Skip to content
Automation
Skill

/slide-excellence

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.

From plugin
auto-empirical-research-skills
3.8k200 skills
Install
$ npx -y skills add brycewang-stanford/Auto-Empirical-Research-Skills --skill slide-excellence --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.
  • Slash command/slide-excellence

Context preview

The summary Claude sees to decide when to auto-load this skill.

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.

SKILL.md

slide-excellence.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 |

Read more
Ships withauto-empirical-research-skills

📌 文档结构(2026-07-22 起): 本文件是中文默认入口 —— banner + badges + 信任面 + 9 阶段流水线速览 + 76 行合集总表。 每个合集的完整描述、按用途分组、精确数字、验证方法在 docs/CONTENT_ZH.md(扩展正文,总表行内的 → 直接跳转到对应锚点)。 English version: README-en.md · 中文扩展正文:docs/CONTENT_ZH.md · README-zh-CN.md 已弃用(重定向占位) 🌐 语言: English |

Get the whole plugin