0b4e

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.