Multi-Agent Verified Implementation System — autonomous development harness with three execution modes (Full/Quick/Bug)
System architect — designs architecture, API contracts, and component boundaries
Task distributor for Agent Teams - creates tasks with dependency ordering and monitors execution
Backend developer — implements API handlers, services, data layer, and migrations
Ruthless plan reviewer - validates plans against clarity, verification, context, and dependency thresholds
Scientific debugger — reproduces, isolates, and fixes bugs with systematic rigor
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub haodiaodemingzi/mavis --plugin mavisFeature development with code-architect/explorer/reviewer agents, CLAUDE.md audit and session learnings, and Agent Skills creation with eval benchmarking from Anthropic.
Production-grade engineering skills for AI coding agents — covering the full software development lifecycle from spec to ship.
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Complete developer toolkit for Claude Code
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
Continuous self-referential AI loops for interactive iterative development, implementing the Ralph Wiggum technique. Run Claude in a while-true loop with the same prompt until task completion.