FastAPI web framework patterns. Triggers on: fastapi, api endpoint, dependency injection, pydantic model, openapi, swagger, starlette, async api, rest api, uvicorn.
Interact with Google's Gemini model via CLI. Use when needing a second opinion from another LLM, cross-validation, or leveraging Gemini's Google Search grounding. Supports multi-turn conversations...
This skill should be used when users question their philosophical stance, their language contradicts their declared epistemology, they are moving between stages and want to verify coherence,...
Chunked N-D arrays for cloud storage. Compressed arrays, parallel I/O, S3/GCS integration, NumPy/Dask/Xarray compatible, for large-scale scientific computing pipelines.
RNN+Transformer hybrid with O(n) inference. Linear time, infinite context, no KV cache. Train like GPT (parallel), infer like RNN (sequential). Linux Foundation AI project. Production at Windows,...
RNN+Transformer hybrid with O(n) inference. Linear time, infinite context, no KV cache. Train like GPT (parallel), infer like RNN (sequential). Linux Foundation AI project. Production at Windows,...
Chunked N-D arrays for cloud storage. Compressed arrays, parallel I/O, S3/GCS integration, NumPy/Dask/Xarray compatible, for large-scale scientific computing pipelines.
Chunked N-D arrays for cloud storage. Compressed arrays, parallel I/O, S3/GCS integration, NumPy/Dask/Xarray compatible, for large-scale scientific computing pipelines.
Use when designing REST or GraphQL APIs, creating OpenAPI specifications, or planning API architecture. Invoke for resource modeling, versioning strategies, pagination patterns, error handling standards.
Use when designing REST or GraphQL APIs, creating OpenAPI specifications, or planning API architecture. Invoke for resource modeling, versioning strategies, pagination patterns, error handling standards.
Create custom OpenCode commands for repetitive tasks. Define command prompts, arguments, shell output injection, file references, and configure agents, models, and descriptions.
Generate SAP Fiori Launchpad URLs from app names using AppList.json. Looks up app information by name and constructs proper FLP URLs with required parameters like sap-client and sap-language.
Use when designing prompts for LLMs, optimizing model performance, building evaluation frameworks, or implementing advanced prompting techniques like chain-of-thought, few-shot learning, or...
Language-agnostic testing principles including TDD, test quality, coverage standards, and test design patterns. Use when writing tests, designing test strategies, or reviewing test quality.
Invokes Google Gemini models for structured outputs, multi-modal tasks, and Google-specific features. Use when users request Gemini, structured JSON output, Google API integration, or...
Develop Ruby on Rails applications with models, controllers, views, Active Record ORM, authentication, and RESTful routes. Use when building Rails applications, managing database relationships,...
Execute approved beads using sub-agent model. Each bead is a work package - agent loads surgical context, designs, implements, and verifies. Continues until feature complete.
Distributed training orchestration across clusters. Scales PyTorch/TensorFlow/HuggingFace from laptop to 1000s of nodes. Built-in hyperparameter tuning with Ray Tune, fault tolerance, elastic...
Distributed training orchestration across clusters. Scales PyTorch/TensorFlow/HuggingFace from laptop to 1000s of nodes. Built-in hyperparameter tuning with Ray Tune, fault tolerance, elastic...
Guides agent to maintain synchronization across model directories (.github, .claude, .codex, .gemini) after modifying skills, agents, or prompts. Ensures consistency between AGENTS.md, CLAUDE.md,...