Results for “dream-interpretation”

Consolidates auto-memory files in ~/.claude/projects by auditing, planning, and executing a 4-phase cleanup with user approval.

按关键词检索周公解梦释义，支持分页。当用户说：梦见蛇是什么意思？梦到飞代表什么？或类似解梦问题时，使用本技能。

当需要将模糊的长期愿景转化为可执行的日常行动，以提升专注力和生活掌控感时

Search conversation history and access Dream-managed profile and memory files without editing them.

当需要为特定挑战或目标进行心态和角色转换时

融合未来蓝图与符号抽象能力，通过符号系统构建未来愿景，将抽象的未来概念转化为具体的符号表达，创造新的未来可能性。

贾宝玉（古典虚构）认知与表达框架（压缩蒸馏）：情不情、反仕途经济、女儿崇拜叙事… 触发：红楼梦 等。虚构；非性别刻板侮辱

当个人感到迷茫，不确定自己真正想要什么，或发现当前追求无法带来深层满足时，调用此模型来探索和澄清内在真实欲望

A reflective tarot draw for emotional support (presence-first, non-clinical, non-predictive).

Socratic deep interview with mathematical ambiguity gating before explicit execution approval

Analyzes evaluation results by requiring a stated hypothesis before examining data, then compares expectations to actual result files to prevent post-hoc rationalization.

DeepEval — LLM evaluation framework, RAG metrics, hallucination detection, red-teaming, CI/CD integration

Mathematical AI interpretability with sheaf cohomology, spectral analysis, causal inference, and hallucination prevention

"Make it interpretable" is four different requests.

Surface beliefs, assumptions, stories, and values shaping a system. Use when deeper mental models need examining with care and evidence.

Curating cross-agent knowledge and institutional memory: extracts patterns from agent journals into METAPATTERNS.md, detects knowledge decay, propagates best practices. Use for memory curation.

Runs focused experiments to validate feasibility of an idea, saving artifacts to .planning/spikes/ and supporting both idea and frontier modes.

Provides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution. Use when needing to run interpretability experiments on massive models (70B+) without local GPU resources, or when working with any PyTorch architecture.

DreamLIP: Language-Image Pre-training with Long Captions

Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when reverse-engineering model algorithms, studying attention patterns, or performing activation patching experiments.

Clarify vague requirements through exploratory questioning and option generation before committing to research or implementation.

将产品想法、用户反馈、研究数据、云文档、附件和已有方案转化为有依据的产品判断、策略、MVP、优先级、Roadmap、PRD、用户故事、验收标准或方案评审。任务涉及产品决策、需求取舍、存量产品修改、范围变更、上线复盘或产品文档交付时使用，即使用户没有说‘产品经理’；纯转写、翻译、校对、格式转换、资料摘要或已定方案的技术实现不由本 Skill 主导，除非仍需产品判断。用户提供链接、文件、截图、脑图、表格、评论或旧产物时，先读取真实内容。

🔮 Divination — Oracle Toolkit for AI Agents

许仙（神话剧虚构）认知与表达框架（压缩蒸馏）：懦弱书生、凡俗与仙恋张力 触发：新白娘子传奇 等。虚构

Extracts and formalizes domain terminology from a conversation into a consistent glossary saved to a local file.

Structured brainstorming for projects and features. Explores multiple options before implementation.

当意识到当前行为模式可能导致不理想的未来，需要一种具体方法来激发改变动力时

Translates user intent into a precise, unambiguous specification and requirements.

Agent skill for agent - invoke with $agent-agent

当个人或组织经历重大环境变化、目标转换或阶段性迷茫时，用于理解当前所处阶段、预测发展轨迹并规划应对策略

Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when reverse-engineering model algorithms, studying attention patterns, or performing activation patching experiments.

Inspect and manipulate transformer internals via HookPoints and activation caching for mechanistic interpretability research.

Analyzes a class for primitive obsession and proposes value object extractions with validation, structure, and refactoring guidance.

融合潜能蒸馏与符号抽象能力，将抽象的潜能转化为符号系统，构建基于符号的潜能表达框架。

当用户提出一个想法或诉求时，通过对话挖掘真实意图、明确边界，提炼成清晰、可执行的概念。