Problem-Solving Techniques by congdon1207/agents.md
npx skills add https://github.com/congdon1207/agents.md --skill 'Problem-Solving Techniques'针对不同类型困境的系统化方法。每种技巧针对特定的问题模式。
在遇到以下情况时应用:
将症状与技巧匹配:
| 困境症状 | 技巧 | 参考 |
|---|---|---|
| 同一件事实现了5种以上方式,特殊用例不断增加 | 简化级联 | references/simplification-cascades.md |
| 常规解决方案不足,需要突破 | 碰撞区思维 | references/collision-zone-thinking.md |
广告位招租
在这里展示您的产品或服务
触达数万 AI 开发者,精准高效
| 相同问题出现在不同地方,重复造轮子 | 元模式识别 | references/meta-pattern-recognition.md |
| 解决方案感觉勉强,"必须这样做" | 反转练习 | references/inversion-exercise.md |
| 这在生产环境能行吗?边界情况不明确? | 规模游戏 | references/scale-game.md |
| 不确定使用哪种技巧 | 当遇到困境时 | references/when-stuck.md |
找到一个能消除多个组件的洞见。"如果这是真的,我们就不需要X、Y、Z。"
关键洞见: 所有事物都是一个通用模式的特例。
危险信号: "只需要再加一个情况..."(无限重复)
强制将不相关的概念结合在一起,以发现涌现属性。"如果我们把X当作Y来对待会怎样?"
关键洞见: 革命性的想法源于有意的隐喻混合。
危险信号: "我已经尝试了这个领域的所有方法"
识别出现在3个以上领域中的模式,以找到通用原则。
关键洞见: 模式如何出现的模式揭示了可重用的抽象。
危险信号: "这个问题是独一无二的"(很可能不是)
翻转核心假设以揭示隐藏的约束。"如果相反的情况成立会怎样?"
关键洞见: 有效的反转揭示了"规则"的上下文依赖性。
危险信号: "只有一种方法可以做到这一点"
在极端情况下测试(放大/缩小1000倍,瞬间/长达一年)以暴露基本事实。
关键洞见: 在一个规模下有效的方法在另一个规模下会失败。
危险信号: "应该能很好地扩展"(未经测试)
references/ 目录阅读特定技巧强大的组合:
根据需要加载详细指南:
references/when-stuck.md - 调度流程图和决策树references/simplification-cascades.md - 级联检测和提取references/collision-zone-thinking.md - 隐喻碰撞过程references/meta-pattern-recognition.md - 模式抽象技巧references/inversion-exercise.md - 假设翻转方法论references/scale-game.md - 极端测试流程references/attribution.md - 来源和改编说明每周安装量
0
仓库
GitHub 星标数
8
首次出现
1970年1月1日
安全审计
Systematic approaches for different types of stuck-ness. Each technique targets specific problem patterns.
Apply when encountering:
Match symptom to technique:
| Stuck Symptom | Technique | Reference |
|---|---|---|
| Same thing implemented 5+ ways, growing special cases | Simplification Cascades | references/simplification-cascades.md |
| Conventional solutions inadequate, need breakthrough | Collision-Zone Thinking | references/collision-zone-thinking.md |
| Same issue in different places, reinventing wheels | Meta-Pattern Recognition | references/meta-pattern-recognition.md |
| Solution feels forced, "must be done this way" | Inversion Exercise | references/inversion-exercise.md |
| Will this work at production? Edge cases unclear? | Scale Game | references/scale-game.md |
| Unsure which technique to use | When Stuck | references/when-stuck.md |
Find one insight eliminating multiple components. "If this is true, we don't need X, Y, Z."
Key insight: Everything is a special case of one general pattern.
Red flag: "Just need to add one more case..." (repeating forever)
Force unrelated concepts together to discover emergent properties. "What if we treated X like Y?"
Key insight: Revolutionary ideas from deliberate metaphor-mixing.
Red flag: "I've tried everything in this domain"
Spot patterns appearing in 3+ domains to find universal principles.
Key insight: Patterns in how patterns emerge reveal reusable abstractions.
Red flag: "This problem is unique" (probably not)
Flip core assumptions to reveal hidden constraints. "What if the opposite were true?"
Key insight: Valid inversions reveal context-dependence of "rules."
Red flag: "There's only one way to do this"
Test at extremes (1000x bigger/smaller, instant/year-long) to expose fundamental truths.
Key insight: What works at one scale fails at another.
Red flag: "Should scale fine" (without testing)
references/Powerful combinations:
Load detailed guides as needed:
references/when-stuck.md - Dispatch flowchart and decision treereferences/simplification-cascades.md - Cascade detection and extractionreferences/collision-zone-thinking.md - Metaphor collision processreferences/meta-pattern-recognition.md - Pattern abstraction techniquesreferences/inversion-exercise.md - Assumption flipping methodologyreferences/scale-game.md - Extreme testing proceduresreferences/attribution.md - Source and adaptation notesWeekly Installs
0
Repository
GitHub Stars
8
First Seen
Jan 1, 1970
Security Audits
React 组合模式指南:Vercel 组件架构最佳实践,提升代码可维护性
107,800 周安装