Token导航 LogoToken导航

Agent Skill · 研究检索

morphological-analysis-triz(形态分析 triz)

morphological-analysis-triz 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。

morphological-analysis-triz 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为只读;许可证为 MIT,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 37,672。

总安装 1,693周安装 72GitHub Stars 85下载 593核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
MIT

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:morphological-analysis-triz(形态分析 triz)
来源仓库:https://github.com/lyndonkl/claude
仓库路径:skills/morphological-analysis-triz
安装命令:
npx skills add https://github.com/lyndonkl/claude --skill morphological-analysis-triz
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/lyndonkl/claude --skill morphological-analysis-triz

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

morphological-analysis-triz 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中快速定位候选结果。适用于关键词搜索、任务场景匹配或来源线索筛选等研究检索场景。通过 npx skills add 命令从指定 GitHub 仓库安装并使用该技能。

安装前需确认权限范围、维护状态,注意是否涉及联网、命令执行或文件读写操作。适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

来源仓库内路径:skills/morphological-analysis-triz

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/lyndonkl/claude --skill morphological-analysis…;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它标注为只读,先用只读任务试一次,确认行为符合预期再扩大使用范围。

常见问题

6 条

morphological-analysis-triz 怎么安装?

在终端执行 npx skills add https://github.com/lyndonkl/claude --skill morphological-analysis-triz。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

morphological-analysis-triz 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

morphological-analysis-triz 需要什么权限?

权限级别是只读。该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

morphological-analysis-triz 是免费的吗?

来源标注的许可证是 MIT。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

morphological-analysis-triz 用的人多吗?

公开数据是累计安装 1,693 次,近一周安装 72 次,下载 593 次,GitHub 85 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

morphological-analysis-triz 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 3 个目录同时收录,说明这个 Skill 流传比较广。
  • 许可证明确为 MIT,商用和分发边界好判断。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。
  • 需要许可证清楚、并且有第三方扫描结果的团队项目。

不太适合

  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
morphological-analysis-triz

形态分析 triz · 本页

1,69385只读MIT通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Morphological Analysis & TRIZ

Workflow

Copy this checklist:

Morphological Analysis & TRIZ Progress:
- [ ] Step 1: Define problem and objectives
- [ ] Step 2: Choose method (MA, TRIZ, or both)
- [ ] Step 3: Build morphological box (if MA)
- [ ] Step 4: Identify contradictions (if TRIZ)
- [ ] Step 5: Apply TRIZ principles
- [ ] Step 6: Evaluate and select solutions

Step 1: Define problem and objectives

Clarify problem statement, key objectives, constraints (cost, size, time, materials), and success criteria.

Step 2: Choose method

  • Morphological Analysis: 3-7 clear parameters, each with 2-5 options, goal is comprehensive exploration
  • TRIZ: Clear contradiction (improving A worsens B), need inventive breakthrough
  • Both: Complex system with parameters AND contradictions

Step 3: Build morphological box (if using MA)

  1. Identify 3-7 independent parameters (changing one doesn't force another)
  2. List 2-5 distinct options per parameter
  3. Create parameter × option matrix

See resources/template.md for structure.

Step 4: Identify contradictions (if using TRIZ)

State clearly:

  • Improving parameter: What to increase?
  • Worsening parameter: What degrades?
  • Look up in TRIZ contradiction matrix

See resources/template.md for 39 TRIZ parameters and contradiction matrix.

Step 5: Apply TRIZ principles

  1. Review 3-4 principles recommended by matrix
  2. Brainstorm applications of each principle
  3. Generate solution concepts
  4. Combine principles for stronger solutions

See resources/template.md for all 40 principles.

For advanced techniques, see resources/methodology.md.

Step 6: Evaluate and select

Morphological: Identify promising combinations, eliminate infeasible, score on objectives, select top 3-5

TRIZ: Assess contradiction resolution, check side effects, estimate difficulty, select most promising

Use resources/evaluators/rubric_morphological_analysis_triz.json for quality criteria.

Common Patterns

Typical Parameters (Examples)

Physical Products: Materials, power source, form factor, control interface, manufacturing method Software: Architecture, data storage, UI, deployment, authentication Services: Delivery channel, pricing model, timing, customization, support level Processes: Automation level, batch size, quality control, scheduling, location

Common Contradictions

Improving ↑Worsens ↓Example TRIZ Principles
SpeedPrecisionSegmentation, Periodic action
StrengthWeightAnti-weight, Composite materials
ReliabilityComplexitySegmentation, Beforehand cushioning
FunctionalityEase of useSegmentation, Universality
CapacitySizeNesting, Another dimension

Full principles list: See resources/template.md for all 40.

When to Combine MA + TRIZ

  1. Build morphological box → Find promising configurations
  2. Identify contradictions in top configurations
  3. Apply TRIZ to resolve contradictions
  4. Re-evaluate configurations with contradictions resolved

Guardrails

Morphological Analysis:

  • Limit parameters: 3-7 parameters (too few = incomplete, too many = explosion)
  • Ensure independence: Changing one parameter shouldn't force changes in another
  • Manageable options: 2-5 per parameter (practical range)
  • Don't enumerate all: Focus on promising clusters

TRIZ:

  • Verify real contradiction: Improving A truly worsens B (not just budget limit)
  • Adapt principles: Use as metaphors, not literal prescriptions
  • Check new contradictions: Solution may introduce new trade-offs
  • Combine principles: Often need 2-3 together

General:

  • Document rationale for parameters/options selected
  • Iterate if first pass reveals missing dimensions
  • Prototype top concepts - don't just analyze

Quick Reference

Resources:

  • resources/template.md - Morphological structure, TRIZ contradiction matrix, 40 principles
  • resources/methodology.md - Advanced TRIZ (trends of evolution, substance-field, ARIZ algorithm)
  • resources/evaluators/rubric_morphological_analysis_triz.json - Quality criteria

Output: morphological-analysis-triz.md with problem definition, morphological matrix (if used), contradictions, TRIZ principles applied, solution concepts, evaluation, selected solutions

Success Criteria:

  • Parameters independent and essential (3-7 with 2-5 options each)
  • Contradictions clearly stated (improving/worsening parameters)
  • Multiple principles applied per contradiction
  • Solutions are novel, feasible, address objectives
  • Top 3-5 selected with rationale
  • Score ≥ 3.5 on rubric

Quick Decisions:

  • Simple configuration? → Morphological only
  • Clear contradiction? → TRIZ only
  • Complex with trade-offs? → Both methods
  • Unsure? → Start TRIZ to identify contradictions, then build morphological box

Common Mistakes:

  1. Too many parameters (>7 = explosion)
  2. Dependent parameters (choosing A forces B)
  3. Vague contradiction ("better vs cheaper" - be specific)
  4. Literal TRIZ (principles are metaphors)
  5. No evaluation (generate but don't filter)

Examples:

Morphological (Portable Speaker):

Power: Battery | Solar | Hybrid
Size: Pocket | Handheld | Tabletop
Audio: Mono | Stereo | Surround
Material: Plastic | Metal | Fabric
Control: Button | Touch | Voice | App
Result: 3×3×3×4×4 = 432 configs → Evaluate top 10

TRIZ (Electric Vehicle Range):

Contradiction: Increase range → worsens cost (battery expensive)
Principles: #6 (Universality - battery is structure), #35 (Parameter change - new chemistry)
Solution: Structural battery pack + high energy density cells

Combined:

Build morphological box for EV architecture → Top config has range/cost contradiction → Apply TRIZ Universality principle → Structural battery resolves both range and cost

For detailed principle explanations, contradiction matrix, advanced techniques (substance-field analysis, ARIZ, trends of evolution), and software/service adaptation, see resources/template.md and resources/methodology.md.

平台分布

Claude Code

31.56%
按下载量换算187

Gemini CLI

23.19%
按下载量换算138

Antigravity

15.59%
按下载量换算92

windsurf

13.72%
按下载量换算81

OpenCode

7.44%
按下载量换算44

github-copilot

3.83%
按下载量换算23

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

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。

继续浏览同类 Skills