This is a structured web research workflow that saves your findings incrementally so you don't lose work when the conversation cuts off. It enforces a specific pattern: create a markdown file in _knowledge_base before you start searching, append discoveries after each WebSearch call, write interim summaries every three searches, and compile a final brief with sourced facts and credibility ratings. The author clearly got burned by losing research mid-session and built guardrails around it. If you do multi-step research tasks where you're gathering information from the web and need that work preserved between context windows, this gives you a disciplined template. It's opinionated about file naming, markdown structure, and separating research from writing.
npx -y skills add alchaincyf/huashu-skills --skill huashu-research --agent claude-codeInstalls into .claude/skills of the current project.
结构化的网络调研流程,核心目标:调研成果实时持久化,防止会话截断丢失工作。
_knowledge_base/research-<主题>-<YYYYMMDD>.md# [主题] 调研笔记
调研日期:YYYY-MM-DD
调研目标:[一句话说明]
## 关键问题
1. [问题1]
2. [问题2]
3. [问题3]
## 发现
(调研中逐步填充)
## 来源列表
(每次搜索后追加)
### 阶段摘要 (第N轮) + 当前关键发现调研结束时,整理文件为结构化简报:
## 调研结论
### 关键事实
1. [事实1](来源:URL)
2. [事实2](来源:URL)
### 来源列表
| 来源 | URL | 发布日期 | 可信度 |
|------|-----|---------|--------|
| ... | ... | ... | 高/中/低 |
### 待确认问题
- [还需要进一步验证的点]
### 写作建议
- [基于调研结果,对后续写作的建议]
_knowledge_base/research-<主题>-<YYYYMMDD>.md_knowledge_base/<分类>/<主题>-<YYYYMM>.md最后更新: 2026-02-06
花叔出品 | AI Native Coder · 独立开发者 公众号「花叔」| 30万+粉丝 | AI工具与效率提升 代表作:小猫补光灯(AppStore付费榜Top1)·《一本书玩转DeepSeek》
sickn33/antigravity-awesome-skills