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.
npx skills add EvoScientist/EvoSkills --skill paper-reviewgit clone --depth 1 https://github.com/EvoScientist/EvoSkillsWrote 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.
[](https://agentmods.dev/skills/evoscientist/evoskills/paper-review)<a href="https://agentmods.dev/skills/evoscientist/evoskills/paper-review"><img src="https://agentmods.dev/badge/skills/evoscientist/evoskills/paper-review/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/evoscientist/evoskills/paper-review"><img src="https://agentmods.dev/badge/skills/evoscientist/evoskills/paper-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00200 | $0.03766 |
| Opus 5.5 | $0.00080 | $0.01506 |
| Sonnet 5.5 | $0.00040 | $0.00753 |
| Haiku 4.5 | $0.00020 | $0.00377 |
Grade A, and why
paper-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 27d 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.
How it starts
The opening of the file, as written. The whole thing — 288 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Paper Review
A systematic approach to self-reviewing academic papers before submission, run as three passes: an adversarial deep read, a checklist sweep (5 aspects, reverse-outlining, figure/table quality), and mechanical consistency scans plus an experimental protocol audit. Ends with rebuttal preparation.
When to Use This Skill
- User wants to review or check a paper draft before submission
- User asks for feedback on paper quality or completeness
- User wants to prepare for potential reviewer criticism
- User mentions "review paper", "check my draft", "self-review"
If the user has already received reviewer comments and needs to write a rebuttal, use the
paper-rebuttalskill instead.
Prerequisites
Before starting review, confirm the paper-writing handoff checklist is satisfied: all sections drafted, claims anchored to evidence, limitation section present, figures finalized, and no unresolved \todo{} markers. If any item is incomplete, finish writing before reviewing.
How to Run the Review: Three Passes
Run the review as three separate passes, in this order, and merge findings only at the end. Do not start from the checklists: a checklist primes you to see only what it names, and the flaws that kill papers in review are often the ones no checklist question points at.
Pass 1 — Adversarial deep read (checklists closed)
Read the paper end-to-end as a skeptical expert reviewer, before consulting any checklist in this skill. Chase cross-section threads as you read:
- Does the evidence actually support each claim at the place it is made?
- Does an assumption stated in the setup ever get revisited — or quietly violated — later?
- Do the numbers quoted in prose match the tables? Does the conclusion deliver what the abstract promised?
- Would this method survive outside the paper's exact setting?
Write down every suspicion with its location, including ones you cannot yet prove — see Calibrated Suspicion below for how to phrase and mark them. This pass is where hidden, cross-section flaws surface; no checklist replaces it.
What ships with it
4 files 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.
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.
- 27d ago Changed · +70 lines · +23 tokens per session 73b01c2ba9a8
- 1mo ago First seen · 218 lines · 177 tokens per session scan A e86ffe859b37
paper-review is a skill published in the GitHub repository EvoScientist/EvoSkills (481 stars, last pushed today), licensed Apache-2.0. It adds 200 tokens to every session and 3,766 once invoked, about $0.0008 per session on Opus 5.5. 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.
Other skills, from other repositories
deltasci
Two-perspective co-reasoning for AI4Science hypothesis generation. Runs a structured 4-round dialogue between a domain scientist (parameterized by a domain pack) and an ML engineer, producing a grounded, falsifiable research hypothesis that is honest about the AI's training-distribution edges. Domain-agnostic via…
LQF_Machine_Learning_Expert_Guide
LQF Machine Learning Expert Guide - Routed skill for ML/Statistical Modeling with Critical Discussion Mode. Triggers on: machine learning, modeling, prediction, training, classification, regression, clustering, deep learning, neural network, model evaluation, feature engineering, hyperparameter tuning, overfitting…
paper-2-web
Use when converting academic papers into dissemination assets such as Paper2Web websites, Paper2Video video abstracts, or Paper2Poster conference posters from LaTeX or PDF sources.
get-available-resources
This skill should be used at the start of any computationally intensive scientific task to detect and report available system resources (CPU cores, GPUs, memory, disk space). It creates a JSON file with resource information and strategic recommendations that inform computational approach decisions such as whether to…
plotly
Interactive scientific and statistical data visualization library for Python. Use when creating charts, plots, or visualizations including scatter plots, line charts, bar charts, heatmaps, 3D plots, geographic maps, statistical distributions, financial charts, and dashboards. Supports both quick visualizations (Plotly…
vss-generate-video-calibration
Use this skill when running or tuning AutoMagicCalib on local MP4s, RTSP, or the bundled sample dataset, or when deploying vss-auto-calibration. Do not use for non-AMC calibration or runtime analytics.