---
id: gh-research
name: "research"
url: https://skills.yangsir.net/skill/gh-research
author: mattpocock
domain: data-ai
tags: ["research", "documentation", "knowledge-management", "primary-sources", "markdown"]
install_count: 703000
rating: 4.90 (120 reviews)
github: https://github.com/mattpocock/skills/tree/main/skills/engineering/research
---

# research

> 此技能能够自动研究问题，基于官方文档、源代码等一手来源进行调研，并将结果整理为 Markdown 文件存入代码仓库。适合需要快速获取权威技术资料、委托背景调研的场景，大幅减少手动查阅时间。

**Stats**: 703,000 installs · 4.9/5 (120 reviews)

## Before / After 对比

### 调研效率提升

**Before**:

没有这个技能时，开发者需要手动搜索官方文档、论坛和博客来收集信息，平均花费30分钟才能找到可靠答案，且容易遗漏关键细节。

**After**:

使用此技能后，只需提出研究问题，背景代理自动从一手来源收集信息并生成结构化笔记，平均5分钟即可获得完整、可信的调研结果。

| Metric | Before | After | Change |
|---|---|---|---|
| 调研耗时 | 30分钟 | 5分钟 | -83% |

## Readme

Spin up a **background agent** to do the research, so you keep working while it reads.

Its job:

1. Investigate the question against **primary sources** — official docs, source code, specs, first-party APIs — not a secondary write-up of them. Follow every claim back to the source that owns it.
2. Write the findings to a single Markdown file, citing each claim's source.
3. Save it where the repo already keeps such notes; match the existing convention, and if there is none, put it somewhere sensible and say where.


---
*Source: https://skills.yangsir.net/skill/gh-research*
*Markdown mirror: https://skills.yangsir.net/api/skill/gh-research/markdown*