Skip to main content
affpapa.org
RU EN
skill CX Codex GP ChatGPT official · OpenAI

model-audit-tieout — Codex skill: what it does, how to install

Audits existing public equity spreadsheets and valuation files for broken formulas, hardcodes, and source gaps. Does not build new models from scratch.

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

What model-audit-tieout does

This workflow runs quality assurance across pre-built valuation spreadsheets and equity forecast workbooks. It flags volatile functions, unlinked plugs, broken references, circular math, and hardcoded numbers where calculations belong. It leaves original workbook formulas intact unless remediation is directly requested.

The inspection flow relies on scripts/audit_workbook.py to parse .xlsx files. Running that helper script without openpyxl installed in your Python environment causes an immediate failure. Findings are compiled into an issue log, tie-out records against filings, and a readiness verdict covering whether the model can back investment decisions.

What it helps with

  • detect hardcoded inputs, circularity, and broken links across spreadsheet tabs
  • reconcile valuation drivers against primary earnings filings and company reports
  • produce an audit memo with a prioritized list of model defects
  • verify downside scenarios for dilution and multiple compression risks

Example prompts for the agent

  • Inspect dcf_model.xlsx for formula inconsistencies and hidden tabs
  • Tie out the operating forecast assumptions against the latest earnings release
  • Run an audit on the equity workbook and create a standalone HTML report

How to install model-audit-tieout

1Skills CLI (Vercel)

npx skills add openai/plugins --skill model-audit-tieout -a codex

2Manually: put the files in place

.agents/skills/model-audit-tieout/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 model-audit-tieout

How do I install model-audit-tieout in Codex?

Run npx skills add openai/plugins --skill model-audit-tieout -a codex. Codex places the skill configuration under .agents/skills/model-audit-tieout/SKILL.md.

What is model-audit-tieout used for?

It verifies existing public equity valuation files and spreadsheets before they are used in portfolio decisions. The skill checks formula integrity, flags unsupported assumptions, and issues an explicit audit verdict.

Which dependencies does the local inspection script need?

The included scripts/audit_workbook.py utility requires openpyxl to inspect Excel workbooks. You can install it using python -m pip install -r scripts/requirements.txt.

Similar skills

All skills for Finance and business →
churn-prevention coreyhaines31 A Claude Code skill for subscription churn: an exit survey at cancellation, an offer matched to the stated reason, and recovery of failed payments. CX Codex +1 121,600installs revops coreyhaines31 This skill helps design RevOps workflows for lead stages, scoring, routing, and marketing-to-sales handoffs. Use it when CRM processes need clear rules. CX Codex +1 114,000installs ads coreyhaines31 Guides paid advertising campaigns across Google Ads and Meta. It connects agents to rigorous playbooks and forbids guessing missing numbers. CX Codex +1 83,400installs pricing coreyhaines31 Turns the agent into a pricing advisor for SaaS: pick a value metric, structure tiers, audit the pricing page. Useful when you can't tell what to charge. CX Codex +1 79,900installs marketing-plan coreyhaines31 Generates an AARRR-structured 12-month marketing plan with an audit score and a 90-day roadmap. Outputs a single Markdown document ready for Notion. CX Codex +1 68,400installs humanizer blader Rewrites text that reads like a chatbot wrote it, keeping the meaning intact. Useful when editing posts, docs or commit messages. CX Codex +1 10,600installs

From the same set596

The whole set →
thesis-tracker Keeps a public-equity thesis alive over time: original underwriting stays put, new evidence gets appended, statuses and actions get refreshed. CX Codex GP ChatGPT ★ 7,604repo stars scenario-sensitivity-generator Generates sensitivity matrices and breakpoint thresholds from public equity models. Helps evaluate thesis changes and downside risks. CX Codex GP ChatGPT ★ 7,604repo stars public-equity-investing Routes public-company and security research to focused investing workflows. Use it for earnings, valuation, model changes, thesis work, and portfolio decisions. CX Codex GP ChatGPT ★ 7,604repo stars portfolio-risk-management Turns a listed-equity thesis into an implementable risk posture: how much to hold, what to hedge with, and when to resize. CX Codex GP ChatGPT ★ 7,604repo stars memo-builder Draft or review formal memos on public equities, with valuation, scenarios, risks and a recommendation. Use it for committee papers, research notes or PM updates. CX Codex GP ChatGPT ★ 7,604repo stars meeting-prep Builds a conversation plan for an issuer meeting: which questions come first, what to listen for, and how to push back on a vague answer. CX Codex GP ChatGPT ★ 7,604repo stars long-short-pitch Builds portfolio-manager-ready public equity pitches. It frames trade mechanics, catalyst timelines, and exit disciplines even under sparse context. CX Codex GP ChatGPT ★ 7,604repo stars idea-generation Sorts a pile of stock candidates into longs, shorts, pairs and catalyst plays, and flags the ones worth dropping. CX Codex GP ChatGPT ★ 7,604repo stars

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

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