菜单
Systematically research a topic or repository using external evidence, claims validation, and synthesized outputs.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Design benchmark runs, ablations, dataset specs, and failure-analysis artifacts.
Investigate workspace state, draft patches, run targeted validation, and package engineering artifacts.
Turn a vague request into a structured problem statement, comparison frame, recommendation, and decision-ready artifact.
Produce multi-format presentation and campaign artifacts from one task thread.
Frame analytical questions, chart directions, metrics, and reproducible data work products.
Discover relevant skill packages and supporting tools before committing to an execution path.
| name | deep-research |
| description | Systematically research a topic or repository using external evidence, claims validation, and synthesized outputs. |
| category | research |
| owner | agent-harness |
| version | 1.0.0 |
| tags | research,evidence,web,analysis |
| tools | external_resource_hub,evidence_dossier_builder,tool_search |
| skills | research_brief,extract_facts,validate_claims,artifact_synthesis |
| artifacts | report,evidence_pack,brief |
| runtime_requirements | web,evidence |
Use this package when the task needs broad web research, evidence collection, and grounded synthesis before output generation.
