菜单
30 → 5 → 15 funnel for brainstorming new features on the existing Forge codebase. Use when adding capability to a mature install, not for greenfield.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Deep review — random exploration + cross-agent review, alternating. Finds integration bugs that self-review misses. Run every 30–60 min during active implementation.
Overview of Forge's Agentic Coding Flywheel methodology. Use to route between plan, bead, and code space. See FLYWHEEL.md at the repo root.
End-of-session ritual. Close finished beads, file new ones for remaining work, run verify, commit in logical groupings, push. Work is not complete until git push succeeds.
Start a new Flywheel planning round. Produce initial markdown plan, route to competing frontier models, synthesize hybrid, refine 4–5×. Use before any coding begins on a new feature.
Translate a polished markdown plan into self-contained beads in .beads/beads.jsonl. Every bead must be executable without reopening the plan. Use after the plan has converged.
Polishing pass over all open beads. Run 4–6 times. "Check your beads N times, implement once." Use after plan-to-beads and between refinement rounds.
| name | idea-wizard |
| description | 30 → 5 → 15 funnel for brainstorming new features on the existing Forge codebase. Use when adding capability to a mature install, not for greenfield. |
Winnowing forces critical evaluation. Asking for "5 ideas" directly produces weak lists; asking for 30 then winnowing produces strong ones.
jq -c 'select(.status!="closed")' .beads/beads.jsonl..flywheel/prompts/idea-wizard.md..beads/beads.jsonl with full descriptions./polish-beads./plan from the start.FLYWHEEL.md §5); save the
proposal to .flywheel/proposals/.For every idea that survives winnowing, verify: