sho7650

Autonomous improvement loop — repeatedly runs QA, Fix, and Refactor cycles to continuously improve code quality. Each round runs tests and auto-reverts refactoring commits that break tests. Leverages SuperClaude commands for enhanced analysis. Uses MCP servers (serena, sequential-thinking, context7, playwright, tavily) for semantic analysis, documentation lookup, and multi-step reasoning.

Create or update Architecture Decision Records

Structured code review with severity-based findings

Safe refactoring with pre/post validation

Docker-based release workflow with release-please integration

Detect user-facing feature drift and update README.md + README.ja.md and the Chrome Web Store descriptions in lockstep. Use when features have shipped but the docs are stale, or before a release. Docs-only — never touches src/.

Development patterns for the obsidian-ai-exporter Chrome Extension (CRXJS + Vite + TypeScript)

Autonomous improvement loop for code quality. Repeatedly runs QA, Fix, and Refactor cycles with test-guarded auto-revert. Use when user says "improve", "run QA loop", "fix and refactor", "code quality scan", or "autonomous improvement". Leverages SuperClaude commands for enhanced analysis. Uses MCP servers (serena, sequential-thinking, context7, tavily, playwright) for semantic analysis, documentation lookup, and multi-step reasoning.

Autonomous improvement loop — repeatedly runs QA, Fix, and Refactor cycles to continuously improve code quality. Each round runs tests and auto-reverts refactoring commits that break tests. Leverages SuperClaude commands and MCP servers (serena, sequential-thinking, context7, playwright, tavily). Uses agent teams for parallel QA when CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS is enabled.

Autonomous improvement loop — repeatedly runs QA, Fix, and Refactor cycles to continuously improve code quality. Each round runs tests and auto-reverts refactoring commits that break tests. Leverages SuperClaude commands for enhanced analysis. Uses MCP servers (serena,sequential-thinking,context7,playwright,tavily) for semantic analysis, documentation lookup, and multi-step reasoning.