general-peer-review

general-peer-review is a skill for Claude Code, Codex from learningmatter-mit/AtomisticSkills. It costs 33 tokens per session (1,030 once invoked), scanned A, original, MIT.

A critical review of a research plan, paper, or simulation workflow before it is run or published. It looks for missing comparisons, weak assumptions, statistical problems, and insufficient sampling.

In plain words
What is it for?
Use it to check research proposals, manuscripts, and simulation plans for suitable baselines, evidence, assumptions, and statistical reliability.
Why use it?
It exposes methodological gaps early, when they are easier to fix than after experiments or publication.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/learningmatter-mit/atomisticskills/general-peer-review
Any agent
npx skills add learningmatter-mit/AtomisticSkills --skill general-peer-review
Clone the repo
git clone --depth 1 https://github.com/learningmatter-mit/AtomisticSkills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for general-peer-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/learningmatter-mit/atomisticskills/general-peer-review.svg)](https://agentmods.dev/skills/learningmatter-mit/atomisticskills/general-peer-review)
Your own site
<a href="https://agentmods.dev/skills/learningmatter-mit/atomisticskills/general-peer-review"><img src="https://agentmods.dev/badge/skills/learningmatter-mit/atomisticskills/general-peer-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,030 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00033 $0.01030
Opus 5 $0.00016 $0.00515
Sonnet 5 $0.00007 $0.00206
Haiku 4.5 $0.00003 $0.00103

Measured 4d ago against content hash 8f1546feaa5c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

general-peer-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.agents/skills/general-peer-review/SKILL.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

General Peer Review

Goal

To rigorously evaluate a research plan, manuscript, or simulation workflow prior to execution or publication. This skill acts as an adversarial reviewer, ensuring scientific rigor by identifying methodological gaps, demanding adequate statistical sampling, highlighting weak assumptions, and suggesting necessary baseline comparisons.

Prerequisites

  • A completed or drafted piece of scientific writing (e.g., research_plan.md, manuscript draft, or experimental summary).
  • Sufficient contextual knowledge regarding the specific simulation or machine-learning methodology being proposed.

Instructions

  1. Review Initialization The agent initializes the review process by loading the target document into memory. This can be done by standard reading tools like view_file.

  2. Literature-Based Validation The agent utilizes skills like general-query-literature-database or general-deep-research to ground the review in established scientific facts.

    • Perform a literature search regarding the specific materials, methodologies, or baseline properties stated in the text.
    • Point out discrepancies between the proposed approach and standard practices found in high-impact journals.
  3. Methodological & Reproducibility Critique The agent systematically analyzes the methodology for common theoretical and computational pitfalls:

    • Ensemble & Sampling: Verify if MD simulations are long enough to reach equilibration and if the number of samples is statistically significant.
    • Level of Theory: Question if the chosen MLIP or DFT functional is adequate for the specific property being computed (e.g., PBE vs. r2SCAN, dispersion corrections for molecular systems).
    • System Size: Check if the supercell size is large enough to avoid finite-size effects and self-interaction (e.g., in defect or dopant studies).
    • Hyperparameters: Ensure critical hyperparameter choices (e.g., $k$-point grid density, energy cutoffs, learning rates) are justified.
    • Reproducibility: Are all protocols, scripts, and model checkpoints adequately specified to allow independent reproduction? Have data availability standards been met?

Read the full file on GitHub · 78 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 78 lines · 33 tokens per session scan A 8f1546feaa5c

Subscribe to this mod's changes

general-peer-review is a skill published in the GitHub repository learningmatter-mit/AtomisticSkills (158 stars, last pushed today), licensed MIT. It adds 33 tokens to every session and 1,030 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

audience-aware-communication

Use this skill when writing any explanation, documentation, or response that will be read by someone else. Match vocabulary, depth, and format to the audience's expertise level before writing.

aiming-lab/MetaClaw · 42 tokens

graceful-error-recovery

Use this skill when a tool call, command, or API request fails. Diagnose the root cause systematically before retrying or changing approach. Do not retry the same failing call without first understanding why it failed.

aiming-lab/MetaClaw · 48 tokens

aios-work-dispatch

Decide when a coding agent may use aios work for independent parallel work, preview the dispatch, and require explicit approval before live model execution. TRIGGER: aios work、parallel dispatch、并发派发、independent work items、独立工作项并行、多 agent 派发、multi-agent dispatch.

rexleimo/aios · 70 tokens

skill-constraints

Enforce browser automation safety constraints — tool usage order, anti-detection rules, screenshot discipline, and human-in-the-loop checks. Use when setting up or verifying browser/MCP tool operations, NOT for every skill execution.

rexleimo/aios · 48 tokens

clarify-ambiguous-requests

Use this skill when the user's request is ambiguous, under-specified, or could be interpreted in multiple ways. If proceeding with a wrong assumption would waste significant work, always ask exactly one focused clarifying question before doing anything.

aiming-lab/MetaClaw · 53 tokens

structured-step-by-step-reasoning

Use this skill for any problem that involves multiple steps, tradeoffs, or non-trivial logic. Think out loud before answering to improve accuracy and transparency. Apply whenever the answer is not immediately obvious.

aiming-lab/MetaClaw · 48 tokens