Token导航 LogoToken导航TokenDH.com
研究检索需要联网github未标认证来源可访问clear审计通过

problem-solving解决问题

Agent Skill

problem-solving 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

272

周安装

11

GitHub Stars

17

下载量

85
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

3

许可证

MIT

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:problem-solving(解决问题)
来源仓库:https://github.com/nguyenthienthanh/aura-frog
仓库路径:skills/problem-solving
安装命令:
npx skills add https://github.com/nguyenthienthanh/aura-frog --skill problem-solving
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。不同来源提供的安装方式可能略有差异;本站展示可直接复制的安装命令,安装前请核对来源页面。

skills.shnpx skills
npx skills add https://github.com/nguyenthienthanh/aura-frog --skill problem-solving

简介

用于查找、检索和筛选相关信息,适合快速定位候选结果。

  • 适用于关键词搜索、任务场景匹配和来源线索筛选。
  • 可结合仓库路径和原始 README 核验具体用法。
  • 安装方式:通过 GitHub 仓库安装,使用前确认权限与维护状态。
  • 注意是否会触发联网、命令执行或文件读写操作。problem-solving 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

SKILL.md

Problem Solving Techniques

Use When: Stuck, need breakthrough, or evaluating approaches


5 Techniques

techniques[5]{name,when,approach}:
  Simplification Cascades,Complexity spiraling / 5+ attempts failed,Strip to minimal → rebuild
  Collision-Zone Thinking,Innovation blocks / need breakthrough,Combine unrelated concepts
  Meta-Pattern Recognition,Same issue across domains,Find underlying pattern
  Inversion Exercise,Forced into "only way" thinking,Ask "what if opposite?"
  Scale Game,Production readiness unclear,Test at 10x / 100x / 1000x

1. Simplification Cascades

When: Complexity spiraling, 5+ implementations tried

Process:

1. Remove ALL features except core
2. Make it work with hardcoded values
3. Add ONE thing back
4. Repeat until issue appears
5. Fix at that layer

Example:

Problem: Auth + caching + retry + logging all broken

Simplify:
1. Remove retry, logging, caching → just auth
2. Auth works? Yes → add caching
3. Caching breaks it → found the issue
4. Fix caching layer
5. Re-add retry, logging

2. Collision-Zone Thinking

When: Need creative breakthrough, conventional approaches failed

Process:

1. List unrelated domains
2. Find principles from each
3. Combine into novel solution

Example:

Problem: Users abandoning checkout

Domains: Gaming + Psychology + Logistics

Collision:
- Gaming: Progress bars, achievements
- Psychology: Loss aversion
- Logistics: Just-in-time delivery

Solution: "Your items are reserved for 10 min" +
          progress indicator +
          "3 people viewing this item"

3. Meta-Pattern Recognition

When: Same issue keeps appearing in different forms

Process:

1. List all similar issues
2. Find what they share
3. Fix the meta-pattern

Example:

Issues:
- Users table query slow
- Orders table query slow
- Products table query slow

Meta-pattern: All queries filter by date without index

Fix: Add date indexes to all tables

4. Inversion Exercise

When: Stuck in "only way" thinking

Process:

1. State current assumption
2. Ask: "What if the opposite?"
3. Explore inverted approach

Example:

Assumption: "We need to cache API responses"

Inversion: "What if we never cache?"
→ Forces real-time design
→ Discovers: Most data doesn't change
→ Solution: Cache-first with invalidation
   (opposite of assumed API-first)

5. Scale Game

When: Production readiness unclear

Process:

1. Test at 10x current load
2. Test at 100x
3. Test at 1000x
4. Find breaking point
5. Design for 10x actual need

Example:

Current: 100 users/day

Scale test:
- 1,000: Works fine
- 10,000: DB connection pool exhausted
- 100,000: Memory OOM

Breaking point: 10,000 users
Design for: 1,000 (10x buffer)
Fix: Connection pooling + memory optimization

Decision Matrix

decision[5]{symptom,technique,model}:
  "Tried everything",Simplification Cascades,sonnet
  "Need creative idea",Collision-Zone Thinking,opus
  "Keeps happening",Meta-Pattern Recognition,sonnet
  "No other way",Inversion Exercise,sonnet
  "Will it scale?",Scale Game,sonnet

Quick Reference

Stuck → Simplify first
Creative block → Collision zones
Recurring issues → Meta-patterns
Tunnel vision → Invert assumptions
Scaling fears → Scale game

Invoke: Use when conventional debugging fails or need breakthrough.

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

04

需要参考平台分布和安装热度时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

OpenCode

28.54%
按下载量换算24

Claude Code

20.9%
按下载量换算18

windsurf

18.28%
按下载量换算16

cline

13.84%
按下载量换算12

Codex

8.77%
按下载量换算7

Antigravity

3.5%
按下载量换算3

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。

来源信息

继续浏览同类 Skills