# synthesizer

synthesizer combines findings from multiple research agents into a structured report, with shared conclusions and disagreements made clear. Use it after parallel research is complete.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 106 installs · ★ 379 repo stars
- Author: liangdabiao
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/liangdabiao/Claude-Code-Stock-Deep-Research-Agent/tree/HEAD/1.claude/skills/synthesizer/SKILL.md
- Updated: 2026-03-07
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/synthesizer

## What it does

The skill groups findings by theme and gauges how strongly sources agree. It can account for differences such as publication dates, methods, or scope, while keeping source attribution in the resulting synthesis. Conclusions backed by several sources are distinguished from findings that rest on a single one.

Ask for a full report, an executive summary, a thematic analysis, or a side-by-side comparison. The suggested output files are `full_report.md`, `executive_summary.md`, and `synthesis_notes.md`. If the synthesis exposes research gaps, the agent can launch additional research. You need findings from other agents first; this skill synthesizes research rather than gathering the original sources.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add liangdabiao/Claude-Code-Stock-Deep-Research-Agent --skill synthesizer -a claude-code
```

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

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add liangdabiao/Claude-Code-Stock-Deep-Research-Agent --skill synthesizer -a codex
```

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

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add liangdabiao/Claude-Code-Stock-Deep-Research-Agent --skill synthesizer -a cursor
```

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

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install liangdabiao/Claude-Code-Stock-Deep-Research-Agent 1.claude/skills/synthesizer
```

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

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add liangdabiao/Claude-Code-Stock-Deep-Research-Agent --skill synthesizer -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/liangdabiao/Claude-Code-Stock-Deep-Research-Agent --path 1.claude/skills/synthesizer
```

### Windsurf (Devin Desktop)

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

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add liangdabiao/Claude-Code-Stock-Deep-Research-Agent --skill synthesizer -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/liangdabiao/Claude-Code-Stock-Deep-Research-Agent/tree/HEAD/1.claude/skills/synthesizer/SKILL.md

## When to use it
- combine findings from several research agents
- group source conclusions by theme and degree of agreement
- explain conflicting research results
- retain source attribution in a synthesized report
- compare research findings in a side-by-side matrix

## Example prompts
- Combine the research agents’ findings into a structured report and save it as `full_report.md`.
- Compare the conclusions, separating shared findings from unresolved disagreements.
- Create a concise research summary in `executive_summary.md` and retain source attribution.

## Similar
- [research-synthesizer](https://affpapa.org/en/nevibecode/agents/research-synthesizer.md) — subagent · 1377 installs
- [deep-research](https://affpapa.org/en/nevibecode/skills/claude-office-skills-deep-research.md) — skill · 5200 installs
- [firecrawl-deep-research](https://affpapa.org/en/nevibecode/skills/firecrawl-deep-research.md) — skill · 36200 installs
- [academic-research-synthesizer](https://affpapa.org/en/nevibecode/agents/academic-research-synthesizer.md) — subagent · 520 installs
- [systematic-literature-review](https://affpapa.org/en/nevibecode/skills/systematic-literature-review.md) — skill · 2500 installs
- [lit-review-assistant](https://affpapa.org/en/nevibecode/skills/lit-review-assistant.md) — skill · 241 installs

From the same set: [liangdabiao/claude-code-stock-deep-research-agent](https://affpapa.org/en/nevibecode/by/liangdabiao/claude-code-stock-deep-research-agent.md) — 5 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
