# book-research-assistant

A skill that plans and vets research for a nonfiction book: turns fact gaps into questions, writes the prompts, and rules on each source.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · ★ 132
- Author: robertguss
- License: LicenseRef-Proprietary · policy=link-only · description only; the file stays with the author
- Source: https://github.com/robertguss/claude-code-toolkit/tree/HEAD/skills/non-fiction-book-factory/book-research-assistant/SKILL.md
- Updated: 2026-09-16
- HTML: https://affpapa.org/en/nevibecode/skills/book-research-assistant

## What it does

The skill runs in two phases. First it takes the Research Gaps Document from `book-architect` and turns each gap into a self-contained deep research prompt, building a Chapter Research Tracker with gap IDs, priorities and the kind of evidence needed. Later, when you bring results back, it goes gap by gap and renders a verdict: Complete, Needs More or Problematic. Each finished chapter gets a summary, and the skill certifies whether you are ready to move on.

It does not run the research itself. You execute the deep search outside, with Claude and Gemini, while the skill handles planning, prompt writing, validation and organization. Under the hood it leans on reference files for question formulation, evidence types, source evaluation and output format.

Upstream documents are required: Research Gaps Document, Master Architecture Document and Section Blueprints from `book-architect`, plus the Book Concept Document from `book-ideation`. Without them planning will not start. The skill also treats LLM research as something that can invent sources, so checking citations and confidence flags is part of the workflow.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add robertguss/claude-code-toolkit --skill book-research-assistant -a claude-code
```

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

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add robertguss/claude-code-toolkit --skill book-research-assistant -a codex
```

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

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add robertguss/claude-code-toolkit --skill book-research-assistant -a cursor
```

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

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install robertguss/claude-code-toolkit book-research-assistant
```

2. **Manually: put the files in place**
- File: `.github/skills/book-research-assistant/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add robertguss/claude-code-toolkit --skill book-research-assistant -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/robertguss/claude-code-toolkit --path skills/non-fiction-book-factory/book-research-assistant
```

### Windsurf (Devin Desktop)

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

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add robertguss/claude-code-toolkit --skill book-research-assistant -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/robertguss/claude-code-toolkit/tree/HEAD/skills/non-fiction-book-factory/book-research-assistant/SKILL.md

## When to use it
- turn fact gaps into specific research questions
- write self-contained deep research prompts
- vet each source and assign a verdict
- summarize a chapter after validation
- decide whether the book is ready for drafting

## Example prompts
- Plan the research for chapter one using my Research Gaps Document
- Validate the results for chapter 3 gaps and give a verdict on each
- Produce the final research synthesis for the whole book

## Similar
- [content-research-writer](https://affpapa.org/en/nevibecode/skills/content-research-writer.md) — skill · 2522 installs
- [narrative-nonfiction](https://affpapa.org/en/nevibecode/skills/narrative-nonfiction.md) — skill · 565 installs
- [creative-research](https://affpapa.org/en/nevibecode/skills/creative-research.md) — skill · 487 installs
- [kids-book-writer](https://affpapa.org/en/nevibecode/skills/kids-book-writer.md) — skill · 519 installs
- [book-review](https://affpapa.org/en/nevibecode/skills/book-review.md) — skill · 589 installs
- [deep-research](https://affpapa.org/en/nevibecode/skills/199-biotechnologies-deep-research.md) — skill · 10200 installs

From the same set: [robertguss/claude-code-toolkit](https://affpapa.org/en/nevibecode/by/robertguss/claude-code-toolkit.md) — 6 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