brycewang-stanford/slide-excellence
skills/41-sticerd-eee-sewage-econometrics-check/skills/slide-excellence/SKILL.md
Multi-agent review for research presentation slides in the sewage-house-prices project (visual, econometric fidelity, proofreading, substance). Use for comprehensive quality check before milestones.
$ install --global
skillsauthnpx skillsauth add brycewang-stanford/Awesome-Agent-Skills-for-Empirical-Research slide-excellenceInstall 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, 5:00 AM163.3s1 file scanned
SKILL.md
- name:
- slide-excellence
- description:
- Multi-agent review for research presentation slides in the sewage-house-prices project (visual, econometric fidelity, proofreading, substance). Use for comprehensive quality check before milestones.
- argument-hint:
- [TEX filename]
- allowed-tools:
- ["Read", "Grep", "Glob", "Write", "Task"]
- context:
- fork
Slide Excellence Review
Run a comprehensive multi-dimensional review of research presentation slides. Multiple agents analyze the file independently, then results are synthesized.
Steps
1. Identify the File
Parse $ARGUMENTS for the filename. Resolve path in docs/conferences/.
2. Run Review Agents in Parallel
Agent 1: Visual Audit (slide-auditor)
- Overflow, font consistency, box fatigue, spacing, images
- Save:
docs/conferences/quality_reports/[FILE]_visual_audit.md
Agent 2: Econometric Fidelity Review (econometrics-reviewer)
- Every quantitative claim on slides must be traceable to the paper (
docs/overleaf/_main.tex) - Check: coefficients, standard errors, sample sizes, p-values match paper tables/figures
- Check: identification strategy correctly described (hedonic pricing, repeat sales, long-difference, DiD, upstream/downstream)
- Check: treatment variables defined correctly (spill_count/spill_hrs, 12/24hr counting methodology)
- Check: confidence intervals and significance stars consistent with paper
- Check: no causal language without identification support
- Save:
docs/conferences/quality_reports/[FILE]_econometrics_report.md
Agent 3: Proofreading (proofreader)
- Grammar, typos, consistency, academic quality, citations
- Save:
docs/conferences/quality_reports/[FILE]_report.md
Agent 4: TikZ Review (only if file contains TikZ)
- Label overlaps, geometric accuracy, visual semantics
- Save:
docs/conferences/quality_reports/[FILE]_tikz_review.md
Agent 5: Substance Review (domain correctness)
- Verify environmental economics claims are accurate
- Check EDM/water company institutional context is correct
- Verify spatial econometrics descriptions match methodology
- Check hedonic pricing theory correctly invoked
- Verify England housing market characterisation
- Save:
docs/conferences/quality_reports/[FILE]_substance_review.md
3. Synthesize Combined Summary
# Slide Excellence Review: [Filename]
## Overall Quality Score: [EXCELLENT / GOOD / NEEDS WORK / POOR]
| Dimension | Critical | Medium | Low |
|-----------|----------|--------|-----|
| Visual/Layout | | | |
| Econometric Fidelity | | | |
| Proofreading | | | |
| Substance | | | |
### Critical Issues (Immediate Action Required)
### Medium Issues (Next Revision)
### Recommended Next Steps
Quality Score Rubric
| Score | Critical | Medium | Meaning | |-------|----------|--------|---------| | Excellent | 0-2 | 0-5 | Ready to present | | Good | 3-5 | 6-15 | Minor refinements | | Needs Work | 6-10 | 16-30 | Significant revision | | Poor | 11+ | 31+ | Major restructuring |
Related Skills
brycewang-stanford/auto-review-loop-minimax
tools
Community
Autonomous multi-round research review loop using MiniMax API. Use when you want to use MiniMax instead of Codex MCP for external review. Trigger with "auto review loop minimax" or "minimax review".
3,665SKILL.mdUpdated May 26, 2026
brycewang-stanford/auto-review-loop-llm
tools
Community
Autonomous research review loop using any OpenAI-compatible LLM API. Configure via llm-chat MCP server or environment variables. Trigger with "auto review loop llm" or "llm review".
3,665SKILL.mdUpdated May 26, 2026
brycewang-stanford/auto-review-loop-minimax
tools
Community
Autonomous multi-round research review loop using MiniMax API. Use when you want to use MiniMax instead of Codex MCP for external review. Trigger with "auto review loop minimax" or "minimax review".
3,665SKILL.mdUpdated May 20, 2026
brycewang-stanford/auto-review-loop-llm
tools
VerifiedTrustedCommunity
Autonomous research review loop using any OpenAI-compatible LLM API. Configure via llm-chat MCP server or environment variables. Trigger with "auto review loop llm" or "llm review".
3,665SKILL.mdUpdated May 20, 2026