# autonomous-investigation

Sets the rules for research skills that run while you are away: question budget, a search plan, and Fact/Inference/Assumption labels on every claim.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 1200 installs · ★ 7673
- Author: deanpeters
- License: CC-BY-SA-4.0 · policy=link-only · description only; the file stays with the author
- Source: https://github.com/deanpeters/Product-Manager-Skills/tree/HEAD/skills/autonomous-investigation/SKILL.md
- Updated: 2026-10-16
- HTML: https://affpapa.org/en/nevibecode/skills/autonomous-investigation

## What it does

This is a contract, not a report generator. The skill spells out how investigation skills should behave: the agent may ask at most a few clarifying questions, and once that budget runs out or nobody replies, it carries on and flags its guesses. An unattended run therefore slows down rather than stalling.

Work starts with a three-point plan: what gets searched, which kinds of sources, how facts will be told apart from interpretation. Then each key claim gets one label. Fact means a checkable URL is attached. Inference means the evidence is cited and you judge the jump. Assumption means a working guess kept for later validation. A separate gaps list holds whatever could not be found, and every domain names its own forbidden fabrications.

Section order stays fixed from run to run, so output N and output N+1 diff cleanly. Signal strength is graded by how many independent channels agree: one is a watch item, two make a working hypothesis, three or more justify briefing leadership. Collection stays within public sources, and the skill rules out pretexting or breaking terms you accepted.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add deanpeters/Product-Manager-Skills --skill autonomous-investigation -a claude-code
```

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

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add deanpeters/Product-Manager-Skills --skill autonomous-investigation -a codex
```

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

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add deanpeters/Product-Manager-Skills --skill autonomous-investigation -a cursor
```

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

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install deanpeters/Product-Manager-Skills autonomous-investigation
```

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

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add deanpeters/Product-Manager-Skills --skill autonomous-investigation -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/deanpeters/Product-Manager-Skills --path skills/autonomous-investigation
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/autonomous-investigation/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add deanpeters/Product-Manager-Skills --skill autonomous-investigation -a opencode
```

### 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/deanpeters/Product-Manager-Skills/tree/HEAD/skills/autonomous-investigation/SKILL.md

## When to use it
- set up a competitive scan you can re-run quarterly without babysitting
- tell sourced facts apart from the model's guesses
- diff two runs and see what actually moved
- give several research skills the same behaviour
- cut a report down to the bullets a decision needs

## Example prompts
- Run an autonomous investigation on the competitor's push into workflow automation, backing our Q3 roadmap bet.
- Show me your three-bullet search plan before you start collecting.
- What changed since last quarter? Diff this run against the previous one.

## Similar
- [setup-matt-pocock-skills](https://affpapa.org/en/nevibecode/skills/setup-matt-pocock-skills.md) — skill · 1052851 installs
- [ask-matt](https://affpapa.org/en/nevibecode/skills/ask-matt.md) — skill · 766587 installs
- [to-tickets](https://affpapa.org/en/nevibecode/skills/to-tickets.md) — skill · 711230 installs
- [writing-plans](https://affpapa.org/en/nevibecode/skills/writing-plans.md) — skill · 282859 installs
- [caveman-review](https://affpapa.org/en/nevibecode/skills/caveman-review.md) — skill · 411800 installs
- [caveman-compress](https://affpapa.org/en/nevibecode/skills/caveman-compress.md) — skill · 411500 installs

From the same set: [deanpeters/product-manager-skills](https://affpapa.org/en/nevibecode/by/deanpeters/product-manager-skills.md) — 73 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