design-advisor
Skill2 starsChanged 58 days agoMITView on GitHub
方案分析与避坑指南。编码前的"大脑"——帮助正确分析问题、设计方案、规避已知错误模式。包含设计指南、样式分析、反模式清单三大模块。可被 dev-flow 步骤 3(制定方案)按需调用,也可独立使用。
3 other projects use a version of this.
Adopted by
Most recently taken up by
- hugobatista/agent-skillstheir own version, first seen Sep 20, 2026
- filip-pilar/founder-skillstheir own version, first seen Sep 19, 2026
- pgomezurrea-eng/claude-skillstheir own version, first seen Sep 12, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- filip-pilar/founder-skills★ 2same name
- hugobatista/agent-skills★ 1same name
- pgomezurrea-eng/claude-skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository29 other files it gives its agents.
- skills/proactive-agent/assets/AGENTS.mdAGENTS.md
- agent-browserSkill
- browser-compatSkill
- browser-toolkitSkill
- code-reviewSkill
- coding-standardsSkill
- complexity-optimizerSkill
- continuous-learning-v2Skill
- dev-compSkill
- dev-flowSkill
- dom-animationSkill
- e2e-testingSkill
- find-skillsSkill
- frontend-patternsSkill
- i18nSkill
- issue-traceSkill
- knowledge-loopSkill
- pdf-readerSkill
- proactive-agentSkill
- requirement-intakeSkill
- research-docSkill
- search-firstSkill
- security-reviewSkill
- self-improving-agentSkill
- smart-commitSkill
- tavily-searchSkill
- tech-docSkill
- verification-loopSkill
- verification-pipelineSkill
The file
Files
design-advisor — 方案分析与避坑指南
定位:编码前的"大脑"——帮助正确分析问题、设计方案、规避已知错误模式。 可被
dev-flow步骤 3(制定方案)按需调用,也可独立使用。
全局输出规范(最高优先级)
本 Skill 生成的方案分析、样式诊断、反模式建议中,文件路径、代码位置引用必须遵循
~/.codebuddy/rules/AI行为规范.mdc的「文件/代码位置引用」规范(反引号包裹相对路径`相对路径`+ 空格后缀行号L行号,IDE 自动识别为可点击链接)。适用范围:方案设计中引用的代码文件、样式分析中的 SCSS/CSS 文件、反模式清单中引用的示例代码位置等所有输出。
路由规则
收到请求后,根据用户意图匹配下表,使用 read_file 加载对应子模块(相对于本 Skill 目录):
| 意图关键词 | 目标模块 | 加载指令 |
| 方案设计 / 评估方案 / 制定方案 / 分析问题 / 排查问题 / 定位根因 | 设计指南 | read_file("modules/design-guide.md") |
| 样式分析 / CSS调试 / 内联样式 / 主题系统 / scss | 样式分析 | read_file("modules/style-analysis.md") |
| 反模式 / 避坑 / 常见错误 / 踩坑 / 经验教训 / 反例 | 反模式清单 | read_file("modules/anti-patterns.md") |
加载策略
- 单一意图:只加载匹配的一个模块。
- 多模块场景:用户意图涉及多个模块时,按需依次加载。例如「帮我分析这个样式问题的方案」→ 先加载设计指南,再加载样式分析。
- dev-flow 调用时:dev-flow 步骤 3 会在
use_skill调用中指定路由目标(如「路由到 design-guide 模块」),直接执行对应的read_file加载。 - 不确定时:默认加载设计指南(design-guide),它是最通用的模块。
模块概览(仅供路由判断,不展开详情)
设计指南(design-guide)
方案设计的核心方法论:追根因、复用已有逻辑、隔离影响范围、对比参照、JS/CSS 断点分析、边界情况处理、问题排查原则、第三方库源码确认。
样式分析(style-analysis)
样式来源分析规范:CSS vs JS 内联样式识别、内联样式覆盖策略、.scss vs .module.scss 差异、主题系统、对比参照修复原则。
反模式清单(anti-patterns)
已发生过的 9 个错误模式及正确做法:反复调参、影响范围失控、自创等价逻辑、跳过根因分析、改动范围越界、误解用户指令、优化范围失控、JS/CSS 断点不一致、优化破坏 DOM 时序。
独立使用
不依赖 dev-flow,可直接触发:
| 用户说 | AI 行为 |
| "帮我分析下这个方案" | read_file 加载 design-guide 模块 |
| "这个样式为什么不对" | read_file 加载 style-analysis 模块 |
| "有没有什么反模式要注意" | read_file 加载 anti-patterns 模块 |
| "评估下这个修改方案" | read_file 加载 design-guide 模块 |
| "分析下这个样式问题的方案" | read_file 依次加载 design-guide + style-analysis |
| "帮我避坑" | read_file 加载 anti-patterns 模块 |
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

