This is a monorepo of six AI agent skills (SKILL.md format) for creative content generation, targeting Claude Code, Cursor, Codex CLI, and other compatible agents. Each skill is a self-contained package with agent instructions, reference libraries, scaffold scripts, and optional companion websites. The skills enable agents to: generate beautiful single-file HTML articles (beautiful-article), create and edit images via GPT-4o (gpt-image-2), retrieve knowledge from local files (kb-retriever), produce deterministic motion-graphics videos with audio (motion-showreel), design polished web pages with anti-AI-cliché rules (web-design-engineer), and build click-driven video presentations with TTS (web-video-presentation). The repository also includes release automation (zero-dependency Node scripts, GitHub Actions), a Claude Code plugin marketplace entry, and two showcase websites (Vite+React+TypeScript). While primarily an application toolkit, it contains structured prompt template libraries and design reference catalogs that resemble curated data assets. The codebase demonstrates high engineering craftsmanship with deterministic rendering pipelines, a session-based audio synthesizer, design token systems, and comprehensive test coverage for the motion-showreel pipeline.
Promptimize is a prompt engineering evaluation and testing toolkit implemented as a Python library with CLI interface. It enables users to define prompt cases (test cases for LLM prompts) as code, associate evaluation functions that score responses on a 0-1 scale, execute test suites across different models and configurations, and generate performance reports. The architecture centers around BasePromptCase and its derivatives (PromptCase, TemplatedPromptCase, LangchainPromptCase) which encapsulate prompt logic and evaluation, Suite classes that manage collections of prompt cases and handle execution/reporting, and utility modules for templating, caching, and result serialization. The toolkit minimizes redundant API calls by caching prompt executions and only re-running when prompts change, supports human review for edge cases, and integrates with Langchain/OpenAI for LLM interactions.