brycewang-stanford/Auto-Empirical-Research-Skills / skills/14-luischanci-claude-code-research-starter/dot-claude/skills/review-paper
review-paper
VerifiedComprehensive manuscript review covering argument structure, identification strategy, econometric specification, citation completeness, and potential referee objections.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 1.8 KB |
SKILL.md
View on GitHub---
name: review-paper
description: Comprehensive manuscript review covering argument structure, identification strategy, econometric specification, citation completeness, and potential referee objections.
disable-model-invocation: true
argument-hint: "[paper filename in master_supporting_docs/ or path to .tex/.pdf]"
allowed-tools: ["Read", "Grep", "Glob", "Write", "Task"]
---
## Review Paper
Produce a thorough referee-style review of an academic manuscript.
### Steps
1. **Identify the paper**: Use `$ARGUMENTS`. Check `master_supporting_docs/supporting_papers/` or the paper folder.
2. **Evaluate across 6 dimensions** (rate each 1-5):
- **Argument Structure:** Research question clarity, logical flow, evidence support, limitations acknowledged
- **Identification Strategy:** Causal claim credibility, identifying assumptions stated, threats discussed, robustness checks proposed
- **Econometric Specification:** Standard errors appropriate, functional form justified, sample selection discussed, multiple testing addressed, economic meaningfulness vs statistical significance
- **Literature Positioning:** Key citations present, accurate characterization, clear differentiation, missing citations identified
- **Writing Quality:** Clarity, tone, notation consistency, abstract quality, self-contained tables/figures
- **Presentation:** Table/figure design, notation consistency across sections, typos, paper length
3. **Generate 3-5 likely referee objections** with suggested responses.
4. **Overall recommendation:** Strong Accept / Accept / Revise & Resubmit / Reject.
5. **Save report** to `quality_reports/paper_review_[sanitized_name].md`.
### Notes
- Be constructive. Identify strengths alongside weaknesses.
- Distinguish CRITICAL (math wrong) from MAJOR (missing discussion) from MINOR (could be clearer).
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| add-product-e2e-evalpaperclipai/paperclipAdd or extend a Paperclip full-stack runner E2E workflow, fixture, matcher, or report evidence path for local or Daytona execution. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| add-runner-evalpaperclipai/paperclipAdd or extend a Paperclip Runner protocol evaluation definition, roster, assertion, or report fixture with provenance and narrow validation. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| diagnose-why-work-stoppedpaperclipai/paperclipCompatibility entry point for failed, stalled, looping, or over-recovered Paperclip work. Use fix-failed-paperclip-run for the full diagnosis, regression, repair, real verification, and green-PR workflow; honor an explicitly requested diagnosis-only scope. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| fix-failed-paperclip-runpaperclipai/paperclipDiagnose and fix failed, stuck, slow, or incorrectly blocked Paperclip tasks and runs. Use with a task/run URL or failure report to trace the root cause, prove a regression red then green, check second-order effects, verify the real workflow, and deliver a PR with passing checks. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |