Skip to main content
skill CX Codex GP ChatGPT official · OpenAI

deck-report-qc — Codex skill: what it does, how to install

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

Install into Codex · Skills CLI (Vercel) All methods and platforms ↓
npx skills add openai/plugins --skill deck-report-qc -a codex
Open on GitHub

What deck-report-qc 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.

What it helps with

  • 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 for the agent

  • 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.

How to install deck-report-qc

1Skills CLI (Vercel)

npx skills add openai/plugins --skill deck-report-qc -a codex

2Manually: put the files in place

.agents/skills/deck-report-qc/SKILL.md

For all projects use ~/.agents/skills/

Step by step, with commands for each platform: Codex skills: how to install, where they live, how to call them

Questions about deck-report-qc

How do I install deck-report-qc in Codex?

Run npx skills add openai/plugins --skill deck-report-qc -a codex in your terminal. The configuration installs to .agents/skills/deck-report-qc/SKILL.md.

What does deck-report-qc do?

It acts as an automated first-pass reviewer for equity research reports and pitch decks. The skill cross-checks metrics against source models, flags mismatches, and outputs an HTML issue summary.

Does deck-report-qc certify documents for external client distribution?

No. The skill is strictly an internal QA gate and explicitly forbids treating its output as certification for external circulation.

Similar skills

All skills for Finance and business →

From the same set596

The whole set →
equity-model-update Updates a copy of a public-company Excel model from source-to-model maps and returns the XLSX with a change log. CX Codex GP ChatGPT ★ 7,604repo stars economic-impact-report Translates policy changes, macro shocks, and industry shifts into concrete consequences for listed equity valuations, earnings, and portfolio allocation. CX Codex GP ChatGPT ★ 7,604repo stars earnings-preview Builds a full pre-earnings report with market expectations, KPI tracking, scenarios, and call questions. Use it before results are released. CX Codex GP ChatGPT ★ 7,604repo stars earnings-deep-dive A skill for analyzing a public company after results, guidance or the earnings call are out. It is not meant for pre-print previews. CX Codex GP ChatGPT ★ 7,604repo stars dcf-model-builder This skill builds public-company DCF workbooks in XLSX, with a formula-based model as its standard route. Use it to create or refresh a valuation and explore scenarios. CX Codex GP ChatGPT ★ 7,604repo stars comps-valuation A Claude and Claude skill that builds comparable-company valuations: picks peers, runs the multiples, and returns a report or an editable workbook. CX Codex GP ChatGPT ★ 7,604repo stars company-tearsheet Extracts verified corporate metrics from public filings and earnings calls into an issuer baseline. Useful before building DCF models or valuation memos. CX Codex GP ChatGPT ★ 7,604repo stars catalyst-calendar Builds and refreshes public-equity catalyst calendars with timing, confidence, thesis links, preparation tasks, and PM decisions. Available for Codex and ChatGPT. CX Codex GP ChatGPT ★ 7,604repo stars

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor