context-engineering-kit

Evaluate and improve Claude Code commands, skills, and agents. Use when testing prompt effectiveness, validating context engineering choices, or measuring improvement quality.

Execute tasks through competitive multi-agent generation, meta-judge evaluation specification, multi-judge evaluation, and evidence-based synthesis

Guide for setup arXiv paper search MCP server using Docker MCP

Reconcile the project's FPF state with recent repository changes

Reset the FPF reasoning cycle to start fresh

Auto-selects best Kaizen method (Gemba Walk, Value Stream, or Muda) for target

Guide for setup Serena MCP server for semantic code retrieval and editing capabilities

creates draft task file in .specs/tasks/draft/ with original user intent

Search the FPF knowledge base and display hypothesis details with assurance information

Manage evidence freshness by identifying stale decisions and providing governance actions

Guide for creating effective skills. This command should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations. Use when creating new skills, editing existing skills, or verifying skills work before deployment - applies TDD to process documentation by testing with subagents before writing, iterating until bulletproof against rationalization

Interactive assistant for creating new Claude commands with proper structure, patterns, and MCP tool integration

Use when executing implementation plans with independent tasks in the current session or facing 3+ independent issues that can be investigated without shared state or dependencies - dispatches fresh subagent for each task with code review between tasks, enabling fast iteration with quality gates