Loading...
Loading...
Found 36 Skills
AI video pipeline validator for Veo 3 feasibility, 8-second scene chunking, and shot continuity. USE WHEN: Validating screenplays for AI video generation, chunking scenes into 8-second segments, generating continuation prompts, scoring feasibility risk, or adding editing metadata. PIPELINE POSITION: screenwriter → **production-validator** → imagine/arch-v INPUT: XML from screenwriter skill (scene tags with duration, action, key_visuals) OUTPUT: Enhanced XML with validation, chunks, continuity tags, and Veo 3 prompts KEY FUNCTIONS: - Veo 3 feasibility validation with risk scoring (LOW/MEDIUM/HIGH/CRITICAL) - 8-second scene chunking with continuation prompts - Shot continuity tagging for editors - Technical optimization for AI-friendly alternatives
CLIP, SigLIP 2, Voyage multimodal-3 patterns for image+text retrieval, cross-modal search, and multimodal document chunking. Use when building RAG with images, implementing visual search, or hybrid retrieval.
Data pipelines, feature stores, and embedding generation for AI/ML systems. Use when building RAG pipelines, ML feature serving, or data transformations. Covers feature stores (Feast, Tecton), embedding pipelines, chunking strategies, orchestration (Dagster, Prefect, Airflow), dbt transformations, data versioning (LakeFS), and experiment tracking (MLflow, W&B).
Vector database implementation for AI/ML applications, semantic search, and RAG systems. Use when building chatbots, search engines, recommendation systems, or similarity-based retrieval. Covers Qdrant (primary), Pinecone, Milvus, pgvector, Chroma, embedding generation (OpenAI, Voyage, Cohere), chunking strategies, and hybrid search patterns.
Use when performing bulk insert, update, or delete operations in Bknd. Covers createMany, updateMany, deleteMany, batch processing with progress, chunking large datasets, error handling strategies, and transaction-like patterns.
UX patterns for complex forms including multi-step wizards, cognitive chunking (5-7 fields max), progressive disclosure, and conditional fields. Use when building checkout flows, onboarding wizards, or forms with many fields.
Efficient project file browser. Use it when you need to list the entire project structure, fuzzy search files, or safely read (supports chunking of large files) local codebase content.
Document chunking implementations and benchmarking tools for RAG pipelines including fixed-size, semantic, recursive, and sentence-based strategies. Use when implementing document processing, optimizing chunk sizes, comparing chunking approaches, benchmarking retrieval performance, or when user mentions chunking, text splitting, document segmentation, RAG optimization, or chunk evaluation.
Recursive Language Model context management for processing documents exceeding context window limits. Enables Claude to match Gemini's 2M token context capability through chunking, sub-LLM delegation, and synthesis.
Proactive token budget assessment and task chunking strategy. Use this skill when queries involve multiple large file uploads, requests for comprehensive multi-document analysis, complex multi-step workflows with heavy research (10+ tool calls), phrases like "complete analysis", "full audit", "thorough review", "deep dive", or tasks combining extensive research with large output artifacts. This skill helps assess token consumption risk early and recommend chunking strategies before beginning work.
tokenization과 context window를 중심으로 긴 입력 처리 한계와 실무 대응 방법(분할, 요약, 우선순위화)을 학습시키는 모듈.
Extract text and data from PDF documents