This walks you through a structured self-review before you submit your own academic paper. It's not for peer reviewing someone else's work. The core is a five-aspect checklist covering contribution sufficiency, writing clarity, results quality, testing completeness, and method design flaws. What makes it interesting is the counterintuitive protocol: simulate writing a rejection of your own paper first, deliberately delete one unsupported claim, and promote a limitation to the main text instead of hiding it. It also includes reverse-outlining to check logical flow and a pointed reminder that every claim in your abstract needs experimental support. Use this when you want to stress-test your draft and prepare for the worst reviewers before they arrive.

skills.sh installs
521
GitHub stars
488
last updated
Aug 21, 2026

Install

$ npx -y skills add evoscientist/evoskills --skill paper-review --agent claude-code

Installs into .claude/skills of the current project.

Files

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-rebuttal skill 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

Sponsors

Details

Repository
github.com/evoscientist/evoskills
Categories
Testing & QA, Git & Pull Requests, Documentation, Code Review & Quality, Design & UI/UX
First seen
Jun 3, 2026

More from evoscientist/evoskills

All 14
1tldraw avatarwrite-unit-teststldraw/tldrawWriting unit and integration tests for the tldraw SDK. Use when creating new tests, adding test coverage, or fixing failing tests in packages/editor or packages503skills.sh installs
2longbridge avatarlongbridge-risk-analysislongbridge/skillsRisk measurement and stress testing via Longbridge — computes VaR (historical simulation / parametric), CVaR (expected shortfall), max drawdown, Sharpe ratio, C496skills.sh installs
3parcadei avatarcomplete-skillparcadei/continuous-claude-v3A complete skill for E2E testing487skills.sh installs
4pedronauck avatarreactpedronauck/skillsReact 19 development under the React Compiler. Use when writing React components or hooks, deciding whether a useMemo/useCallback/memo belongs in the code, diag473skills.sh installs
5jezweb avataragent-browserjezweb/claude-skillsBrowser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking scr469skills.sh installs
6pedronauck avataragent-browserpedronauck/skillsAutomates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web 466skills.sh installs