← ClaudeAtlas

brainstormlisted

Multi-persona divergent→convergent brainstorm (platform skill). Agent loads this skill and runs the co-located runner (diverge → challenge → converge); humans only state intent (头脑风暴 / 帮我发散一下 / brainstorm / 想点子). Sibling of adversarial-review; reuses its provider layer. Use when the user wants ideas / options / approaches for an open-ended problem — NOT for reviewing existing code (that is adversarial-review).
yunsii/wezdeck · ★ 5 · AI & Automation · score 77
Install: claude install-skill yunsii/wezdeck
# Brainstorm (platform skill — single source) **Who runs:** the coding agent, **not** the human. **Never** tell the user to copy-paste `run.sh` as the primary path. **Never** replace this with a solo idea dump and call it a brainstorm — the point is *multiple independent personas + cross-model*, then a judge. This directory is the **only** skill + runner unit. Other paths are symlinks (installed by `scripts/dev/link-platform-skills.sh`). Do not maintain a second SKILL.md body. ## Who runs what | Actor | Duty | | --- | --- | | **Human** | Intent only:「头脑风暴」「帮我想想点子」「发散一下这个问题」 | | **Any agent** | Load this skill → phrase the problem → run → relay result | | **Host headless backends** | `claude` / `codex` / `grok` as personas / challenger / judge | ## When to load / run - User wants ideas, options, approaches, or angles on an open-ended question - User explicitly says 头脑风暴 / brainstorm / 发散 / 想点子 **Skip / redirect:** - Concrete diff / existing **code** → **adversarial-review** (this skill is generative, not a defect finder) - Someone's **design doc / RFC / ADR / 方案** when the intent is only to **evaluate that proposal** → default **设计评审** (main-agent structured challenge; host `validation.md` → Design proposal review). Do **not** default to a full diverge pass that ignores the proposal - Same design doc when the user still wants **alternatives** → this skill is appropriate: phrase problem + extract hard constraints from the doc; prefer challenge-heavy use; ful