测试2123

在任何创造性工作之前必须使用 - 创建功能、构建组件、添加新功能或修改行为。通过协作对话探索用户意图、需求和设计。

Security Scan

This is an instruction-only brainstorming/design facilitation skill that is internally consistent with its stated purpose; it expects access to project files and git to write and commit design docs, so confirm you want the agent to have repository/file write access before enabling it.

Purpose & Capability

Name/description describe collaborative brainstorming and turning ideas into designs. The SKILL.md's actions (ask questions, propose options, produce design writeups) match that purpose. It also instructs the agent to inspect project files, docs, and recent commits and to write docs and commit them to git — these follow from the purpose but imply repository/file read/write and git privileges that are not explicitly declared.

Instruction Scope

Instructions stay within design/brainstorming scope. They explicitly tell the agent to 'first view current project status (files, documentation, recent commits)', create docs under docs/plans/..., and commit the design doc to git. Those file-system and git actions are relevant to the skill but are broader than a pure conversational helper — the instructions are precise about outputs but leave implementation (how to read/commit) unspecified.

Install Mechanism

No install spec or code files are included (instruction-only), so nothing is written to disk or downloaded by an installer. This is the lowest-risk install profile.

Credentials

The skill declares no required environment variables or credentials. However, its runtime instructions implicitly require access to the workspace/repository and ability to create and commit files via git (or equivalent). That implicit need is proportional to the purpose but should be acknowledged: enabling the skill effectively grants repository read/write rights to whatever agent/tool executes it.

Persistence & Privilege

always:false and normal agent invocation are used. The skill does not request persistent presence or attempt to modify other skills or global agent settings. It does reference required/recommended sub-skills, which is normal.

Assessment

This skill appears to do what it says: guide brainstorming, propose design options, and produce/commit design docs. Before enabling it, confirm the execution environment (the agent) should have read access to your project files and permission to write and commit to the repository. If you are uncomfortable with automatic commits, require manual review of generated docs or run the skill in a sandbox/copy of the repo. Also verify any referenced sub-skills (e.g., core-writing-plans) before granting broader access, and ensure no secrets are present in the repo files the agent will read.

Brainstorming - 将想法转化为设计

概述

通过自然的协作对话，帮助将模糊的想法转化为完整的设计和规格说明。

首先了解当前项目上下文，然后逐个提问来完善想法。一旦理解了要构建的内容，以小节形式（200-300字）呈现设计，每节后确认是否正确。

流程

理解想法

• 首先查看当前项目状态（文件、文档、最近提交）
• 逐个提问来完善想法
• 尽可能使用选择题，开放题也可以
• 每条消息只问一个问题 - 如果需要更多探索，分多个问题
• 聚焦于理解：目的、约束、成功标准

探索方案

• 提出 2-3 种不同方案及其权衡
• 以对话方式呈现选项，包括推荐和理由
• 优先展示推荐方案并解释原因

呈现设计

• 确信理解了要构建的内容后，呈现设计
• 分成 200-300 字的小节
• 每节后询问是否正确
• 涵盖：架构、组件、数据流、错误处理、测试
• 准备好返回澄清不清楚的地方

设计完成后

文档输出

• 将验证通过的设计写入 docs/plans/YYYY-MM-DD-<topic>-design.md
• 提交设计文档到 git

继续实施（如果需要）

• 询问：「准备好开始实施了吗？」
• REQUIRED SUB-SKILL: 使用 core-writing-plans 创建详细实施计划

领域扩展钩子

如果是嵌入式项目：

• RECOMMENDED: 使用 embedded-datasheet-analysis 分析硬件数据手册
• RECOMMENDED: 使用 embedded-feasibility-assessment 评估硬件约束
• RECOMMENDED: 使用 embedded-platform-selection 选择合适平台

如果是仿真项目：

• RECOMMENDED: 使用 simulation-requirements 分析仿真需求
• RECOMMENDED: 使用 simulation-architecture 设计仿真架构

核心原则

• 一次一个问题 - 不要用多个问题压垮用户
• 首选选择题 - 比开放题更容易回答
• YAGNI 原则 - 从所有设计中移除不必要的功能
• 探索替代方案 - 在确定之前始终提出 2-3 种方案
• 增量验证 - 分节呈现设计，验证每节
• 保持灵活 - 当某些内容不清楚时返回澄清