원클릭으로
research
Deep research on any topic using web search and browsing. Synthesizes information from multiple sources into a comprehensive report.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
Deep research on any topic using web search and browsing. Synthesizes information from multiple sources into a comprehensive report.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
| name | research |
| description | Deep research on any topic using web search and browsing. Synthesizes information from multiple sources into a comprehensive report. |
| triggers | ["research this","find out about","what is the best","compare options for","investigate"] |
Conduct thorough research on a topic by searching the web, reading multiple sources, and synthesizing findings into a clear report.
web_search with 2-3 different query formulationsweb_browseweb_search — find relevant pagesweb_browse — read full page contenthttp_fetch — access APIs for datamemory_store — save research findings for laterknowledge_store — add entities/relations to knowledge graph## Research Report: {topic}
### Summary
{2-3 sentence overview}
### Key Findings
1. {finding with source}
2. {finding with source}
3. {finding with source}
### Detailed Analysis
{in-depth discussion}
### Sources
- [Title](url) — what was learned
- [Title](url) — what was learned
Enforces a strict 4-phase methodology (Plan, Generate, Review, DoD) for development tickets to ensure high-quality, secure, and production-ready code. Features a continuous YOLO mode loop for autonomous task completion.
Performs thorough code review on files or diffs. Checks for bugs, security issues, performance problems, and code quality.
Systematic debugging assistant. Analyzes errors, traces root causes, and suggests fixes with evidence.
Verifies that NDE-OS agent core code is production-ready with no mocks, no fakes, no TODOs, and matches all R&D comparison claims. Use after implementing any agent core module, before marking a task as complete, or when auditing code quality against the implementation plan.
Explains code in plain language. Breaks down complex logic, traces execution flow, and creates documentation.
Sets up new project scaffolding with proper structure, configuration, and tooling. Supports Rust, TypeScript, Python, and more.