# deck-report-qc

First-pass quality control for equity research decks and memos. Spots metric mismatches and missing citations before senior review.

- skill · `type=skill` · Codex, ChatGPT · ★ 7604
- Author: OpenAI · official OpenAI repository
- License: LicenseRef-Proprietary · policy=link-only · description only; the file stays with the author
- Source: https://github.com/openai/plugins/tree/HEAD/plugins/public-equity-investing/skills/deck-report-qc/SKILL.md
- Updated: 2026-10-08
- HTML: https://affpapa.org/en/nevibecode/skills/deck-report-qc

## What it does

The skill runs an initial quality check on public equity decks and research memos. When processing PPTX or DOCX files, it scans content using `python scripts/inspect_deck_report.py <file1> <file2> --outdir qc_out`. It traces reported metrics back to source data and flags questionable figures with `needs_review`.

By default, the workflow produces a standalone HTML report highlighting high-priority discrepancies for senior reviewers. Mismatched EPS, price targets, or valuation metrics take precedence over minor styling flaws. If a chart is an embedded image, inspecting its underlying numbers requires the original model file.

This gate never rewrites slides or approves documents for external distribution. Instead, it logs issues and suggests edits. Complex formula discrepancies route to `model-audit-tieout`, while table formatting issues move to `excel-data-cleaner`.

## Install

### Codex (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add openai/plugins --skill deck-report-qc -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/deck-report-qc/SKILL.md` — For all projects use ~/.agents/skills/

### Claude Code

1. **Skills CLI (Vercel)**
```bash
npx skills add openai/plugins --skill deck-report-qc -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/deck-report-qc/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/deck-report-qc/

### Cursor

**Manually: put the files in place**
- File: `.cursor/skills/deck-report-qc/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install openai/plugins deck-report-qc
```

2. **Manually: put the files in place**
- File: `.github/skills/deck-report-qc/SKILL.md`

### Gemini CLI

**Platform CLI**
```bash
gemini skills install https://github.com/openai/plugins --path plugins/public-equity-investing/skills/deck-report-qc
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/deck-report-qc/SKILL.md` — The legacy .windsurf/skills/ path still works

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/openai/plugins/tree/HEAD/plugins/public-equity-investing/skills/deck-report-qc/SKILL.md

## When to use it
- spot conflicting valuation multiples and EPS metrics across slides
- generate an HTML issue report for senior analysts
- verify citation coverage and footnotes in equity research notes
- flag flattened charts that lack linked source spreadsheets

## Example prompts
- Run first-pass QC on `pitch.pptx` using `model.xlsx` as the supporting source.
- Generate a standalone HTML review report for `initiation_memo.docx`.
- Inspect `valuation_deck.pdf` and flag any conflicting valuation metrics.

## Similar
- [churn-prevention](https://affpapa.org/en/nevibecode/skills/coreyhaines31-churn-prevention.md) — skill · 121600 installs
- [revops](https://affpapa.org/en/nevibecode/skills/revops.md) — skill · 114000 installs
- [ads](https://affpapa.org/en/nevibecode/skills/ads.md) — skill · 83400 installs
- [pricing](https://affpapa.org/en/nevibecode/skills/pricing.md) — skill · 79900 installs
- [marketing-plan](https://affpapa.org/en/nevibecode/skills/marketing-plan.md) — skill · 68400 installs
- [humanizer](https://affpapa.org/en/nevibecode/skills/blader-humanizer.md) — skill · 10600 installs

From the same set: [openai/plugins](https://affpapa.org/en/nevibecode/by/openai/plugins.md) — 596 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md