Menu
Work board driven development. Post typed work items with dependencies, agents poll by role. Use for multi-step features where ordering matters.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Declarative multi-stage workflows. Define staged pipelines where each stage feeds its result to the next. Use for structured multi-agent tasks.
GitHub integration via gh CLI. List issues, create PRs, comment on issues. Use for agents that bridge GitHub and the Workshop board.
Autonomous board worker. Receives work items, implements them, reports results. Designed for agents that poll the board and execute tasks independently.
Multiple LLM backends in one workshop. Claude and Codex agents working together. Use when different models have different strengths.
Scheduled agent for periodic checks. Use for CI monitoring, PR scanning, health checks, or any polling-based workflow.
Coordinate a team of AI agents to build software. Break tasks down, create specialist agents from profiles, delegate via ask/cast, review results, and clean up. Use when you need to orchestrate multi-agent workflows.
| name | board |
| description | Work board driven development. Post typed work items with dependencies, agents poll by role. Use for multi-step features where ordering matters. |
| license | MIT |
| metadata | {"author":"joshrotenberg","version":"1.0"} |
Structured task tracker. Work items have types, dependencies, and lifecycle states. Agents claim work matching their role.
agent(:coder, "Check the board for :code items. Claim one, implement it, mark done.",
work_types: [:code])
agent(:reviewer, "Check the board for :review items. Claim one, review it.",
work_types: [:review])
# Post work
work(:cache, "Implement LRU cache", type: :code, priority: 1,
spec: "LRU with TTL, max 1000 entries")
work(:cache_review, "Review cache", type: :review, depends_on: [:cache])
work(:cache_tests, "Test cache", type: :test, depends_on: [:cache])
# Check board
board()
board(status: :ready)
# Agents claim and advance
claim_work(:cache, :coder)
start_work(:cache)
complete_work(:cache, "Done with GenServer-backed LRU")
# :cache_review and :cache_tests auto-unblock to :ready
Pipe: you control the flow manually. A then B then C. Board: agents self-organize. Dependencies handle ordering. New work can be added anytime.