深度调研的多Agent编排工作流：把一个调研目标拆成可并行子目标，用 Claude Code 非交互模式（`claude -p`）运行子进程；联网与采集优先使用已安装的 skills，其次使用 MCP 工具；用脚本聚合子结果并分章精修，最终交付"成品报告文件路径 +...
Web research with Graph-of-Thoughts for fast-changing topics. Use when user requests research, analysis, investigation, or comparison requiring current information. Features hypothesis testing,...
This skill should be used when the user asks to "research code", "how does X work", "where is Y defined", "who calls Z", "trace code flow", "find usages", "review a PR", "explore this library",...
This skill should be used when users mention 'generate rules', 'isolation rules', 'methodology preset', 'apply preset', 'saturation', 'am I saturated', 'branch', 'fork', 'explore alternative',...
This skill should be used when the user asks to "identify web application vulnerabilities", "explain common security flaws", "understand vulnerability categories", "learn about injection attacks",...
This skill should be used when the user asks to "identify web application vulnerabilities", "explain common security flaws", "understand vulnerability categories", "learn about injection attacks",...
This skill should be used when the user asks to "identify web application vulnerabilities", "explain common security flaws", "understand vulnerability categories", "learn about injection attacks",...
This skill should be used when the user asks to "identify web application vulnerabilities", "explain common security flaws", "understand vulnerability categories", "learn about injection attacks",...
This skill should be used when the user asks to "identify web application vulnerabilities", "explain common security flaws", "understand vulnerability categories", "learn about injection attacks",...
This skill should be used when the user asks to "identify web application vulnerabilities", "explain common security flaws", "understand vulnerability categories", "learn about injection attacks",...
This skill should be used when the user asks to "identify web application vulnerabilities", "explain common security flaws", "understand vulnerability categories", "learn about injection attacks",...
Enables Claude to conduct comprehensive research using Gemini Deep Research for in-depth analysis and reports
Document codebase as-is with thoughts directory for historical context
Document codebase as-is with thoughts directory for historical context
Use when formulating clinical research questions (PICOT framework), evaluating health evidence quality (study design hierarchy, bias assessment, GRADE), prioritizing patient-important outcomes,...
Analyze user research data to uncover insights, identify patterns, and inform design decisions. Synthesize qualitative and quantitative research into actionable recommendations.
Conduct comprehensive research on any topic by coordinating 2-4 specialized researcher agents in parallel, then synthesizing findings into a detailed report via mandatory report-writer agent delegation
This skill should be used when the user asks to "test for insecure direct object references," "find IDOR vulnerabilities," "exploit broken access control," "enumerate user IDs or object...
This skill should be used when the user asks to "test for insecure direct object references," "find IDOR vulnerabilities," "exploit broken access control," "enumerate user IDs or object...
This skill should be used when the user asks to "test for insecure direct object references," "find IDOR vulnerabilities," "exploit broken access control," "enumerate user IDs or object...