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
4.9k200 skills

Claude Code

$ npx -y skills add brycewang-stanford/Auto-Empirical-Research-Skills --skill slide-excellence --agent claude-code

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
@brycewang-stanford
Ships withauto-empirical-research-skills

## 🔥 力荐 · StatsPAI — Stata 与 R 的 Python 平替,为 AI Agent 而生 🔁 Stata / R 平替:reghdfe、csdid、rdrobust、synth、fixest、did 等常用命令在 Python 中一站式替代,一个 import statspai as sp 搞定 DID / RD / IV / SCM / DML / matching 🤖 面向 Agent 设计:结构化结果对象 + 内置 MCP Server,Claude / Codex

4.9k200 skills
Get the whole plugin

Stars on GitHub

Momentum

stars in total
4.9k
Star history of brycewang-stanford/Auto-Empirical-Research-Skills on GitHub, a chart by star-history.com

More skills from other plugins.

agent-builder

agent-builder

Load immediately after an Agent intent, before the first agent_builder_* call. Governs how you create, configure, test, and…

n8n12d209k
@n8n-io@n8n-ioInstall Skill
browser-use

browser-use

Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work. Also covers…

@browser-use@browser-useInstall Skill
agent-browser

agent-browser

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling…

@vercel-labs-2@vercel-labs-2Install Skill
add-anydoc

add-anydoc

Add local office-document-to-Markdown conversion to NanoClaw agent containers with the pinned Firecrawl AnyDoc CLI. Use when…

@nanocoai@nanocoaiInstall Skill

Questions about slide-excellence.

Which coding agents can use slide-excellence?
slide-excellence installs in Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf with the skills CLI, using each agent's flag shown on this page. Flowy's auto-invocation, which fires a skill when your prompt matches, runs in Claude Code only.