一键导入
research-engine
High-performance research intelligence for web search, content synthesis, and iterative deep-dive investigations.
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。
菜单
High-performance research intelligence for web search, content synthesis, and iterative deep-dive investigations.
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
A project and task management system for tracking work across the Abraxas system.
The Sovereign Vault for verified truth fragments and historical provenance tracking.
Soter is the Risk Sensing & Triggering pillar of the Sovereign Brain. It monitors for linguistic sycophancy and mechanistic attention sinks to trigger an Epistemic Crisis (T=1) and assign a Risk Score (R[0-5]).
The core governance and system integrity layer of the Abraxas sovereign environment.
The ingestion and filtration loop for external data entering the Abraxas system.
The Void Mapper for identifying and resolving epistemic gaps.
| name | research-engine |
| description | High-performance research intelligence for web search, content synthesis, and iterative deep-dive investigations. |
The Research Engine provides the tools necessary to expand the system's knowledge base through active information gathering and synthesis. It automates the process of discovering, fetching, and distilling information from the open web.
The engine moves beyond simple search by implementing iterative discovery and structured synthesis.
The engine utilizes a multi-stage search process:
The synthesize tool transforms disparate pieces of information into structured reports.
A multi-pass process that evolves from a broad question to specific, verified claims.
web_searchSearch the web for current information.
query (required), max_results (optional).web_fetchExtract content from a specific URL.
url (required), extract_links (optional).synthesize_reportSynthesize a report from multiple sources.
topic (required), sources (list of {type, value}), report_format (optional).deep_dive_researchExecute a multi-iteration research workflow.
research_question (required), max_iterations (optional), require_verification (optional), focus_areas (optional).health_checkDiagnostic status of the engine and its API dependencies.
verbose (optional).requests for HTTP communication and re for HTML cleaning.