Design and build AI agents for any domain. Use when users: (1) ask to "create an agent", "build an assistant", or "design an AI system" (2) want to understand agent architecture, agentic patterns, or autonomous AI (3) need help with capabilities, subagents, planning, or skill mechanisms (4) ask about AI coding agents, agent runtimes, or similar internals (5) want to build agents for business, research, creative, or operational tasks Keywords: agent, assistant, autonomous, workflow, tool use, multi-step, orchestration

中文简介正在准备中。当前显示原文说明。

Deeply research technical architecture, source code, mechanisms, SDKs, frameworks, project comparisons, and system-design options across repositories, history, official docs, issues, discussions, and high-quality community signals. Use when the user asks for deep research, source-level understanding, architecture comparison, mechanism satisfaction, or evidence for designing a system. Always map the question and obtain confirmation before beginning substantive research; skip for simple factual lookups or straightforward implementation tasks.

中文简介正在准备中。当前显示原文说明。

Coach leaders and managers to prepare, run, and review high-bandwidth meetings that advance real work and decisions. Use for meeting retrospectives, employee work reviews, decision meetings, agenda and question design, direct feedback, meeting-quality diagnosis, or repeated low-value discussions. Preserve direct standards without taking over the worker's work or degrading the truth signal.

中文简介正在准备中。当前显示原文说明。

Coach workers, employees, and individual contributors to turn meetings, transcripts, minutes, and work notes into better execution: infer leader expectations, diagnose previous work, identify next actions, judge delivery readiness, and prepare a high-bandwidth update. Use after meetings, during work, before reviews, or across repeated low-value discussions. Perform semantic review from source evidence.

中文简介正在准备中。当前显示原文说明。

Research why neural architectures and training methods work through forward computation, geometry, gradients, optimization dynamics, historical experiments, and competing explanations. Use for deep mechanism questions about neural networks, AI models, layers, representations, or training; explain the meaning in plain language with evidence and explicit limits.

中文简介正在准备中。当前显示原文说明。

Recover and review local human-AI conversations from Claude Code, Codex, opencode, Grok Build, and Cursor. Use when the user wants to revisit, search, extract, summarize, or compare work across Agent session stores, time ranges, projects, or named conversations. Follow the user's requested output; question clustering, problem-space mapping, artifact review, drift analysis, and insights are optional lenses.

中文简介正在准备中。当前显示原文说明。