brycewang-stanford/respond-to-referee
skills/41-sticerd-eee-sewage-econometrics-check/skills/respond-to-referee/SKILL.md
Structure point-by-point referee responses for the sewage-house-prices paper. Classifies each comment (NEW ANALYSIS / CLARIFICATION / REWRITE / DISAGREE / MINOR), produces a tracking document, drafts a response letter in LaTeX, and flags items needing new analysis or user judgment. This skill should be used when asked to "respond to referees", "draft revision", "address referee comments", or "R&R".
$ install --global
skillsauthnpx skillsauth add brycewang-stanford/Awesome-Agent-Skills-for-Empirical-Research respond-to-refereeInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: May 20, 2026, 4:59 AM99.4s1 file scanned
SKILL.md
- name:
- respond-to-referee
- description:
- Structure point-by-point referee responses for the sewage-house-prices paper. Classifies each comment (NEW ANALYSIS / CLARIFICATION / REWRITE / DISAGREE / MINOR), produces a tracking document, drafts a response letter in LaTeX, and flags items needing new analysis or user judgment. This skill should be used when asked to "respond to referees", "draft revision", "address referee comments", or "R&R".
- argument-hint:
- [referee report file path]
- allowed-tools:
- ["Read", "Grep", "Glob", "Write", "Edit", "Agent"]
Respond to Referee
Structure a point-by-point response to referee reports for the sewage-house-prices manuscript.
Input: $ARGUMENTS — path to referee report file(s).
Project-Specific Context
Manuscript
- Main document:
docs/overleaf/_main.tex - Sections:
docs/overleaf/*.tex - Bibliography:
docs/overleaf/refs.bib
Analysis
- Scripts:
scripts/R/09_analysis/ - Tables:
output/tables/ - Figures:
output/figures/
Common Referee Concerns for This Paper
- Short EDM panel (2021-2024) — limited time variation
- LSOA FE may not capture neighbourhood-level sorting
- Spill count vs hours as treatment — which matters more?
- External validity beyond England
- Dry spill identification — rainfall threshold sensitivity
- Multiple testing across 6 radii and multiple specifications
Workflow
Step 1: Parse Inputs
- Read referee report(s) from
$ARGUMENTS - Read the manuscript (
docs/overleaf/_main.texand section files) - Scan existing analysis scripts to know what already exists
Step 2: Classify Every Comment
Assign each referee point a classification:
| Class | Action | |-------|--------| | NEW ANALYSIS | Flag for user — requires new R script or specification | | CLARIFICATION | Draft revised text for the relevant section | | REWRITE | Draft structural revision of a section | | DISAGREE | Draft diplomatic pushback — flag for user review (mandatory) | | MINOR | Draft fix directly (typos, formatting, minor edits) |
Step 3: Build Tracking Document
Save to output/log/referee_response_tracker.md:
# Referee Response Tracker
**Date:** YYYY-MM-DD
**Journal:** [if known]
**Decision:** [R&R / Major / Minor]
## Summary
- Referee 1: N comments (X new analysis, Y clarification, Z disagree, W minor)
- Referee 2: N comments (...)
- Editor: N comments (...)
- **Total new analyses required:** X
## Action Items (Priority Order)
### HIGH: New Analysis Required
| # | Ref | Point | Status |
|---|-----|-------|--------|
| 1 | R1.3 | [Brief] | TODO |
### MEDIUM: Clarification / Rewriting
| # | Ref | Point | Status |
|---|-----|-------|--------|
| 1 | R1.1 | [Brief] | TODO |
### FLAGGED: Disagreements (require user review)
| # | Ref | Point | Draft Response |
|---|-----|-------|---------------|
| 1 | R2.5 | [Brief] | [Draft] |
### LOW: Minor Edits
- [ ] R1.7: Fix typo on p. 12
Step 4: Draft Response Letter
Generate LaTeX response letter:
\documentclass[12pt]{article}
\usepackage[margin=1in]{geometry}
\usepackage{xcolor}
\definecolor{response}{RGB}{0,0,128}
\begin{document}
\title{Response to Referee Reports: Sewage in Our Waters}
\author{[Authors]}
\date{\today}
\maketitle
Dear Editor,
We thank the editor and referees for their careful and constructive comments.
We have revised the manuscript to address all points raised.
\bigskip
\textbf{Summary of major changes:}
\begin{enumerate}
\item [Major change 1 — addresses R1.3, R2.1]
\item [Major change 2 — addresses R1.5]
\end{enumerate}
\newpage
\section*{Response to Referee 1}
\subsection*{Comment 1.1}
\textit{[Exact quote of referee comment]}
\medskip
\textcolor{response}{%
\textbf{Response:} [Draft response]
\textbf{Paper change:} [Section X, page Y]
}
\end{document}
Save to output/log/referee_response_[date].tex.
Step 5: Diplomatic Disagreement Protocol
When classification is DISAGREE:
- Open with acknowledgment of the referee's point
- Provide specific evidence (data, results, published work)
- Offer partial concession where possible
- Never say: "The referee is wrong" or "misunderstood"
- Instead say: "We respectfully note...", "Upon reflection, we believe..."
- FLAG prominently for user review
Principles
- The response letter is the authors' voice. Match their academic tone.
- Never fabricate results. Mark NEW ANALYSIS items as TBD until implemented.
- Flag all DISAGREE items. These need human judgment — never resolve disagreements autonomously.
- Prioritize editor's comments. The editor signals which concerns matter most.
- Track everything. Every referee comment appears in both tracker and response letter.
Related Skills
brycewang-stanford/thematic-analysis
development
VerifiedTrustedCommunity
Conduct rigorous thematic analysis (TA) of qualitative data following Braun and Clarke's (2006) six-phase framework. Use whenever the user mentions 'thematic analysis', 'TA', 'Braun and Clarke', 'qualitative coding', 'identifying themes', or asks for help analysing interviews, focus groups, open-ended survey responses, or transcripts to identify patterns. Also trigger for questions about inductive vs theoretical coding, semantic vs latent themes, essentialist vs constructionist epistemology, building a thematic map, or writing up a qualitative findings section. Covers all six phases, the four upfront analytic decisions, the 15-point quality checklist, and the five common pitfalls. Produces a Word document write-up and an annotated thematic map. Does NOT cover IPA, grounded theory, discourse analysis, conversation analysis, or narrative analysis — use a different method for those.
1,685SKILL.mdUpdated Jun 5, 2026
brycewang-stanford/slr-prisma
development
VerifiedTrustedCommunity
Guide users through writing a systematic literature review (SLR) following the PRISMA 2020 framework. Use this skill whenever the user mentions 'systematic review', 'systematic literature review', 'SLR', 'PRISMA', 'PRISMA 2020', 'PRISMA flow diagram', 'PRISMA checklist', or asks for help writing, structuring, or auditing a literature review that follows reporting guidelines. Also trigger when the user asks about inclusion/exclusion criteria for a review, search strategies for databases like Scopus/WoS/PubMed, study selection processes, risk of bias assessment, or narrative synthesis for a review paper. This skill covers the full PRISMA 2020 checklist (27 items), produces a Word document manuscript in strict journal article format, generates an annotated PRISMA flow diagram, and enforces APA 7th Edition referencing throughout. It does NOT cover meta-analysis or statistical pooling. By Chuah Kee Man.
1,685SKILL.mdUpdated Jun 5, 2026
brycewang-stanford/running-placebo-analysis
testing
VerifiedTrustedCommunity
Performs placebo-in-time sensitivity analysis with hierarchical null model and optional Bayesian assurance. Use when checking model robustness, verifying lack of pre-intervention effects, or estimating study power.
1,685SKILL.mdUpdated Jun 5, 2026
brycewang-stanford/running-causalpy-experiments
data-ai
VerifiedTrustedCommunity
Fit, summarize, plot, and interpret a chosen CausalPy experiment. Use after the causal method has been selected, including when configuring PyMC/sklearn models and scale-aware custom priors.
1,685SKILL.mdUpdated Jun 5, 2026