全部能力

Use when researching Apple frameworks, APIs, or WWDC sessions - provides techniques for retrieving full transcripts, code samples, and documentation using…

Use this skill for general PostgreSQL table design. **Trigger when user asks to:** - Design PostgreSQL tables, schemas, or data models when creating new tables and when modifying existing ones. - Choose data types, constraints, or indexes for PostgreSQL - Create user tables, order tables, reference tables, or JSONB schemas - Understand PostgreSQL best practices for normalization, constraints, or indexing - Design update-heavy, upsert-heavy, or OLTP-style tables **Keywords:** PostgreSQL schema, table design, data types, PRIMARY KEY, FOREIGN KEY, indexes, B-tree, GIN, JSONB, constraints, normalization, identity columns, partitioning, row-level security Comprehensive reference covering data types, indexing strategies, constraints, JSONB patterns, partitioning, and PostgreSQL-specific best practices.

High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search,…

Guide to selecting and optimizing embedding models for vector search applications.

Compress large language models using knowledge distillation from teacher to student models. Use when deploying smaller models with retained performance,…

Data framework for building LLM applications with RAG. Specializes in document ingestion (300+ connectors), indexing, and querying. Features vector indices,…

Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm,…

NVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation, fact-checking, hallucination detection, PII…

Use when the user asks to "research code", "how does X work", "where is Y defined", "who calls Z", "trace code flow", "find usages", "explore this library",…

Framework for state-of-the-art sentence, text, and image embeddings. Provides 5000+ pre-trained models for semantic similarity, clustering, and retrieval.…

Persistent cross-session memory using Memento MCP knowledge graph (mcp__memento__* tools). Recall-before-acting: search memory before starting tasks, on errors, and when receiving corrections. Multi-dimensional search: two queries per recall event (technical topic + process/workflow learnings). Store-after-discovery: persist solutions, conventions, and corrections immediately. Three-step recall: search, open_nodes, traverse relations. WORKING_STATE.md for crash recovery. Self-reminder protocol every 5-10 messages. Activate on task start, errors, corrections, session boundaries, or explicit memory requests. See references/agents-md-setup.md for AGENTS.md integration.

Half-Quadratic Quantization for LLMs without calibration data. Use when quantizing models to 4/3/2-bit precision without needing calibration datasets, for fast…

亚马逊关键词研究与市场机会分析，面向卖家。获取自动补全建议（长尾关键词），分析竞争对手格局，以及…

Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6×…

Provides guidance for performing causal interventions on PyTorch models using pyvene's declarative intervention framework. Use when conducting causal tracing,…

Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training

High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2×…

GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics),…

Build complex AI systems with declarative programming, optimize prompts automatically, create modular RAG systems and agents with DSPy - Stanford NLP's…

Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream…