idea-wizard
Made by JeffGenerate and operationalize improvement ideas for projects. Use when brainstorming features, planning improvements, creating beads from ideas, or "what should we build next".
From Jeffrey's Skills.md: professionally crafted skills for any AI agent, installed and kept in sync by the jsm CLI. Subscription only, $20/month.
Works With
Quality and Utility come from canonical skill metadata. Community ratings appear separately as stars when subscriber reviews exist.
Subscribe to download
Public previews are available, but downloads, CLI sync, and premium content require an active subscription.
Sign In to Subscribe- Full skill content with deterministic versioning
- CLI sync + local search index
- Access to Jeffrey’s premium library
Save to your account
Saved skills live in your cloud list. Run jsm sync on each machine to pull them locally.
What's New with this Skill
1Updates, enhancements, and release notes for this skill.
New: Idea Wizard, generate 30, winnow to 5, expand the next 10, then turn the survivors into beads
A structured answer to "what should we build next?" Six phases: ground in reality (read AGENTS.md and all beads, open and closed), generate 30 ideas and winnow to 5 with full rationale, expand with the next 10 to make a 15-idea pool, check overlaps with existing beads, create beads, then refine them in plan space for four to five more rounds. The output is a set of self-documenting beads with dependencies, not a brainstorm dump.
- Ground first: read AGENTS.md and all existing beads (open and closed) before generating anything, so the new ideas don't duplicate existing work
- Phase 2 generation prompt asks for 30 ideas, winnows to 5, and demands full rationale per surviving idea, ranked from best to worst
- Phase 3 expansion ("ok and your next best 10 and why") fills out a 15-idea pool. Ideas #6-15 are often complementary to the top 5
- Overlap check before bead creation: direct duplicates are skipped in favor of the existing bead; complementary ideas are merged into it
- Phase 6 refinement runs four to five rounds in plan space (no implementation): re-read AGENTS.md, check every bead, add tests with detailed logging, and never oversimplify or drop features
- Validation: bv --robot-insights | jq '.Cycles' must come back empty after dependencies are added