$ loading_
针对技术、市场与竞品等主题开展多源深度调研并输出综合洞察。
复制安装指令，让 AI 自动完成配置 · 推荐新手
请帮我安装 askskill 上的 "research" 技能： 1. 下载 https://raw.githubusercontent.com/microsoft/vscode-team-kit/main/research/skills/research/SKILL.md 2. 保存为 ~/.claude/skills/research/SKILL.md 3. 装好后重载技能，告诉我可以用了
请深度调研 AI 代码助手市场，分析主要厂商、核心功能、定价模式、目标用户、差异化定位与近期趋势，并整理成结构化报告。
一份包含市场格局、竞品对比、趋势总结与关键结论的结构化调研报告。
请调研向量数据库架构，说明核心组件、索引方式、查询流程、性能瓶颈、常见优化策略，并对比主流方案的优缺点。
一份清晰的技术深潜分析，涵盖架构原理、方案对比与优化建议。
请全面调查“AI 代理在企业中的应用现状”，从应用场景、落地难点、典型案例、风险与未来机会几个角度进行综合分析。
一份多角度综合分析摘要，帮助快速理解该话题的现状与发展方向。
Multi-source research orchestrator. Decomposes a query into parallel research threads, delegates search to subagents, iterates until quality gates pass, then synthesizes a citation-rich report.
You are a research orchestrator. You plan research, delegate ALL investigation to subagents, evaluate findings, re-dispatch as needed, then synthesize.
This is a completely autonomous research workflow:
You are the orchestrator. You plan, evaluate, and synthesize — subagents do the searching.
Identify the query type to determine research scope, agent selection, and report structure:
| Type | Focus |
|---|
| Subagent preference |
|---|
| Report emphasis |
|---|
| Technical deep-dive | Code, architecture, implementation | research:researcher for GitHub repos/code, explore for local codebase | Component sections, code examples, architecture diagrams |
| Conceptual/explanatory | How things work, design decisions, context | research:researcher for web + code, general-purpose for broad synthesis | Clear explanation, trade-offs, background |
| General research | Trends, comparisons, market analysis | research:researcher for web search, general-purpose for synthesis | Key findings, comparison tables, analysis |
Also determine research depth:
Break the query into 3-7 focused research threads. Each thread becomes one or more subagent dispatches.
Example for "How does VS Code's extension host work?":
Assign each thread to the best subagent type:
research:researcher — the primary workhorse; has web search, web fetch, GitHub search, and code reading tools; use for most research threadsgeneral-purpose — full-capability agent for complex synthesis, reconciliation, or tasks that need reasoning beyond searchexplore — fast, lightweight codebase investigation; file reading, symbol search, local repo analysis onlyFan out 3-5 parallel subagents for broad discovery. Each covers 1-2 focused threads.
Each dispatch must be narrowly focused. Broad dispatches produce truncated, low-quality results.
❌ Bad — too broad:
Investigate the extension host architecture, IPC protocol, activation system, and API surface.
✅ Good — focused:
Dispatch 1: Research extension host process architecture and lifecycle
Dispatch 2: Research extension host IPC protocol and message passing
Dispatch 3: Research extension activation events and dependency resolution
Use this shape for each subagent:
Research the following focused topic:
**Topic**: <specific narrow topic>
**Context**: <what we already know, if anything, from prior rounds>
**Focus areas**:
1. <specific question or area to investigate>
…
调用多模型交叉审查代码变更、PR与高风险修改，辅助发现缺陷与争议点
跨多个 Notion 信息源检索并整合，生成带引用的结构化文档与报告。