Process and generate multimedia content using Google Gemini API. Capabilities include analyze audio files (transcription with timestamps, summarization, speech understanding, music/sound analysis up to 9.5 hours), understand images (captioning, object detection, OCR, visual Q&A, segmentation), process videos (scene detection, Q&A, temporal analysis, YouTube URLs, up to 6 hours), extract from documents (PDF tables, forms, charts, diagrams, multi-page), generate images (text-to-image, editing, composition, refinement). Use when working with audio/video files, analyzing images or screenshots, processing PDF documents, extracting structured data from media, creating images from text prompts, or implementing multimodal AI features. Supports multiple models (Gemini 2.5/2.0) with context windows up to 2M tokens.
Migrate all asyncio.gather() calls to asyncio.TaskGroup for structured concurrency. Use this skill to fix P1-2: replace gather with TaskGroup context managers, add Semaphore-based backpressure for concurrent operations, and use except* for ExceptionGroup handling. Targets Python 3.11+ structured concurrency patterns.
Fix known bugs in the WeChat Article Summarizer project. Use this skill when investigating and fixing code bugs including: deprecated API usage, missing imports, type errors, null safety issues, and container initialization problems. Targets BUG-001 through BUG-006 from the project's TEST_ISSUES.txt.
Set up a complete CI/CD pipeline using GitHub Actions. Use this skill to fix P2-8: create workflows for linting (ruff), type checking (mypy), testing (pytest with timeout), security scanning (pip-audit), and build verification. Includes dependency caching and matrix testing for Python 3.12-3.14.
Improve code quality in the WeChat Article Summarizer project. Use this skill for automated code style fixes (ruff), test infrastructure improvements, and pytest-timeout setup. Targets WARN-001 (4711 ruff issues) and WARN-004 (test suite structural defects) from TEST_ISSUES.txt.
Refactor the DI container from eager to lazy initialization to unblock 186 tests. Use this skill to fix P0-1: convert container.py to use cached_property/lazy providers, create a test container with mock adapters in conftest.py, and eliminate module-level container instantiation across the codebase.
Detect and fix hexagonal architecture boundary violations in the domain layer. Use this skill to fix P1-1: find all imports in domain/ that reference infrastructure/, presentation/, or mcp/ packages, replace them with Protocol-based port interfaces, and set up an automated boundary check script.
Decompose the 113KB GUI app.py God Object into modular components. Use this skill to fix P0-2: split app.py into CTkFrame subclasses (sidebar, article list, summarization, export, settings), CTkToplevel dialogs, MVVM ViewModels, reusable widgets, and a pub/sub event bus. Each extracted file should be <400 lines.