dragon375014/claude-skills-governance-meta
Defensive and offensive governance patterns harvested from a working codebase. 7 concept docs + 3 runnable templates + 3 governance skills. ZH-TW guide included. Part of the specmit toolchain. MIT.
Defensive and offensive governance patterns harvested from a working codebase. 7 concept docs + 3 runnable templates + 3 governance skills. ZH-TW guide included. Part of the specmit toolchain. MIT.
npx skills add dragon375014/claude-skills-governance-metaDefensive and offensive governance patterns harvested from a working codebase. 7 concept docs + 3 runnable templates + 3 governance skills. ZH-TW guide included. Part of the specmit toolchain. MIT.
Shared sandbox SDK: ManagerClient, skills loader, monitor (heartbeat + watchdog + artifact finalize). Consumed by am-pi-agent and am-opencode-agent as a submodule.
Plan. Work. Review. Learn. — A minimal disciplined agentic development framework.
A Claude Code skill that actually designs beautiful UI. Extract your design taste → build unlimited production-quality UI from it. No subscriptions. No sloppy output.
SwiftUI agent skill for Claude Code, Codex, and other AI tools.
🤖 Automate your Gmail inbox with AI-powered email organization, smart categorization, and language-aware draft responses using Claude Sonnet 4.5
Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, evaluation rubrics, and test suites. Use when designing prompts for new LLM applications, refactoring existing prompts for better accuracy or token efficiency, implementing chain-of-thought or few-shot learning, creating system prompts with personas and guardrails, building JSON/function-calling schemas, or developing prompt evaluation frameworks to measure and improve model performance.