Agent skill · product strategy · aiskillstore
beads-workflow
Converting markdown plans into beads (tasks with dependencies) and polishing them until they're implementation-ready. The bridge between planning and agent swarm execution. Includes exact prompts used.
Why this skill is useful
Provides a structured methodology for converting markdown plans into detailed, self-contained tasks with dependencies that enhance AI's task management capabilities.
What it needs
About 10k tokens when loaded. Last updated 2026-08-07. 405 stars on the source repository.
What this skill does
Beads Workflow — From Plan to Actionable Tasks Core Principle: "Check your beads N times, implement once" — where N is as many as you can stomach. Beads are so detailed and polished that you can mechanically unleash a big swarm of agents to implement them, and it will come out just about perfectly. --- What Are Beads? Beads are epics/tasks/subtasks with dependency structure, optimized for AI coding agents. Think of them as Jira or Linear, but designed for machines. Key properties: Self-contained — Never need to refer back to the original markdown plan Self-documenting — Include background, reasoning, justifications, considerations Dependency-aware — Explicit structure of what blocks what Rich descriptions — Long markdown comments, not short bullet points --- Why Beads Work --- Converting Plans to Beads THE EXACT PROMPT — Plan to Beads Conversion (Claude Code + Opus 4.5) Note: Replace PLANTOCREATEGHPAGESWEBEXPORTAPP.md with your actual plan filename. Alternative Shorter Version What This Creates Tasks and subtasks with clear scope Dependency links (what must complete before what) Detailed descriptions with: Background context Reasoning and justification Technical considerations How it serves project goals --- Polishing Beads Why Polish? Even after initial conversion, beads continue to improve with review. You get incremental improvements even at round 6+. THE EXACT PROMPT — Polish Beads (Full Version) THE EXACT PROMPT — Polish Beads (Standard Version) Polishing Protocol 1. Run the polishing prompt 2. Review changes 3. Repeat until steady-state (typically 6-9 rounds) 4. If it flatlines, start a fresh CC session 5. Optionally have Codex with GPT 5.2 do a final round --- Fresh Session Technique If polishing starts to flatline, start a brand new Claude Code session: THE EXACT PROMPT — Re-establish Context THE EXACT PROMPT — Then Review Beads Then follow up with the standard polish prompt. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills aiskillstore/beads-workflow