run-cold-review-panel SKILL.md skillA

run-cold-review-panel from gxcaesar/open-research-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add gxcaesar/open-research-skills/run-cold-review-panel@git:20260909.71c1b78

Pins git:20260909.71c1b78 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
gxcaesar/open-research-skills
Path
skills/run-cold-review-panel/SKILL.md
Versions recorded
1
Latest version
git:20260909.71c1b78, committed Sep 9, 2026
Size
4,373 bytes
Repository stars
63
License
Apache-2.0

Use when a manuscript you wrote is nearly finished and needs a hostile read before it is submitted, including a mock review, a simulated reviewer panel, a pre-submission review, red-team the paper, asking whether this would get rejected, or checking which reviewer objection the paper cannot survive. Use for your own unsubmitted manuscript; reviewing someone else's submission as an invited referee is a different task.

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

# Run a Cold Review Panel

Read your own manuscript with reviewers that have never seen the project. The value comes
entirely from what they do not know: an author's summary of the work repairs, in the
reading, exactly the gaps a reviewer would have fallen into.

The panel is inbound. The manuscript is yours and has not been submitted.

## Select one mode

| Mode | Responsibility | Read first |
|---|---|---|
| `isolation-manifest` | Construct and prove the reviewers' context, from the filesystem rather than from assertion | `references/isolation.md` |
| `lens-assignment` | Assign the reading lenses and the model families that carry them | `references/lenses.md` |
| `artifact-execution` | Have one reviewer actually run the released artifact and report what happened | `references/artifact-execution.md` |
| `meta-review` | Adjudicate the reports into one decision with prioritised repairs | `references/meta-review.md` |

## Resolve the installed skill and components

Resolve `SKILL_DIR` as the directory containing this `SKILL.md`. Every runtime resource
is below that directory; never resolve through a package parent.

## Prove the isolation, do not assert it
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add gxcaesar/open-research-skills/run-cold-review-panel@sha256:3edd463f28e12928

The line at the top of this page pins the label git:20260909.71c1b78, 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_t5uajz2jfk3ok3bs.svg)](https://markdownregistry.com/a/art_t5uajz2jfk3ok3bs)

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

Versions

The registry has recorded 1 version of this file, committed on Sep 9, 2026.

versioncommittedcommitsizeaudit
git:20260909.71c1b78 latest2026-09-09 71c1b78 4,373 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 (4373 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

gxcaesar/open-research-skills · 63 stars · license Apache-2.0 · pushed 2026-09-23 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_t5uajz2jfk3ok3bs
GET https://markdownregistry.com/api/v1/resolve?ref=gxcaesar/open-research-skills/run-cold-review-panel
GET https://markdownregistry.com/api/v1/blob/3edd463f28e12928d87f7c2ab375cd3c64016b8663423fd38f4eda83a290fae5

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 gxcaesar/open-research-skills

build-scientific-visualizations SKILL.md skill
gxcaesar/open-research-skills · skills/build-scientific-visualizations/SKILL.md · Use when creating, redesigning, planning, or visually auditing scientific figures, flowcharts, method schematics or…
git:20260915.f147274 · audit A · 63 stars
develop-method-to-sota SKILL.md skill
gxcaesar/open-research-skills · skills/develop-method-to-sota/SKILL.md · Use when a method is not yet beating its baseline and the next change has to be chosen, including improving a model…
git:20260909.71c1b78 · audit A · 63 stars
prepare-conference-manuscripts SKILL.md skill
gxcaesar/open-research-skills · skills/prepare-conference-manuscripts/SKILL.md · Use when preparing, drafting, revising, polishing, rebutting, auditing, anonymizing, packaging, or checking a…
git:20260910.8ef32d9 · audit A · 63 stars
prepare-journal-manuscripts SKILL.md skill
gxcaesar/open-research-skills · skills/prepare-journal-manuscripts/SKILL.md · Use when preparing, drafting, revising, polishing, auditing, or packaging a journal manuscript, abstract, statistical…
git:20260910.8ef32d9 · audit A · 63 stars
release-research-artifacts SKILL.md skill
gxcaesar/open-research-skills · skills/release-research-artifacts/SKILL.md · Use when packaging the code and data a reader or reviewer will download, including releasing the code for a paper…
git:20260910.fb2f39d · audit A · 63 stars
research-publication-pipeline SKILL.md skill
gxcaesar/open-research-skills · skills/research-publication-pipeline/SKILL.md · Use when selecting, starting, or resuming an evidence-gated research route for a top computer-science venue or…
git:20260915.91a4bb2 · audit A · 63 stars
review-others-manuscripts SKILL.md skill
gxcaesar/open-research-skills · skills/review-others-manuscripts/SKILL.md · Use when acting as an invited referee on someone else's submission, including writing a referee report, drafting…
git:20260909.71c1b78 · audit A · 63 stars
survey-and-audit-novelty SKILL.md skill
gxcaesar/open-research-skills · skills/survey-and-audit-novelty/SKILL.md · Use when deciding whether a research direction is still open, including a literature survey that has to end in a…
git:20260909.71c1b78 · audit A · 63 stars
writing-funding-proposals SKILL.md skill
gxcaesar/open-research-skills · skills/writing-funding-proposals/SKILL.md · Use when writing a research funding proposal: establishing current policy or authority, organizing evidence, mapping…
git:20260910.b487f4a · audit A · 63 stars

Every file in gxcaesar/open-research-skills

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