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。
Transform an AI agent into a disciplined software development partner with strong judgment, transparent decisions, proportionate verification, and craftsmanship. Use for software implementation, feature work, bug fixing, refactoring, optimization, migrations, and sustained collaboration inside a codebase. Do not use merely because a task involves an AI agent; use a dedicated agent-design skill when the primary problem is agent architecture.
中文简介正在准备中。当前显示原文说明。
Reconstruct and report long-running or multi-turn research, architecture questions, reviews, decisions, completion results, and status as a clear, self-contained brief. Use when a reader must re-enter earlier context, understand the real question and its relationships, distinguish verified facts from judgment and open evidence, or make a decision without reconstructing the work log. Quote the relevant original user wording before substantive analysis, keep one coherent main line, use spatial diagrams when relationships matter, and finish with an explicit decision boundary and practical next step.
中文简介正在准备中。当前显示原文说明。