Loading...
Loading...
Found 1,748 Skills
Build Python agents with Agentica SDK - @agentic decorator, spawn(), persistence, MCP integration
Instruments Python and TypeScript code with MLflow Tracing for observability. Triggers on questions about adding tracing, instrumenting agents/LLM apps, getting started with MLflow tracing, or tracing specific frameworks (LangGraph, LangChain, OpenAI, DSPy, CrewAI, AutoGen). Examples - "How do I add tracing?", "How to instrument my agent?", "How to trace my LangChain app?", "Getting started with MLflow tracing", "Trace my TypeScript app"
Manages Python CLI tools with uv. Learn when to use uvx for temporary execution, uv tool install for persistent tools, and how to differentiate between tool dependencies and project dependencies. Includes version management, listing, cleanup, and scenarios for running tools with specific Python versions.
Manages Python project dependencies with uv. Learn how to add, remove, and updates dependencies, organize them into groups (dev, test, lint, docs), pin versions, handle conflicts, and manages lock files for reproducible installations across environments. Use when adding or updating packages, organizing development dependencies, resolving version conflicts, or managing lock files in CI/CD pipelines.
Initialize and configure new Python projects with uv, including creating projects, setting up pyproject.toml, managing dependency groups, and pinning Python versions. Use when starting new projects, configuring development environments, or standardizing project structure with uv. Covers `uv init`, `uv add`, `uv python pin`, and initial project scaffolding with proper dependency organization.
Debugs and resolves common uv issues. Learn to diagnose dependency resolution failures, handle version conflicts, fix cache problems, troubleshoot Python environment issues, optimize performance, and solve platform-specific problems. Use when uv commands fail, dependencies won't resolve, cache is corrupted, Python installation issues occur, or performance is slow.
Migrate existing Python projects to uv from pip, Poetry, Pipenv, or Conda. Learn how to convert dependency files, preserve development environment setup, validate the migration, and plan team rollout. Use when converting legacy projects to modern uv tooling, consolidating different package managers, or standardizing Python development workflows across teams.
Provides Complete patterns for testing async Python code with pytest: pytest-asyncio configuration, AsyncMock usage, async fixtures, testing FastAPI with AsyncClient, testing Kafka async producers/consumers, event loop and cleanup patterns. Use when: Testing async functions, async use cases, FastAPI endpoints, async database operations, Kafka async clients, or any async/await code patterns.
Verifies that implemented code is actually integrated into the system and executes at runtime, preventing "done but not integrated" failures. Use when marking features complete, before moving ADRs to completed status, after implementing new modules/nodes/services, or when claiming "feature works". Triggers on "verify implementation", "is this integrated", "check if code is wired", "prove it runs", or before declaring work complete. Works with Python modules, LangGraph nodes, CLI commands, API endpoints, and service classes. Enforces Creation-Connection-Verification (CCV) principle.
Implements OpenTelemetry (OTEL) logging with trace context correlation and structured logging. Use when setting up production logging with OTEL exporters, structlog/loguru integration, trace context propagation, and comprehensive test patterns. Covers Python implementations for FastAPI, Kafka consumers, and background jobs. Includes OTLP, Jaeger, and console exporters.
Sets up async tests with proper fixtures and mocks using pytest-asyncio patterns. Use when testing async functions, creating async fixtures, mocking async services, or handling async context managers. Covers @pytest_asyncio.fixture, AsyncMock with side_effect, async generator fixtures (yield), and testing async context managers. Works with Python async/await patterns, pytest-asyncio, and unittest.mock.AsyncMock.
Detects orphaned code (files/functions that exist but are never imported or called in production), preventing "created but not integrated" failures. Use before marking features complete, before moving ADRs to completed, during code reviews, or as part of quality gates. Triggers on "detect orphaned code", "find dead code", "check for unused modules", "verify integration", or proactively before completion. Works with Python modules, functions, classes, and LangGraph nodes. Catches the ADR-013 failure pattern where code exists and tests pass but is never integrated.