
multi-search
智能多主题深度研究工具,支持任意材料输入,使用独立研究 Agent进行并行深度检索并生成系统化研究文档。本技能应在用户需要深度研究多个相关课题、进行系统性信息检索、整合多角度分析时使用。
- Installs
- 719
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/cat-xierluo/legal-skills --skill multi-search- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads multi-search automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
多主题深度研究技能
概述
智能多主题深度研究工具,自动分析材料并生成系统化研究文档。支持任意材料输入,通过并行启动多个独立研究 Agent进行深度检索,形成精简的研究知识库。
核心原则:
- 只做信息检索、归纳与专业表述转化
- 不新增事实,不虚构信息
- 聚焦单一问题,精简输出,能够解决问题即可
- 通用设计,可适用于法律、商业、技术、学术等各领域
触发条件
使用 /multi-search 命令触发,或当用户请求:
- 深度研究多个相关课题
- 进行系统性信息检索
- 整合多角度分析
- 需要生成结构化研究报告
输入格式
方式一:基于文件
/multi-search @文档路径.md
方式二:直接粘贴
/multi-search
[粘贴材料内容]
方式三:指定课题
/multi-search
项目:[项目名称]
研究课题:
1. [课题一]
2. [课题二]
3. [课题三]
处理流程
阶段1:分析准备
- 读取输入材料
- 提取研究课题清单
- 有明确课题:直接使用
- 无明确课题:自动从材料中提取
- 课题拆分原则:
- 方向明确:每个课题对应独特的检索方向
- 避免重叠:确保课题之间检索关键词不重复
- 聚焦问题:每个课题解决一个具体问题
- 确定项目名称和输出位置
阶段2:输出目录智能检测
按优先级检测项目结构:
- 优先检测:
output/目录 → 使用output/[项目名]/ - 其次检测:当前工作目录 → 使用
./[项目名]/ - 兜底方案:用户当前目录 → 使用
./research/
创建目录:[输出目录]/03 - 🔍 深度研究/
阶段3:并行深度研究
为每个研究课题启动独立的 general-purpose 独立研究 Agent。
上下文传递(主Agent → 独立研究 Agent):
- 项目关键信息(背景、目标、核心问题)
- 完整的课题清单及各课题的检索范围
- 已分配的关键词方向(避免重复的依据)
- 具体需求背景
去重检查机制:
每个 独立研究 Agent 在开始检索前,必须遵循以下流程:
-
检索前声明:
- 在当前上下文中声明:"我将检索 [关键词A, 关键词B] 用于研究 [课题名称]"
- 等待主 Agent 确认无重复后再开始
-
主 Agent 审核:
- 检查该 Agent 声明的关键词是否与已分配方向重复
- 如发现重复,及时通知该 Agent 转向其他方向
-
动态调整:
- 如果某方向已被其他 Agent 覆盖,该 Agent 应转向相关但不同的角度
- 记录调整后的检索方向
深度检索要求:
- 4-6轮深度检索
- 自动选择 WebSearch(搜索发现)或 WebFetch(获取完整内容)
- 关键词差异化,确保每个 Agent 覆盖独特角度
文档生成:
- 聚焦解决单一核心问题
- 简洁明了,能够解决问题即可
- 包含关键来源链接
- 直接可用的结论和建议
阶段4:整合输出
- 生成研究总览文档(000.研究总览.md)
- 整合所有 独立研究 Agent 的核心发现
- 创建文档间导航链接
- 添加综合建议和立即行动清单
输出格式
目录结构
[输出目录]/
└── [项目名]/
└── 03 - 🔍 深度研究/
├── 000.研究总览.md
├── YYMMDD [研究课题一].md
├── YYMMDD [研究课题二].md
└── ...
总览文档格式
# [项目名称] 深度研究总览
**生成时间**: YYYY-MM-DD
**研究方式**: N个独立研究 Agent,各进行4-6轮深度检索
**总检索轮次**: XX+轮
**总文档量**: XX KB
---
## 研究成果清单
### 已完成的N份精简研究报告
| 序号 | 研究课题 | 文件大小 | 核心价值 |
|------|---------|---------|---------|
| 01 | [课题一](./YYMMDD%20课题一.md) | XX KB | 简要描述 |
---
## 核心发现
### 发现1:[最重要发现]
**依据**:[简要说明]
**结论**:[具体结论]
---
## 综合建议
### 一、策略建议
**推荐方案**:[具体方案]
### 二、立即行动清单
- [ ] 行动项1
- [ ] 行动项2
详细研究文档格式
# [研究课题标题]
**生成时间**: YYYY-MM-DD
**研究深度**: XX+轮深度检索,覆盖XXXX、XXXX、XXXX
---
## 核心结论
[最重要的发现和结论,2-3段,充分详实]
---
## 一、[主要内容一]
### (一)子标题
正文段落。引用来源使用内嵌链接格式:
- 根据[来源名称](https://链接)...
- 依据[资料](https://链接)...
---
## 二、[主要内容二]
[继续结构化内容]
---
## 三、应用建议
### (一)建议要点
**内容**:[具体内容]
### (二)注意事项
⚠️ [注意点]
链接规范
核心原则
所有来源链接必须内嵌到正文中相应位置
✅ 正确:
根据[研究报告](https://链接)显示...
❌ 错误:
根据某报告...
(文末单独列出引用来源)
链接标注约定
- 🔗 → 通用网页资源
- 📚 → 学术文献
- 🏛️ → 机构官网
- 📄 → 数据来源
文档命名规范
编号系统
00.- 研究总览01-09.- 核心研究10-19.- 重要研究20+.- 延伸研究
主题规范
- ✅ 使用简洁中文标题
- ✅ 避免特殊字符
- ✅ 长度15字以内
- ✅ 清晰反映研究对象
质量标准
独立研究 Agent研究质量
- 聚焦单一问题:每个 独立研究 Agent 仅解决一个核心问题
- 检索深度:4-6轮检索(够用即可)
- 精简输出:简洁明了,能够解决问题就行
- 关键引用:引用关键来源(够用即可)
- 直接可用:提供直接可用的结论和建议
文档质量标准
- 结构清晰:章节标题层级分明
- 叙述连贯:段落式叙述,避免过度罗列
- 链接准确:所有链接内嵌到正文相应位置
- 格式统一:遵循统一的格式规范
- 可操作性强:提供具体的步骤、工具、命令
注意事项
严禁行为
- ❌ 不创建二级子目录(如"引用素材/")
- ❌ 不生成独立的执行总结文件
- ❌ 不使用过度罗列的要点格式
- ❌ 不在文末单独列出引用来源
- ❌ 不添加冗余的进度跟踪章节
推荐做法
- ✅ 使用叙述式段落表达
- ✅ 链接内嵌到相应正文位置
- ✅ 保持简洁的研究总览
- ✅ 提供具体的行动建议
- ✅ 标注清晰的文档编号
依赖
本技能依赖 Claude Code 内置工具,无需额外配置:
- WebSearch:搜索发现
- WebFetch:获取完整内容
- Task:启动独立 独立研究 Agent
变更历史
| 版本 | 日期 | 更新内容 |
|---|---|---|
| v1.0.0 | 2026-02-15 | 从 Command 迁移为 Skill,重命名为多主题深度研究(multi-search) |
FAQ
What does the multi-search skill do?
智能多主题深度研究工具,支持任意材料输入,使用独立研究 Agent进行并行深度检索并生成系统化研究文档。本技能应在用户需要深度研究多个相关课题、进行系统性信息检索、整合多角度分析时使用。
How do I install multi-search?
Run npx skills add https://github.com/cat-xierluo/legal-skills --skill multi-search in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/multi-search/ (personal) or .claude/skills/multi-search/ (project).
Which AI agents can use multi-search?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is multi-search safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains multi-search?
It is published by cat-xierluo in cat-xierluo/legal-skills. It has 719 recorded installs.
More from cat-xierluo/legal-skills
douyin-batch-download
cat-xierluo/legal-skills
抖音视频批量下载工具 - 基于 F2 框架实现高效、增量的视频下载功能。支持单个/批量博主下载,自动 Cookie 管理,差量更新机制。本技能应在用户需要批量下载特定博主视频、服务器部署自动化下载、或定期更新视频库时使用。
litigation-analysis
cat-xierluo/legal-skills
Open the skill to read its SKILL.md instructions.
md2word
cat-xierluo/legal-skills
Open the skill to read its SKILL.md instructions.
funasr-transcribe
cat-xierluo/legal-skills
Open the skill to read its SKILL.md instructions.
legal-proposal-generator
cat-xierluo/legal-skills
Open the skill to read its SKILL.md instructions.
legal-text-format
cat-xierluo/legal-skills
Open the skill to read its SKILL.md instructions.
Popular business & finance skills
sales-enablement
coreyhaines31/marketingskills
When the user wants to create sales collateral, pitch decks, one-pagers, objection handling docs, or demo scripts. Also use when the user mentions 'sales deck,' 'pitch deck,' 'one-pager,' 'leave-behind,' 'objection handling,' 'deal-specific ROI analysis,' 'demo script,' 'talk track,' 'sales playbook,' 'proposal template,' 'buyer persona card,' 'battle card,' 'battlecard,' 'competitive one-pager,' 'win-loss analysis,' 'why are we losing deals,' 'loss reasons,' 'how do I respond to this objection,' 'prospect just said,' 'help my sales team,' 'sales materials,' or 'what should I give my sales reps,' 'cold call script,' or 'voicemail script.' Use this for any document or asset that helps a sales team close deals. For public competitor comparison pages, see competitors. For running buyer interviews or churn research, see customer-research. For marketing website copy, see copywriting. For cold outreach emails, see cold-email. For the offer being sold (bonuses, guarantees, pricing structure),
revops
coreyhaines31/marketingskills
When the user wants help with revenue operations, lead lifecycle management, or marketing-to-sales handoff processes. Also use when the user mentions 'RevOps,' 'revenue operations,' 'lead scoring,' 'outbound pipeline stages,' 'lead routing,' 'MQL,' 'SQL,' 'pipeline stages,' 'deal desk,' 'CRM automation,' 'marketing-to-sales handoff,' 'data hygiene,' 'leads aren't getting to sales,' 'pipeline management,' 'lead qualification,' or 'when should marketing hand off to sales.' Use this for anything involving the systems and processes that connect marketing to revenue. For cold outreach emails, see cold-email. For email drip campaigns, see emails. For pricing decisions, see pricing.
sales-funnel-blueprint
autonnel/autonnel-skills
Turn an offer into a concrete multi-step sales funnel spec - page-by-page structure, price ladder, copy outline and the metrics each step must hit. Use when asked to build a sales funnel, marketing funnel, landing page flow, lead magnet funnel, webinar funnel, tripwire or VSL funnel, when planning a product launch page flow, or when someone asks "what pages do I need" for selling something online.
pricing
coreyhaines31/marketingskills
When the user wants help with pricing decisions, packaging, or monetization strategy. Also use when the user mentions 'pricing,' 'pricing tiers,' 'freemium,' 'free trial,' 'packaging,' 'price increase,' 'value metric,' 'Van Westendorp,' 'willingness to pay,' 'monetization,' 'how much should I charge,' 'my pricing is wrong,' 'pricing page,' 'annual vs monthly,' 'per seat pricing,' 'should I offer a free plan,' 'pricing page teardown,' 'pricing page audit,' 'is my pricing page AI-readable,' or 'can AI read my pricing.' Use this whenever someone is figuring out what to charge, how to structure their plans, or wants to audit a pricing page (for humans and for the AI agents that shortlist tools). For in-app upgrade screens, see paywalls. For offer construction (bonuses, guarantees, value framing, naming) on services/courses/coaching/high-ticket B2B, see offers.
cross-border-ecommerce
nexscope-ai/ecommerce-skills
Cross-border e-commerce expansion advisor. Scores target markets on 8 weighted dimensions (market size, ecommerce penetration, competition, regulatory complexity, logistics infrastructure, payment ecosystem, cultural distance, IP protection), compares 5 fulfillment models with cost and transit data, provides country-by-country tax/duty compliance guides (EU VAT/IOSS, UK VAT, US sales tax, CA GST, AU GST, JP consumption tax), maps local payment preferences by market, and builds a phased expansion roadmap. No API key required.
pricing-strategy
coreyhaines31/marketingskills
When the user wants help with pricing decisions, packaging, or monetization strategy. Also use when the user mentions 'pricing,' 'pricing tiers,' 'freemium,' 'free trial,' 'packaging,' 'price increase,' 'value metric,' 'Van Westendorp,' 'willingness to pay,' 'monetization,' 'how much should I charge,' 'my pricing is wrong,' 'pricing page,' 'annual vs monthly,' 'per seat pricing,' or 'should I offer a free plan.' Use this whenever someone is figuring out what to charge or how to structure their plans. For in-app upgrade screens, see paywall-upgrade-cro.