# 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.

- 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/earnings-deep-dive/SKILL.md
- Updated: 2026-10-08
- HTML: https://affpapa.org/en/nevibecode/skills/earnings-deep-dive

## What it does

The skill works on numbers that are already published. Official filings and releases come first, the call transcript backs the narrative and any guidance that only came up on the call. Every figure and quote carries a source tag; anything derived by the analyst needs its formula, assumptions and a confidence note. GAAP versus non-GAAP, reported versus constant currency, company guidance versus analyst estimates — all of it stays labelled, so the two do not blur together.

There are several routes. The default is a full deep dive: quarterly key metrics and growth trajectory built on the issuer's own drivers, a Q&A treatment and a debate map. Ask for something short and you get a one-page tear sheet. If you explicitly want a dashboard, the skill keeps ownership of the analysis and hands a `public_equity_investing_dashboard.v1` payload to `dashboard-builder`. A deterministic file mode exists too, for when you supply `plan.json`, normalized CSVs or model-update inputs.

Before gathering evidence the skill reads the shared runtime contract in `../public-equity-investing/SKILL.md` and resolves only the source categories the task needs: filings and IR, transcripts and presentations, internal research, portfolio models and trackers, market data and estimates. When no transcript exists, a full deep dive does not render an empty Q&A table — it shows a visible limitation labelled `transcript not provided` or `transcript source not found` and names the missing artifact.

## Install

### Codex (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add openai/plugins --skill earnings-deep-dive -a codex
```

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

### Claude Code

1. **Skills CLI (Vercel)**
```bash
npx skills add openai/plugins --skill earnings-deep-dive -a claude-code
```

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

### Cursor

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

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install openai/plugins earnings-deep-dive
```

2. **Manually: put the files in place**
- File: `.github/skills/earnings-deep-dive/SKILL.md`

### Gemini CLI

**Platform CLI**
```bash
gemini skills install https://github.com/openai/plugins --path plugins/public-equity-investing/skills/earnings-deep-dive
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/earnings-deep-dive/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/earnings-deep-dive/SKILL.md

## When to use it
- separate one-off items from recurring operating performance after a print
- attach a source tag to every reported number and quote
- map call Q&A by questioner, firm and answering executive
- check whether below-the-line items distort headline EPS
- produce a standalone HTML report after results

## Example prompts
- Run a full deep dive on this quarter's results using the latest call and guidance
- Give me a one-page tear sheet on the print
- Map the call Q&A and list what confirms and what breaks the bull case

## Similar
- [earnings-analysis](https://affpapa.org/en/nevibecode/skills/earnings-analysis.md) — skill · 3400 installs
- [earnings-preview-single](https://affpapa.org/en/nevibecode/skills/earnings-preview-single.md) — skill · 1800 installs
- [earnings-trade-analyzer](https://affpapa.org/en/nevibecode/skills/earnings-trade-analyzer.md) — skill · 3400 installs
- [earnings-preview](https://affpapa.org/en/nevibecode/skills/himself65-earnings-preview.md) — skill · 3200 installs
- [longbridge-earnings](https://affpapa.org/en/nevibecode/skills/longbridge-earnings.md) — skill · 3800 installs
- [earnings-recap](https://affpapa.org/en/nevibecode/skills/earnings-recap.md) — skill · 3200 installs

From the same set: [openai/plugins](https://affpapa.org/en/nevibecode/by/openai/plugins.md) — 528 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