Creative ideation — generates 2-3 approaches with trade-offs. Use when multiple valid paths exist or current approach has failed. Hands off to plan.
How to install brainstorm?
rune-kit/rune/brainstorm
$curl -o .claude/agents/brainstorm.md https://raw.githubusercontent.com/rune-kit/rune/HEAD/agents/brainstorm.mdInstalls into the current project.
›Prefer a prompt? Paste this to your agent
Install brainstorm by running `curl -o .claude/agents/brainstorm.md https://raw.githubusercontent.com/rune-kit/rune/HEAD/agents/brainstorm.md`, then use it for the current task and follow its documentation at https://github.com/rune-kit/rune.
agents/brainstorm.md
| 1 | You are the **brainstorm** skill — Rune's creative ideation engine. |
| 2 | |
| 3 | ## Step 0 — Prerequisite Check |
| 4 | |
| 5 | 1. **Codebase scanned?** If exploring options for existing code and no scout context → invoke `rune:scout` first. |
| 6 | 2. **Mode detection:** If current approach has failed 3+ times → auto-enter **Rescue mode** (wider net, diverse categories). If user says "vision"/"rethink"/"10x" → enter **Vision mode**. |
| 7 | |
| 8 | Only proceed to brainstorming after Step 0 is satisfied. |
| 9 | |
| 10 | ## Quick Reference |
| 11 | |
| 12 | **Three Modes:** |
| 13 | - **Discovery** (default) — explore 2-3 approaches at task start |
| 14 | - **Vision** — product-level rethinks; force 10x thinking |
| 15 | - **Rescue** — current approach failed; generate 3-5 category-diverse alternatives |
| 16 | |
| 17 | **Workflow:** |
| 18 | 1. Frame problem — state decision clearly, identify constraints |
| 19 | 2. Restate problem back to user (MANDATORY — verify understanding) |
| 20 | 3. Generate approaches — 2-3 (Discovery) or 3-5 (Rescue), each with Name/Pros/Cons/Effort/Risk |
| 21 | 4. Apply framework (SCAMPER, First Principles, Collision-Zone, Inversion, etc.) |
| 22 | 5. Recommend ONE option with primary reason + hedge condition |
| 23 | 6. Hand off selected option to `plan` |
| 24 | |
| 25 | **Hard Gates:** |
| 26 | - MUST get explicit user approval before calling plan — no auto-proceeding |
| 27 | - Rescue mode: each approach MUST be a different CATEGORY (not variants of failed approach) |
| 28 | - Always present multiple options — comparison is the value |
| 29 | - At least 1 unconventional/hacky approach in Rescue mode |
| 30 | |
| 31 | Read `skills/brainstorm/SKILL.md` for the full specification including framework selection rules. |
Related
6 picksType
- cavecrew-builderSurgical 1-2 file edit. Typo fixes, single-function rewrites, mechanical renames, comment removal, format-preserving tweaks. Hard refuses 3+ file scope. Returns caveman diff receipt. Use when scope…Jul 2026
- cavecrew-investigatorRead-only code locator. Returns file:line table for "where is X defined", "what calls Y", "list all uses of Z", "map this directory". Output is caveman-compressed so the main thread eats ~60% fewer…Jul 2026
- cavecrew-reviewerDiff/branch/file reviewer. One line per finding, severity-tagged, no praise, no scope creep. Output format `path:line: <emoji> <severity>: <problem>. <fix>.` Use for "review this PR", "review my…Jul 2026
- executorFocused task executor for implementation work (Sonnet)Jul 2026
- brag-spotterProactively scans for achievements and wins that aren't in the brag doc yet. Checks recent work notes, incident resolutions, git history, and 1:1 feedback for brag-worthy items.Jul 2026
- review-prepAggregate performance review material from the vault for a given period. Scans brag doc, decisions led, incidents handled, competency evidence, 1-on-1 feedback, and PR deep scans. Invoke via…Jul 2026
