“learning”的搜索结果

Applies the reasoning, principles, and frameworks of Jürgen Schmidhuber (LSTM co-inventor and deep learning pioneer). Reach for this skill whenever tackling problems involving sequence learning, artificial curiosity, intrinsic motivation, reinforcement learning architectures, or predicting long-term technological and cosmic evolution. Use this when discussing AGI timelines, the history and attribution of AI breakthroughs, data compression as learning, or when designing autonomous agents that must set their own goals. Trigger this skill for topics like recurrent neural networks, algorithmic information theory, open-source AI democratization, and evaluating true existential risks versus media hype.

中文简介正在准备中。当前显示原文说明。

Applies the reasoning style of Ilya Sutskever (deep learning pioneer, co-founder of OpenAI and Safe Superintelligence Inc.) to problems involving AI architecture, scaling laws, alignment, and research strategy. Reach for this skill whenever discussing machine learning paradigms, the limits of compute and data, AGI timelines, superintelligence safety, or deciding between hardcoding vs. learning. Trigger this skill for questions about next-word prediction, reinforcement learning efficiency, generalization gaps, and transitioning from brute-force scaling to fundamental research, even if the user doesn't explicitly name him.

中文简介正在准备中。当前显示原文说明。

Design a service-learning project connecting genuine community need with embedded curriculum learning. Use when planning community projects, civic engagement, or social action units.

中文简介正在准备中。当前显示原文说明。

Structure a direct experience into a full learning cycle with concrete experience, reflection, and conceptual transfer. Use when planning field trips, simulations, or practical tasks.

中文简介正在准备中。当前显示原文说明。

Meta-cognitive and practical strategies for learning any language -- learner autonomy, goal setting, strategy taxonomy (Oxford's SILL framework), memory strategies, cognitive strategies (note-taking, summarizing, analyzing, reasoning), compensation strategies, metacognitive strategies (planning, monitoring, evaluating), affective strategies (managing anxiety, self-encouragement), social strategies (collaboration, questioning, empathy), immersion design, study habit optimization, plateau diagnosis, and motivation maintenance. Use when designing a language learning plan, diagnosing a learner's stuck points, selecting study methods, or building self-directed learning skills.

中文简介正在准备中。当前显示原文说明。

Add a new learning to the agent learnings file. Use when the user says /add-learning, asks to record a lesson, or when an implementation produced a reusable insight worth preserving for future agents.

中文简介正在准备中。当前显示原文说明。

Agent assistance skill that provides stuck detection, memory management, and session learning capabilities for AI agents Trigger terms: agent stuck, loop detected, session memory, agent learning, condense memory, stuck detection, agent memory, session learnings, extraction Use when: User reports agent is stuck, looping, or needs memory/learning management

中文简介正在准备中。当前显示原文说明。

Verify, customize, or opt out of moflo's AUTOMATIC durable-learning sharing across git worktrees / Conductor workspaces on one machine. As of the worktree-auto-sharing change this is on by default — learnings converge across a repo's worktrees with no setup. Use when the user asks "is memory shared across my worktrees?", "where are my worktree learnings stored?", "turn off worktree memory sharing", "share learnings across my separate clones", or "point my worktrees at a custom store". For a team or cross-machine (git-tracked) sharing, use /memory-team instead.

中文简介正在准备中。当前显示原文说明。

Audit and maintain the learnings in `docs/solutions/` against the current codebase — fix drifted paths and links, merge overlapping docs, replace guidance the code no longer supports, delete obsolete docs, reconcile the `CONCEPTS.md` glossary, then report and commit. Also bootstraps `CONCEPTS.md` on request and, when asked, culls docs whose reasoning the code already explains. Use for "refresh the learnings", "audit docs/solutions", "are our solution docs still accurate", "clean up / prune the learnings", "create a CONCEPTS.md", or after a refactor, rename, migration, or dependency upgrade that likely invalidated documented solutions. Not for capturing a new learning — use `learn-with-docs`.

中文简介正在准备中。当前显示原文说明。

Persistent cross-session knowledge base. Manages per-project learnings that compound across sessions — patterns, pitfalls, preferences, and project quirks. The agent gets smarter on your codebase over time. At session start, searches relevant learnings. During sessions, logs discoveries. Supports review, search, prune, and export. Use proactively when the agent encounters a durable project quirk, user preference, or pattern that would save 5+ minutes next time. Also use at session start to recover context. Triggers: "remember this", "log this", "what have we learned?", "show learnings".

中文简介正在准备中。当前显示原文说明。

Trains and applies base-resolution deep learning models on ChIP-seq / ChIP-nexus / CUT&RUN data. Uses BPNet (Avsec 2021 Nat Genet 53:354; soft motif syntax from ChIP-nexus), chromBPNet (Pampari A et al 2024 bioRxiv; bias-factorized base-resolution profiles), EnFormer (Avsec 2021 Nat Methods 18:1196; 196 kb input, ~100 kb effective receptive field), DeepSEA (Zhou 2015; multi-task CNN), and JASPAR 2026 deep-learning collection (1259 BPNet ChIP models). Performs in silico mutagenesis for variant-effect prediction, DeepLIFT/Grad attribution, and TF-MoDISco motif discovery from attribution scores. Use when predicting variant effects on TF binding, discovering soft motif syntax / cooperativity, integrating ChIP-seq with sequence-only predictions, or applying precomputed JASPAR Deep Learning models to new variants.

中文简介正在准备中。当前显示原文说明。

Save the latest learning as a numbered markdown file under ~/.claude/learnings and update the learnings index with title and tags. Use when the user says "save", asks to record a learning, or wants the current insight stored for later.

中文简介正在准备中。当前显示原文说明。

Machine learning in Python with scikit-learn. Use when working with supervised learning (classification, regression), unsupervised learning (clustering, dimensionality reduction), model evaluation, hyperparameter tuning, preprocessing, or building ML pipelines. Provides comprehensive reference documentation for algorithms, preprocessing techniques, pipelines, and best practices.

中文简介正在准备中。当前显示原文说明。

Trains and applies base-resolution deep learning models on ChIP-seq / ChIP-nexus / CUT&RUN data. Uses BPNet (Avsec 2021 Nat Genet 53:354; soft motif syntax from ChIP-nexus), chromBPNet (Pampari A et al 2025 Nat Genet; bias-factorized base-resolution profiles), EnFormer (Avsec 2021 Nat Methods 18:1196; 196 kb input, ~100 kb effective receptive field), DeepSEA (Zhou 2015; multi-task CNN), and JASPAR 2026 deep-learning collection (1259 BPNet ChIP models). Performs in silico mutagenesis for variant-effect prediction, DeepLIFT/Grad attribution, and TF-MoDISco motif discovery from attribution scores. Use when predicting variant effects on TF binding, discovering soft motif syntax / cooperativity, integrating ChIP-seq with sequence-only predictions, or applying precomputed JASPAR Deep Learning models to new variants.

中文简介正在准备中。当前显示原文说明。

Manage project learnings. Review, search, prune, and export what gstack has learned across sessions. Use when asked to "what have we learned", "show learnings", "prune stale learnings", or "export learnings". Proactively suggest when the user asks about past patterns or wonders "didn't we fix this before?"

中文简介正在准备中。当前显示原文说明。

Trains and applies base-resolution deep learning models on ChIP-seq / ChIP-nexus / CUT&RUN data. Uses BPNet (Avsec 2021 Nat Genet 53:354; soft motif syntax from ChIP-nexus), chromBPNet (Pampari A et al 2025 Nat Genet; bias-factorized base-resolution profiles), EnFormer (Avsec 2021 Nat Methods 18:1196; 196 kb input, ~100 kb effective receptive field), DeepSEA (Zhou 2015; multi-task CNN), and JASPAR 2026 deep-learning collection (1259 BPNet ChIP models). Performs in silico mutagenesis for variant-effect prediction, DeepLIFT/Grad attribution, and TF-MoDISco motif discovery from attribution scores. Use when predicting variant effects on TF binding, discovering soft motif syntax / cooperativity, integrating ChIP-seq with sequence-only predictions, or applying precomputed JASPAR Deep Learning models to new variants.

中文简介正在准备中。当前显示原文说明。

为尚未使用机器学习的现有应用梳理推荐、分类、预测等功能的引入步骤，从明确问题、检查数据到初始模型的训练、评估和集成。

• 为现有应用添加推荐功能
• 检查训练数据是否准备就绪
• 为预测功能设计备用规则

从复杂工作与失败中提炼根本原因、下次可采取的行动和识别问题的具体信号，整理成可复用的学习记录，并将根因相同的新案例合并到已有记录中。

• 在复杂工作后记录收获
• 记录故障调查的根因与教训
• 合并根因相同的学习记录

Review recent Claude Code chats to identify development strengths, recurring difficulties, and learning priorities. Receive a personalized report with practical recommendations and relevant HackerNews articles, delivered to your own Slack direct messages.

中文简介正在准备中。当前显示英语简介。

• Reviewing development habits from recent chats
• Prioritizing recurring technical difficulties
• Finding learning articles relevant to current work

Capture lessons from completed tasks, train patterns from explicit examples, and consolidate accumulated learning into long-term storage. Use SONA and MicroLoRA adaptation tools for individual domains, then verify results in the appropriate stores.

中文简介正在准备中。当前显示英语简介。

• Capturing lessons after a successful task
• Consolidating accumulated task histories
• Creating learning adapters for separate domains

Create agents that learn from interactions and adapt their behavior over time. Monitor learning progress, review efficiency and accuracy metrics, trigger adjustments from feedback, and share acquired knowledge with other agents through dedicated tools.

中文简介正在准备中。当前显示英语简介。

• Create an agent with initial learning settings
• Monitor learning progress, efficiency, and accuracy
• Adjust agent behavior based on feedback

Learn AI engineering by building a project one stage at a time. The tutor guides predictions, learner-written code, automated checks, and reflection, then records progress so the next session can continue from the right stage.

中文简介正在准备中。当前显示英语简介。

• Learn AI engineering through hands-on projects
• Resume a project from the next unfinished stage
• Find coding mistakes with step-by-step hints

Build and evaluate single-agent reinforcement learning experiments, where an agent learns actions from rewards. Use Stable Baselines3 to choose algorithms, create environments, monitor training, and save models with the normalization data needed for consistent evaluation.

中文简介正在准备中。当前显示英语简介。

• Set up a reproducible reinforcement learning experiment
• Create and validate a custom Gymnasium environment
• Monitor training and save checkpoints

Plan and review PufferLib reinforcement learning workflows, where agents learn through rewards. Covers version-specific environment checks, parallel execution, training and evaluation plans, plus checkpoint inspection before loading saved models.

中文简介正在准备中。当前显示英语简介。

• Choose APIs for a specific PufferLib version
• Check environment behavior before training
• Create training and evaluation plans with separate seeds