By ggprompts
Multi-session orchestration - beads workflows, parallel workers, visual QA via tabz-expert, completion pipelines
npx claudepluginhub ggprompts/tabzbeads --plugin conductorFully autonomous backlog completion. Runs waves until backlog empty with zero user prompts. Use when you want hands-off parallel issue processing.
Interactive multi-session orchestration. Select issues, choose terminal count (1-4), pick mode (interactive/autonomous), then spawn workers. Main entry point for spawning workers.
Multi-phase workflow for brainstorming, scaffolding, and setting up new projects with skill-aware configuration
Prepare beads backlog before work: analyze state, match skills, estimate complexity, enhance prompts. Runs full pipeline automatically.
Grab a ready issue and start working on it directly (no worker spawn)
Show beads issue tracker status overview
Analyze worker session transcripts to find patterns, missed opportunities, and improvement areas
Multi-session Claude workflow orchestration. Spawn workers via TabzChrome, coordinate parallel tasks, use subagents for monitoring/exploration, manage beads issues. Use this skill when coordinating multiple Claude sessions or managing complex multi-step workflows.
Enhance beads issue prompts with skill hints, key files, and structured context. Used by bd-plan's Enhance Prompts activity to prepare issues for workers.
Run a conductor wave from the conductor-wave molecule template
Fully autonomous backlog completion. Runs waves until `bd ready` is empty. Self-resumable after /wipe. Use when you want hands-off parallel issue processing.
Visual QA check between waves - runs as tabz-expert subagent to screenshot changes and check for browser errors.
Complete a wave of parallel workers: verify all workers finished, merge branches, run unified review, cleanup worktrees. Invoke with /conductor:bdc-wave-done <issue-ids>
Close a beads issue with completion reason.
Code review with confidence-based filtering. Modes: quick (lint+types), standard (Sonnet), thorough (parallel agents). Worker applies fixes from review findings.
Run Codex code review (read-only, cheaper). Uses GPT model for analysis.
Stage and commit changes with conventional commit format.
Analyze work and create follow-up beads issues if needed.
Run tests if available. Standalone command for test verification.
Verify beads metadata and update core documentation (README.md, CHANGELOG.md, CLAUDE.md). Creates missing docs, enforces line limits.
Run build and report errors. Standalone command for build verification.
Complete worker task: verify build, run tests, commit, and close issue. Code review happens at conductor level after merge. Invoke with /conductor:bdw-worker-done <issue-id>
Self-optimize worker context by analyzing issue, identifying skills, and restarting with enhanced prompt
Read-only code review with confidence-based filtering. Reviews changes against CLAUDE.md, flags issues for the caller to fix. Quality over quantity.
Orchestrate multi-session Claude workflows. Use for: spawning Claude agents in TabzChrome sidebar, killing terminals, sending prompts to other sessions via tmux, coordinating parallel work, browser automation via tabz MCP tools.
DEPRECATED - Use /conductor:bdw-update-docs command instead. Kept for backwards compatibility.
Specialized reviewer for error handling. Finds empty catch blocks, swallowed errors, silent fallbacks, missing logging. Use for thorough reviews or standalone audit.
Search and install skills from skillsmp.com (28k+ skills). Invoked via Task tool. Use when spawning workers that need specific capabilities, or when user asks to find/install skills.
A collection of plugins for development workflows, browser automation, and multi-session orchestration.
bd- (user commands), bdc- (conductor skills), bdw- (worker skills)bd CLIcommands/, internal skills in skills/# User entry points (commands)
/conductor:bd-start [issue-id] # Single-session: you do the work (no spawn)
/conductor:bd-plan # Prepare backlog
/conductor:bd-conduct # Interactive orchestration (1-4 workers)
/conductor:bd-auto # Fully autonomous (all ready, no prompts)
/conductor:bd-status # View issue state
/conductor:bd-new-project # Project scaffolding
./install.sh
Complete collection of battle-tested Claude Code configs from an Anthropic hackathon winner - agents, skills, hooks, rules, and legacy command shims evolved over 10+ months of intensive daily use
Uses power tools
Uses Bash, Write, or Edit tools
Team-oriented workflow plugin with role agents, 27 specialist agents, ECC-inspired commands, layered rules, and hooks skeleton.
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Comprehensive .NET development skills for modern C#, ASP.NET, MAUI, Blazor, Aspire, EF Core, Native AOT, testing, security, performance optimization, CI/CD, and cloud-native applications
Manus-style persistent markdown files for planning, progress tracking, and knowledge storage. Works with Claude Code, Kiro, Clawd CLI, Gemini CLI, Cursor, Continue, Hermes, and 17+ AI coding assistants. Now with Arabic, German, Spanish, and Chinese (Simplified & Traditional) support.