Tech Evaluation logo

Tech Evaluation

Community
312362115
tech-evaluation

技术选型技能:在多个候选方案中做出有依据的决策。 和 deep-research 的区别:deep-research 是广度调研(搞清楚一件事), tech-evaluation 是聚焦决策(A 还是 B,选哪个,给结论)。 包含权重矩阵、PoC 验证流程、决策报告模板。 触发词:选型、选哪个、A 还是 B、对比、评估方案、用什么框架、用什么库。 触发场景:task-start 方案阶段遇到选型问题、引入新依赖前、架构决策。 即使用户没有说"选型",只要意图是"在几个方案中做选择",都应触发此技能。

Overview

Publisher312362115
Repositoryclaude
Skill nametech-evaluation
Stars
107
Forks
17
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by 312362115 on GitHub. Read the source before you install it.

Installation

Install the Tech Evaluation AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/312362115/claude/tree/main/skills/tech-evaluation
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/312362115/claude.git /tmp/claude
mkdir -p .claude/skills
cp -r /tmp/claude/skills/tech-evaluation .claude/skills/tech-evaluation
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Tech Evaluation in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Tech Evaluation on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Tech Evaluation is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

技术选型(Tech Evaluation)

选型的核心不是"哪个更好",而是"在我们的场景下哪个更合适"。 没有最好的技术,只有最合适的技术。


第一步:定义选型问题

用 AskUserQuestion 明确以下信息:

要素问什么为什么重要
要解决的问题选型是为了解决什么?锚定评估标准
候选方案已经有哪些候选?需要我帮忙发现更多吗?确定评估范围
硬性约束必须满足的条件(许可证、语言、兼容性)先排除不合格的
优先维度最看重什么?(性能 / 生态 / 学习成本 / 成本)决定权重
决策时间需要多深入?快速判断还是深度评估?控制投入

第二步:快速筛选

2.1 排除不合格的

用硬性约束做第一轮筛选:

markdown
## 候选方案筛选

| 候选 | 约束 1(MIT 许可) | 约束 2(支持 TS) | 约束 3(活跃维护) | 结果 |
|------|-------------------|-------------------|-------------------|------|
| 方案 A | ✅ | ✅ | ✅ | 进入评估 |
| 方案 B | ✅ | ❌ | ✅ | 排除 |
| 方案 C | ✅ | ✅ | ❌(2 年无更新) | 排除 |

2.2 快速判断路径

如果筛选后只剩 1-2 个候选,且差异明显:

  • 直接给出推荐 + 理由,不需要走完整评估
  • 记录决策到 spec 文档中即可

如果筛选后有 2-3 个势均力敌的候选 → 进入第三步完整评估。


第三步:多维度评估

3.1 构建评估矩阵

根据用户关注的维度,构建权重矩阵:

markdown
## 评估维度与权重

| 维度 | 权重 | 说明 |
|------|------|------|
| 功能匹配度 | 30% | 是否满足核心需求 |
| 性能 | 25% | 对应场景下的实际表现 |
| 生态与社区 | 20% | 文档质量、社区活跃度、第三方集成 |
| 学习成本 | 15% | 团队上手难度 |
| 运维成本 | 10% | 部署复杂度、监控、升级成本 |

权重确定方式:

  • 用户明确说了优先级 → 直接用
  • 用户没说 → 给出建议权重,让用户确认

3.2 逐维度评估

对每个维度,用事实和数据评估,不用"感觉":

维度怎么评估数据来源
功能匹配度列出需求清单,逐项检查每个候选是否支持官方文档、GitHub issues
性能找 benchmark 数据,或自己跑 PoC 测试官方 benchmark、第三方评测、自测
生态与社区GitHub stars/issues 响应速度、npm 周下载量、Stack Overflow 问题数GitHub、npm、Stack Overflow
学习成本文档质量、API 设计是否直觉、有无迁移指南官方文档、教程资源
运维成本部署方式、配置复杂度、升级历史(有无 breaking changes)CHANGELOG、升级指南

3.3 PoC 验证(可选但推荐)

对关键维度,写代码验证比看文档更可靠:

markdown
## PoC 验证

### 验证目标
用方案 A 和方案 B 分别实现 <核心场景>,对比:
- 代码量和复杂度
- 实际性能数据
- 遇到的坑

### 验证结果
| 指标 | 方案 A | 方案 B |
|------|--------|--------|
| 代码行数 | 120 行 | 85 行 |
| 响应时间(p95) | 23ms | 18ms |
| 遇到的问题 | 文档缺失,靠看源码 | 顺利,文档完整 |

PoC 不需要做完整功能,只需要验证最不确定的维度。


第四步:综合评分与决策

4.1 评分汇总

markdown
## 综合评分

| 维度 | 权重 | 方案 A | 方案 B | 方案 C |
|------|------|--------|--------|--------|
| 功能匹配度 | 30% | 9 | 8 | 7 |
| 性能 | 25% | 7 | 9 | 8 |
| 生态与社区 | 20% | 8 | 7 | 9 |
| 学习成本 | 15% | 6 | 8 | 7 |
| 运维成本 | 10% | 7 | 8 | 6 |
| **加权总分** | | **7.65** | **8.05** | **7.50** |

4.2 给出决策

markdown
## 选型决策

**推荐:方案 B**

### 核心理由
- 加权总分最高(8.05)
- 在最看重的性能维度(权重 25%)上明显领先
- PoC 验证中开发体验最好

### 取舍说明
- 放弃方案 A 的原因:学习成本较高,团队没有相关经验
- 放弃方案 C 的原因:社区活跃但功能匹配度不足

### 风险提示
- 方案 B 的社区规模较小,未来可能面临维护风险
- 建议:核心功能不过度依赖其独有特性,保持可替换性

第五步:输出选型报告

选型结论写入 spec 文档(调 writing skill 的技术文档模式),至少包含:

  • 背景与动机:为什么需要选型
  • 候选方案:有哪些选项
  • 评估过程:评估维度、权重、数据来源
  • PoC 结果:如果做了验证
  • 决策与取舍:选了什么、为什么选它、放弃了什么

选型准则

  • 场景优先:不存在"最好的"技术,只有"最合适当前场景的"技术
  • 数据说话:每个评分都要有事实依据,不凭印象打分
  • 验证不确定性:最不确定的维度用 PoC 验证,不靠猜
  • 考虑团队:技术本身好不等于团队用得好,学习成本是真实成本
  • 留退路:优先选不锁定的方案,保持可替换性
  • 不过度评估:2 个候选差异明显就直接选,不需要搞 5 维 10 分的矩阵

与其他 skill 的关系

task-start(方案阶段遇到选型)→ tech-evaluation(评估决策)
deep-research(需要广度调研时)← tech-evaluation 按需调用
tech-evaluation → writing(输出选型报告到 spec)

tech-evaluation vs deep-research:

  • tech-evaluation:必须给结论。"选 A,因为 XYZ"
  • deep-research:不一定给结论。"目前市场格局是这样,趋势是那样"
  • 选型前如果对候选方案不够了解,可以先用 deep-research 调研,再用 tech-evaluation 决策

Frequently asked questions

What does the Tech Evaluation AI skill do?

技术选型技能:在多个候选方案中做出有依据的决策。 和 deep-research 的区别:deep-research 是广度调研(搞清楚一件事), tech-evaluation 是聚焦决策(A 还是 B,选哪个,给结论)。 包含权重矩阵、PoC 验证流程、决策报告模板。 触发词:选型、选哪个、A 还是 B、对比、评估方案、用什么框架、用什么库。 触发场景:task-start 方案阶段遇到选型问题、引入新依赖前、架构决策。 即使用户没有说"选型",只要意图是"在几个方案中做选择",都应触发此技能。

Why use Tech Evaluation on TypingMind?

Because you install it once and use it with any model. Tech Evaluation is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Tech Evaluation in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/312362115/claude/tree/main/skills/tech-evaluation. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Tech Evaluation?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Tech Evaluation?

As many as you like. As long as a model supports skills, you can use Tech Evaluation with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Tech Evaluation AI skill free?

Yes. It is published on GitHub by 312362115 under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇