Assistant for creating, editing, and debugging reactive Python notebooks with marimo. Use when you need to build marimo notebooks, debug reactive execution, add interactive UI elements, or convert traditional notebooks to marimo format. Provides code patterns, utility functions, and best practices for marimo…
A small, readable implementation of a university research paper, baseline, or experiment in deep learning. Deep learning is a type of machine learning that learns patterns from data using layered mathematical models.
Async and concurrency best practices for Python — event-loop discipline, task lifecycle, bounded fan-out, and async generator cleanup. Triggers on writing or reviewing asyncio code, async def functions, createtask/gather/TaskGroup usage, semaphores and queues, async generators and streams, blocking-call audits, or…
Python software engineering guidelines from real PR review patterns. This skill should be used when writing, reviewing, or refactoring Python code — especially dataclasses, service interfaces, error handling, and type annotations. Triggers on tasks involving Python modules, API design, data modeling, type safety…
Extract Jupyter notebook cells into tested Python modules while preserving the exploration workflow. Use when converting prototyping notebooks into production code.
Convenções dos serviços Python do Cérebro Amigo V3 (orchestrator-py, agents-py, notifier-py). Use ao criar ou alterar: nó/grafo LangGraph, fluxo conversacional, qualquer chamada ao Claude (via client LLM unificado provider-switchável, LLMPROVIDER; vigente: Anthropic API direta — ADR-044), client/SDK de LLM, roteamento…
OpenAI Agents SDK (Python) development. Use when building AI agents, multi-agent handoffs, function tools, guardrails, sessions, streaming, or tracing with the openai-agents / agents Python package — including Azure OpenAI via LiteLLM. Triggers on imports from agents, uses of Runner.runsync/Runner.runstreamed…
Build backend AI with Vercel AI SDK v6 stable. Covers Output API (replaces generateObject/streamObject), speech synthesis, transcription, embeddings, MCP tools with security guidance. Includes v4→v5 migration and 15 error solutions with workarounds. Use when: implementing AI SDK v5/v6, migrating versions…
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright…
Migrate Python applications from LiteLLM to Portkey AI Gateway. Covers litellm.completion, Router, Proxy, fallbacks, caching, retries, callbacks, embeddings, and image generation. Use when the user wants to replace LiteLLM with Portkey or switch from LiteLLM to Portkey.
Complete reference for the Portkey AI Gateway Python SDK with unified API access to 200+ LLMs, automatic fallbacks, caching, and full observability. Use when building Python applications that need LLM integration with production-grade reliability.
Migrates Flyte 1 machine learning code to Flyte 2 and unlocks net-new v2 patterns. Use when migrating Flyte 1 ML workloads (training, HPO, GPU/deep learning, batch inference) to Flyte 2, specifying GPU resources, or building the end-to-end pipeline pattern. Trigger words - migrate training, HPO, GPU, deep learning…
Migrates Slurm (sbatch/srun) HPC workloads to Flyte 2 (the flyte Python SDK) — job scripts become typed tasks, #SBATCH pragmas become TaskEnvironment config, job arrays become flyte.map or asyncio.gather, and multi-node training becomes a clustered task environment. Use when porting an HPC or supercomputer cluster…
Use when instrumenting a Python agentic app with Monocle telemetry — this is the default, deep posture. Beyond placing the setup call and grading traces, when a gap turns out to be in Monocle itself this skill fixes Monocle directly against a local, writable clone (cloning it from upstream on first use if absent) and…
Reviews Python code for PEP8 compliance, type hints, modern best practices (Python 3.9+), and code quality. Detects anti-patterns, validates documentation, and provides severity-based recommendations. Integrates with modern tooling (ruff, mypy, uv).
Sets up modern Python projects with uv tooling, src layout, and PEP8 standards. Handles both new and existing projects, presents interactive library selection for CLI/TUI apps, generates pyproject.toml, and provides complete scaffolding with type hints and proper structure.
Modify EDPS (ESO Data Processing System) workflows written in Python. Add or change tasks, datasources, and classification rules in instrument workflow packages. Use when editing wkf.py, datasources.py, classification.py, or related workflow files for any ESO instrument pipeline.
Use when writing Python code that imports from inkbox, uses pip install inkbox, or when adding email, phone, or agent identity features using the Inkbox Python SDK.
★not rated 2 5mo agoA41 tokens
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: