danielgamy981/claude-code-main
Build and run Claude Code from source with Bun, a TypeScript and React Ink terminal AI coding assistant for Anthropic API and MCP support
Build and run Claude Code from source with Bun, a TypeScript and React Ink terminal AI coding assistant for Anthropic API and MCP support
npx add-skill danielgamy981/claude-code-mainBuild and run Claude Code from source with Bun, a TypeScript and React Ink terminal AI coding assistant for Anthropic API and MCP support
An MCP server for designing Renovate configurations interactively
基于微信读书官方 Agent Skill 的二创项目精选 · Curated projects built on WeRead's official Agent Skill (released 2026-05-17)
🧪 Provide expert Swift Testing guidance with best practices for XCTest, async tests, parallel execution, and seamless Agent Skills integration.
Exercise: Build applications with GitHub Copilot agent mode
Disciplined method for investigating a specific bug, regression, or anomalous behavior. Use when the user reports a concrete symptom ("X is broken", "this worked last week", "Y returns the wrong value", "intermittent failure in Z") and wants the root cause found — not a quick patch. Enforces reproduce-first, read-only diagnosis, differential disconfirmation, and git forensics. Do NOT use for open-ended "find any bugs" sweeps, code review, or feature work.
AI Session Memory with Think-Execute-Reflect Quality Loops — give your agent a brain that survives every session. Built on the Intelligent Distance principle.