Loading...
Loading...
Found 2,609 Skills
This skill should be used when the user asks to "build a RAG pipeline", "create retrieval augmented generation", "use ColBERTv2 in DSPy", "set up a retriever in DSPy", mentions "RAG with DSPy", "context retrieval", "multi-hop RAG", or needs to build a DSPy system that retrieves external knowledge to answer questions with grounded, factual responses.
Write systems code in the style of Linus Torvalds, creator of Linux and Git. Emphasizes pragmatic excellence, performance awareness, subsystem design, and uncompromising code review. Use when writing kernel-level code or high-performance systems.
Build RAG systems - embeddings, vector stores, chunking, and retrieval optimization
Apply meta-principles of software craftsmanship: DRY, orthogonality, tracer bullets, and design by contract. Use when the user mentions "best practices", "pragmatic approach", "broken windows", "tracer bullet", or "software craftsmanship". Covers estimation, domain languages, and reversibility. For code-level quality, see clean-code. For refactoring techniques, see refactoring-patterns.
Alibaba Cloud OSS CLI (ossutil 2.0) skill. Install, configure, and operate OSS from the command line based on the official ossutil overview.
Comprehensive toolkit for generating best practice Terragrunt configurations (HCL files) following current standards and conventions. Use this skill when creating new Terragrunt resources (root configs, child modules, stacks, environment setups), or building multi-environment Terragrunt projects.
Use when adding multi-format RAG ingest, chunk, embed, and retrieval pipelines; pair with architect-python-uv-batch or architect-python-uv-fastapi-sqlalchemy.
Manage operations such as login, upload, download, transfer, and sharing for Baidu Netdisk. Complete cloud storage file management tasks via the bdpan command-line tool.
[Pragmatic DDD Architecture] Guide for creating DDD Repositories (Interfaces and Infrastructure). Use when creating repository contracts or implementing them using Drizzle ORM, Zod, and Postgres. Enforces completely typed transactions with Drizzle Transaction types (no 'unknown'), Result returns for Railway-oriented programming via neverthrow, and mapping pg node errors to domain errors. Fits our docker-compose / drizzle-kit standard testing workflow.
Analyze code repository logging coverage to ensure all function branches have LOGE/LOGI logs and identify high-frequency log risks. Supports multiple programming languages (C++, Java, Python, JavaScript, etc.)
Multi-backend storage layer with automatic failover between Redis, database, and memory backends. Includes circuit breakers per backend and health-aware routing for high availability.
Delta Lake integration with cloud storage (S3, GCS, Azure). Covers storage_options, PyArrow filesystem, time travel, and partitioned writes.