brainstorm
Creative ideation and solution exploration. Generates multiple approaches with trade-offs, uses structured frameworks (SCAMPER, First Principles), and hands off to plan for structuring.
Rune-kit · 已有 AI 审核记录
安装与使用
运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。
npx skills add Rune-kit/rune --skill brainstorm技能说明
name: brainstorm description: "Creative ideation and solution exploration. Generates multiple approaches with trade-offs, uses structured frameworks (SCAMPER, First Principles), and hands off to plan for structuring." metadata: author: runedev version: "0.8.0" layer: L2 model: opus group: creation tools: "Read, Glob, Grep" emit: ideas.ready listen: codebase.scanned
brainstorm
Purpose
Creative ideation and solution exploration. Brainstorm is the creative engine of the Creation group — it generates multiple approaches with trade-offs, explores alternatives using structured frameworks, and hands the selected approach to plan for structuring. Uses opus for deep creative reasoning.
Modes
Discovery Mode (default)
Normal brainstorming at the start of a task — generate approaches before any code is written.
Vision Mode
Activated for product-level rethinks — not "how to implement X" but "should we even build X?" Forces 10x thinking instead of incremental improvement.
Vision Mode triggers:
- Manual:
/rune brainstorm vision <product area> - Called by
@rune-pro/product.feature-specwhen requirements feel incremental - When the user says "rethink", "reimagine", "what if we", "step back"
Vision Mode constraints:
- MUST restate the user's REAL problem (not their proposed solution) — "you asked for a settings page, but your real problem is users can't find the right config"
- MUST generate 2-3 approaches where at least 1 eliminates the need for the feature entirely
- MUST apply the "10-star experience" lens: what would a 1-star, 5-star, and 10-star version look like?
- MUST challenge assumptions: "why does this need to be a page?" "why does the user need to do this at all?"
Design-It-Twice Mode
Activated when exploring alternative interface shapes for a deepening candidate. Spawns N=3-4 parallel subagents, each pinned to a radically different design constraint (minimize / maximize-flexibility / optimize-common-case / ports-and-adapters), computes a diversity score over feature vectors, and presents sequentially with an opinionated recommendation. Used by improve-architecture when a deepened module's interface is non-obvious.
Design-It-Twice triggers:
improve-architecture(Step 7 hand-off) when the picked candidate has multiple credible interface shapes- User says "design it twice", "explore interfaces", "what are the API options"
- Manual:
/rune brainstorm design-it-twice <module>
Design-It-Twice constraints:
- MUST spawn N=3 (minimum) or N=4 (when dependency category is remote-owned or true-external) parallel subagents
- Each subagent pinned to exactly ONE of the 4 standard constraints — enforced via prompt template
- Diversity score MUST be >= 0.4 before presenting (re-spawn once if below)
- Recommendation MUST be opinionated with a concrete hedge condition — "it depends" is BLOCKED
- Hybrid synthesis (Step 4.5) is opt-in when 2 designs have complementary strengths
- council (Step 3.75) is opt-in per the narrow trigger — MUST NOT fire on every design-it-twice run, and its output MUST NOT replace the diversity-score mechanism, only supplement it
Full doctrine: references/design-it-twice.md.
Rescue Mode
Activated when an approach has been tried and fundamentally failed — not a bug, but a wrong approach. Rescue mode forces category-diverse alternatives instead of variants of the failed approach.
Rescue Mode triggers:
cookPhase 4: Approach Pivot Gate fires (3 debug-fix loops exhausted + re-plan still fails)debug: 3-Fix Escalation Rule fires AND root cause is "approach doesn't work" (not a bug in implementation)fix: 3 fix attempts fail AND each attempt reveals a different blocker (systemic, not localized)- Manual:
/rune brainstorm rescue <what failed and why>
Rescue Mode input:
mode: "rescue"
failed_approach: string — what was tried
failure_evidence: string[] — concrete reasons it failed (error messages, blockers, dead ends)
original_goal: string — what we're still trying to achieve
Rescue Mode constraints:
- MUST generate 3-5 approaches (more than Discovery's 2-3 — wider net)
- Each approach MUST be a different category, not a variant of the failed one
- At least 1 approach must be "unconventional" (hacky, wrapper, reverse-engineer, proxy, etc.)
- MUST use Collision-Zone Thinking or Inversion Exercise — conventional thinking already failed
- MUST explicitly state why each approach is a different category from the failed one
- Failed approach MUST be listed as "Option X (FAILED)" — visible reminder not to loop back
Category examples (approaches in different categories):
Direct API call ≠ Wrapper/middleware layer ≠ Reverse engineering ≠ Browser automation
≠ Extension/plugin ≠ Proxy/bridge service ≠ Alternative tool entirely
Triggers
- Called by
cookwhen multiple valid approaches exist for a feature (Discovery Mode) - Called by
cookApproach Pivot Gate when current approach fundamentally fails (Rescue Mode) - Called by
debug3-Fix Escalation when root cause is architectural, not a bug (Rescue Mode) - Called by
planwhen architecture decision needs creative exploration (Discovery Mode) /rune brainstorm <topic>— manual brainstorming (Discovery Mode)/rune brainstorm rescue <context>— manual rescue (Rescue Mode)- Auto-trigger: when task description is vague or open-ended (Discovery Mode)
Calls (outbound)
ba(L2): when no requirements spec exists yet AND brainstorm is a standalone entry point — hand off for requirement elicitation BEFORE pl