antbald/BALDART
Claude Agent Framework - Reusable framework for coordinating AI agents and humans in software projects
Claude Agent Framework - Reusable framework for coordinating AI agents and humans in software projects
npx add-skill antbald/BALDARTClaude Agent Framework - Reusable framework for coordinating AI agents and humans in software projects
A collection of Claude Code skills for evaluating LLM applications end-to-end: prompts, RAG pipelines, tool calls, and agents. Built for prompt engineers, AI builders, and teams who want a repeatable loop of "edit → eval → see scores → improve" instead of vibes-based iteration.
Build AI agent teams in your terminal with one command using Neurogent, a TypeScript CLI for fast local agent workflows
A developer's guide to the missing manual of Agentic AI. Demystifying the confusion between RAG vs. Agents, Tools vs. Skills, and Chains vs. Orchestration with clear mental models and code examples.
Organize Claude Code docs in Korean and English for fast access to guides, analysis, and best practices
Three slash commands (/kickoff, /autonomy, /ship) that turn Claude Code into a fully autonomous developer. Claude works continuously through a backlog, makes all decisions itself, and only stops when it genuinely needs human input.
Microsoft Agent 365 quickstart local Python agent registered with M365 Copilot via persistent DevTunnel — no Azure deploy. Ships Draft Dodger (an email tone advisor), end-to-end A365 observability wiring (Purview Audit log + Aspire OTel mirror), an interactive /draft-dodger-setup skill for Claude Code