菜单
轻量需求头脑风暴 — 先扫代码库确认前置条件，再用 2-3 轮聚焦讨论锁定范围和方案。Use when user says "brainstorm this feature", "需求讨论", "sdd brainstorm", or wants to explore a feature idea before writing specs. Replaces heavyweight brainstorming workflows that burn tokens.
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
Extremely strict maintainability review focused on structural simplification, abstraction quality, and spaghetti-condition growth. Not a general correctness review -- this is a deep code quality audit that pushes for "code judo" moves that delete complexity. Use when asked to "code review", "maintainability review", "code quality audit", "/code-review", or "/review-quality".
Spawns a verifier subagent to audit your work: traces what was done, reviews the diff, runs builds/tests, and delivers a PASS/FAIL verdict. Auto-retries fixes up to 3 rounds. Use when asked to "check work", "verify changes", "self-verify", "/self-verify", "/check", or "/verify".
按规格文档的 Ticket 逐个实现代码，每个 Ticket 独立上下文避免幻觉。内置 todo 进度追踪，支持 LSP 诊断、worktree 隔离、子智能体委派等按需升级。Use when user says "implement ticket", "实现这个任务", "sdd implement", "开始实现", or wants to execute tasks from a spec. Reads .plan/spec.md for task breakdown.
将头脑风暴结论转化为结构化规格文档，包含需求、技术设计、任务拆解和决策记录。Use when user says "write spec", "写规格", "sdd spec", or wants to formalize a brainstormed idea into an implementable specification. Reads .plan/brainstorm.md if available.
Comprehensive quality analysis tool for Claude Skills. Evaluates skills from GitHub URLs, marketplace links, ZIP files, or local directories across five dimensions (structure, security, UX, code quality, integration) using balanced scoring and three output modes (comprehensive report, interactive review, pass/fail certification). Triggers on "analyze skill quality", "review this skill", "evaluate skill", or "skill quality check".
Comprehensive security analysis for Claude Code skills with P0-P3 enhancements. Detects malicious code, obfuscation, YAML injection, typosquatting, time bombs, sandbox escapes, and 40+ attack patterns. Use for analyzing skills before installation or auditing existing skills.
| name | sdd-brainstorm |
| description | 轻量需求头脑风暴 — 先扫代码库确认前置条件，再用 2-3 轮聚焦讨论锁定范围和方案。Use when user says "brainstorm this feature", "需求讨论", "sdd brainstorm", or wants to explore a feature idea before writing specs. Replaces heavyweight brainstorming workflows that burn tokens. |
| argument-hint | Describe the feature or requirement you want to brainstorm |
| disable-model-invocation | true |
用最少轮次帮用户理清需求、锁定方案，为写规格文档做准备。
开始讨论前，用 grep/read 快速扫描代码库：
整理成「前置条件摘要」展示给用户，确认准确性。
如果
.plan/brainstorm.md已存在（上次讨论的残留），先读取并告知用户，避免重复工作。
聚焦 What：
每轮给出理解和建议，请用户确认。不连珠炮提问。
聚焦 How：
用户已有方案时直接确认，不强行推销替代方案。
输出结构化摘要：
## 需求摘要
- **目标**：一句话
- **用户场景**：核心场景列表
- **非目标**：明确不做的事
## 选定方案
- **方案**：一句话
- **关键决策**：已确认的技术决策
- **开放问题**：仍需确认的点（如有）
## 前置条件
- **涉及文件**：需修改的文件列表
- **依赖模块**：相关模块
- **约束**：已知技术约束
提示用户：
结论如上。接下来可以用
/sdd-spec生成规格文档，或用/grill-me压力测试方案。
| 信号 | 升级动作 | 何时值得 |
|---|---|---|
| 涉及 3+ 模块，方案不确定 | 进入 plan mode 做结构化探索 | 跨模块重构、架构选型 |
| 需要了解符号依赖关系 | 调 LSP workspaceSymbol / findReferences | 接口变更、影响面分析 |
| 方案需要领域建模 | 派发「软件架构师」子智能体 | 新领域、复杂业务规则 |
判断标准：如果 grep + 对话能在 3 轮内锁定方案，就不升级。升级是为了节省后续返工成本，不是为了流程完整。
写入 .plan/brainstorm.md。