xueruisu/paper-prism/review-simulator

Claude Code and agent skill by xueruisu/paper-prism

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Use when Codex needs to simulate reviewer feedback, explain reviewer risks, and turn critique into a PaperPRISM revision plan.

Install

npx vskill@latest install xueruisu/paper-prism/review-simulator

SKILL.md

Review Simulator

Read ../_shared/paperprism_codex_native.md before acting.

Goal

Review the current paper or section as a skeptical reviewer and convert feedback into actionable revisions.

Workflow

  1. Read the draft, paper.tex, ClaimEvidenceMap, WritingPlan, and PaperState if available.
  2. Evaluate novelty, technical quality, evidence rigor, clarity, significance, and limitations.
  3. Group issues as must-fix, should-fix, and writing-only.
  4. Map each issue to a claim, section, paragraph, sentence slot, or missing evidence item.
  5. Route evidence gaps to experiment-planner, novelty risks to novelty-evaluator, and prose fixes to paper-writer.
  6. Mark sentence slots verified only after they are already supported and pass review.
  7. Update PaperState with revision tasks.

Rules

  • Do not hide missing evidence as a prose issue.
  • Do not claim reviewer risk decreased unless the underlying evidence or text changed.
  • Keep reviewer comments concrete and actionable.
  • If a review issue requires adding, deleting, or reordering sentences, route to logical-template-builder to revise the ClozeBlueprint before prose repair.
  • Never mark a sentence verified directly from planned.
  • Before final export, report planned_sentences and unsupported_sentences; block export unless both are zero.

Expected Outputs

  • Reviewer-style critique.
  • Prioritized revision plan.
  • Slot-level or claim-level revision targets when possible.
  • Minimal user questions for blocked revisions.

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
0

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/xueruisu/paper-prism/review-simulator/badge)](https://verified-skill.com/skills/xueruisu/paper-prism/review-simulator)

Something wrong with this skill or its page? Tell us.