# initiating-coverage

initiating-coverage — a skill for writing full equity initiation reports with thesis, valuation and evidence discipline.

- skill · `type=skill` · Codex, ChatGPT, Claude Code, Cursor, GitHub Copilot, Gemini CLI, Windsurf (Devin Desktop), Claude.ai · ★ 8052 repo stars
- 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/initiating-coverage/SKILL.md
- Updated: 2026-10-08
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/initiating-coverage

## What it does

Builds an equity initiation report: pulls data from files and connectors (filings, earnings transcripts, internal models, market estimates), frames the investment thesis, embeds valuation and explicitly marks what is proven versus assumed. Works in several modes — sell-side, buy-side, hedge fund, long-only, credit-adjacent, sector — and adapts structure to the task. Before finalizing a report, it requires current price, market cap, consensus estimates and enterprise value inputs; without them it flags gaps and explains which conclusions are blocked.

The output is a full HTML report or a structured research agenda when context is thin. The skill coordinates with others: `financial-source-of-truth` for data validation, `company-tearsheet` for issuer baseline, model skills for DCF and comps, `scenario-sensitivity-generator` for cases. Not for trade pitches, brief IC memos, earnings notes or one-page profiles — separate skills handle those.

The report must include report date, data sources, fact confidence, unresolved conflicts and key assumptions. Facts, company claims, street estimates, model-derived values and assumptions are labeled separately. When debt, leases, dilution or capital intensity matter, the skill demands a fully diluted cap table and proof of post-financing returns.

## Install

### Codex (native platform)

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

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

### Claude Code

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

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

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add openai/plugins --skill initiating-coverage -a cursor
```

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

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install openai/plugins plugins/public-equity-investing/skills/initiating-coverage
```

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

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add openai/plugins --skill initiating-coverage -a gemini-cli
```

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

### Windsurf (Devin Desktop)

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

## When to use it
- write a full equity initiation report with thesis and valuation
- gather data from filings, transcripts and models into one document
- check which sources are available and what must be assumed
- label confidence level: facts, analyst estimates, model conclusions
- prepare a structured research plan when data is incomplete

## Example prompts
- Build an initiation report for company X with thesis and valuation, pull data from 10-K and earnings transcripts
- Write a hedge fund initiation: thesis, valuation, sources and assumptions
- Prepare a research agenda and missing source list for an initiation on company Y

## Similar
- [earnings](https://affpapa.org/en/nevibecode/commands/earnings.md) — command · ★ 41441 repo stars
- [taiwan-equity-research-coverage](https://affpapa.org/en/nevibecode/skills/taiwan-equity-research-coverage.md) — skill · 809 installs
- [stock-grades](https://affpapa.org/en/nevibecode/skills/stock-grades.md) — skill · 258 installs
- [earnings-analysis](https://affpapa.org/en/nevibecode/skills/earnings-analysis.md) — skill · 3700 installs
- [financial-analyst-master](https://affpapa.org/en/nevibecode/skills/financial-analyst-master.md) — skill · 333 installs
- [stock-analysis](https://affpapa.org/en/nevibecode/skills/stock-analysis.md) — skill · 22 installs

## Other versions with the same name
- [initiating-coverage · anthropics](https://affpapa.org/en/nevibecode/skills/anthropics-initiating-coverage.md) — 2100 installs

From the same set: [openai/plugins](https://affpapa.org/en/nevibecode/by/openai/plugins.md) — 567 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
