Workbench for structured software development with TDD, project planning, and beads integration.
npx claudepluginhub gvarela/workbenchCreate architectural design decisions based on validated research
Transform design into detailed phased execution plan with embedded tasks
Creates a comprehensive handoff document to transfer your work context to another agent or resume in a new session. Captures critical context, learnings, and next steps that aren't in the formal documentation.
Researches existing UI patterns, styles, and layouts, then creates an initial mockup iteration through interactive discussion. Follows the "research what EXISTS" philosophy before proposing changes.
Creates a comprehensive documentation structure for a new project or feature, setting up folders and files for research, planning, and task tracking with proper metadata.
Conducts comprehensive codebase research and documents findings by spawning specialized agents to work in parallel, gathering detailed information about existing implementation.
Quick reference for wb workflow commands and beads integration
**Next-generation task implementation using coordinator + worker agent pattern.**
You are tasked with implementing tasks from a structured task list in `tasks.md`, following Test-Driven Development (TDD) practices and the phased implementation approach defined in the project documentation.
Resume work from a handoff document created in a previous session
Update status across all project documentation files based on progress
Validate that execution plan was correctly implemented and verify all success criteria
Validate project documentation follows wb workflow correctly
Analyzes codebase implementation details. Finds how specific components work, traces data flow, and documents technical details with precise file:line references.
Finds specific components and files in the codebase. Specializes in locating where features are implemented, which files contain certain functionality, and mapping the codebase structure.
Finds similar patterns and implementations in the codebase. Identifies conventions, recurring patterns, and examples that can guide new implementations.
Verifies task completion by running tests, checking scope adherence, and validating implementation against requirements. Returns structured pass/fail report.
Iterate on UI mockups, capturing keeps/removes/changes with full fidelity. Versions each iteration and maintains decision log.
Enforces project documentation structure in docs/plans/ directories - research.md for facts, design.md for decisions, tasks.md for implementation, thoughts/ for explorations.
Interactive code review walkthrough using tmux and nvim for pair programming style review. Use when user says "review", "walk through changes", "explain this diff", "prep for PR", or wants to understand what changed.
Monitors beads status and reminds about bd sync at session end or when phases complete.
Use when implementing features, fixing bugs, or writing any production code - enforces RED-GREEN-REFACTOR cycle where tests must fail before writing implementation code. Activates before coding begins.
Use when about to claim work is complete, fixed, passing, or done - requires running verification commands and confirming output before making any success claims. Evidence before assertions.
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Modifies files
Hook triggers on file write and edit operations
Uses power tools
Uses Bash, Write, or Edit tools
Manus-style persistent markdown files for planning, progress tracking, and knowledge storage. Works with Claude Code, Kiro, Clawd CLI, Gemini CLI, Cursor, Continue, and 16+ AI coding assistants. Now with Arabic, German, Spanish, and Chinese (Simplified & Traditional) support.
Comprehensive C4 architecture documentation workflow with bottom-up code analysis, component synthesis, container mapping, and context diagram generation
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.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Orchestrate multi-agent teams for parallel code review, hypothesis-driven debugging, and coordinated feature development using Claude Code's Agent Teams