# idea-generation

Sorts a pile of stock candidates into longs, shorts, pairs and catalyst plays, and flags the ones worth dropping.

- 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/idea-generation/SKILL.md
- Updated: 2026-10-08
- HTML: https://affpapa.org/en/nevibecode/skills/idea-generation

## What it does

This skill handles the first pass over public-equity candidates. Feed it screens, notes, files or connected sources, and it returns candidates grouped by archetype: long, short, pair, relative value, catalyst, watchlist. False positives get marked as rejected instead of quietly promoted.

The workflow is spelled out step by step. Set the mandate and universe, normalize tickers, ADRs, share classes, currencies and fiscal calendars, map thematic names by beneficiary pathway, then run PM triage on denominator quality, estimate credibility, catalyst path, liquidity and false-positive risk. For structured input there is `scripts/score_ideas.py`, which takes a CSV of candidate rows and scoring fields and writes ranked support output plus warnings. It does not produce market data of its own.

One rule is explicit: a screen result is never a final recommendation. This is a research-prioritization tool, not a trade advisor. The `crowded` label is reserved for cases backed by positioning, ownership, flows or short interest; when the only support is price appreciation or narrative visibility, the output uses `expectations-heavy`, `valuation-gated` or `crowding-risk candidate`. A name does not advance just because it rallied after a thematic catalyst — the driver has to link to orders, backlog, revenue, margins or estimate revisions, or it gets tagged `needs exposure attribution`.

## Install

### Codex (native platform)

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

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

### Claude Code

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

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

### Cursor

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

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install openai/plugins idea-generation
```

2. **Manually: put the files in place**
- File: `.github/skills/idea-generation/SKILL.md`

### Gemini CLI

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

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/idea-generation/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/idea-generation/SKILL.md

## When to use it
- group stock candidates by idea archetype
- drop false positives before deep research
- check what backs a crowded-position label
- tie a stock's driver to orders, revenue or estimate revisions
- route a candidate to the right next workflow

## Example prompts
- Triage this list of stock candidates by archetype and tell me what deserves deeper work
- Run `candidates.csv` through `scripts/score_ideas.py` and show me the warnings
- Check whether the `crowded` label holds for these names and relabel the weak ones

## Similar
- [canslim-screener](https://affpapa.org/en/nevibecode/skills/canslim-screener.md) — skill · 3600 installs
- [dividend-growth-pullback-screener](https://affpapa.org/en/nevibecode/skills/dividend-growth-pullback-screener.md) — skill · 3300 installs
- [idea-generation-and-ideation](https://affpapa.org/en/nevibecode/skills/idea-generation-and-ideation.md) — skill · 654 installs
- [proposal-generation](https://affpapa.org/en/nevibecode/skills/proposal-generation.md) — skill · 651 installs
- [comp-analysis](https://affpapa.org/en/nevibecode/skills/comp-analysis.md) — skill · 2800 installs
- [gmgn-heat-rank](https://affpapa.org/en/nevibecode/skills/gmgn-heat-rank.md) — skill · 4700 installs

## Other versions with the same name
- [idea-generation · anthropics](https://affpapa.org/en/nevibecode/skills/anthropics-idea-generation.md) — 1200 installs
- [idea-generation · lingzhi227](https://affpapa.org/en/nevibecode/skills/lingzhi227-idea-generation.md) — 1800 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