Skills matching the name, description or GitHub author.
Expert guidance for using the Azure AI Projects client library (azure-ai-projects) to build and deploy AI applications with Microsoft Foundry. This skill covers agent creation, tools integration, evaluation, co...
Expert guidance for building AI agents using Microsoft Agent Framework. Use when creating single agents, multi-agent workflows, chat applications, or integrating tools with LLMs. Covers ChatAgent, tools (@ai_fu...
Production-grade WebSocket patterns for Python (FastAPI/Starlette) with connection management, rooms, and message protocols
Implement comprehensive testing strategies with pytest, fixtures, mocking, and test-driven development. Use when writing Python tests, setting up test suites, or implementing testing best practices.
Analyze animated GIF files by extracting and viewing frames as sequential video. Use when: - User mentions a GIF file path (e.g., "./demo.gif", "~/Downloads/animation.gif") - User wants to analyze or understan...
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or...
Dev Container を最短で導入/更新するためのブートストラップ。stack を自動判定（node/python/rust）し、テンプレート適用または安全更新を行う。既存 .devcontainer がある場合はバックアップ後にマージ。Chat オプション: s...
测试 AST 能检测 subprocess 危险用法
测试 AST 能检测真实的 eval() 调用
测试 AST 能区分注释和代码中的危险模式
Use when profiling and making small performance improvements in Python research code.
Use when doing a quick preflight to assess scope, risks, and priorities for Python research code refactoring.
Use when checking for data leaks, PII handling, and license risks in Python research code.
Use when standardizing Python research code dependencies, environment setup, and lockfiles.
Use when running or explaining uv or ty commands, managing dependencies/lockfiles/virtualenvs, or running Python in this repo.
Use when adding formatting, linting, and type checking to Python research code.
Use when improving data loading, validation, and IO boundaries in Python research code.
Bootstrap a new Python project using the OCREvaluation default layout and toolchain (uv, ruff, ty, pre-commit). Use when asked to scaffold a new Python repo, initialize standard folders, or set up uv/ruff/ty/pr...
Use when improving run configuration, seeding, and reproducibility for Python research code.
Use when documenting Python research code usage, setup, and experiment reproduction.
Use when organizing experiment logs, results, and metadata for Python research code.
Use when refactoring Python research code to improve project structure, modularity, and entrypoints.
Use when adding tests and regression checks for Python research code.
Use when adding minimal CI automation for lint, tests, and type checks in Python research code.
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.