peer-review-simulator
Skill for simulating peer review feedback on manuscripts
npx skills add a5c-ai/babysitter --skill peer-review-simulator --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Peer Review Simulator Skill ## Purpose Simulate peer review feedback on manuscripts to identify potential issues and improve quality before submission. ## Capabilities - Analyze manuscript quality - Identify methodological issues - Check statistical validity - Assess presentation clarity - Generate reviewer comments - Prioritize improvements ## Usage Guidelines 1. Load manuscript 2. Analyze structure 3. Review methodology 4. Check statistics 5. Generate feedback 6. Prioritize issues ## Process Integration Works within scientific discovery workflows for: - Pre-submission review - Quality improvement - Manuscript refinement - Author preparation ## Configuration - Review criteria - Strictness levels - Focus areas - Output formats ## Output Artifacts - Review reports - Comment summaries - Issue prioritization - Improvement suggestions
- Purpose
- Capabilities
- Usage Guidelines
- Process Integration
- Configuration
- Output Artifacts
What does the peer-review-simulator skill do?
Skill for simulating peer review feedback on manuscripts
How do I install it?
Run `npx skills add a5c-ai/babysitter --skill peer-review-simulator --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From a5c-ai/babysitter, a repository with 1,642 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.
