Yida Skill Evaluator logo

Yida Skill Evaluator

Organization
openyida
yida-skill-evaluator

评测指定的 OpenYida 技能质量。输入技能名称,自动执行全链路闭环评测 (静态校验 → 路由测试 → 安全合规 → 覆盖度 → 多维评分 → 准出门槛 → 优化建议), 生成评测报告和改进建议。不要触发本技能来执行其他 OpenYida 开发任务。

Overview

Publisheropenyida
Repositoryopenyida
Skill nameyida-skill-evaluator
Stars
228
Forks
50
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 openyida on GitHub. Read the source before you install it.

Installation

Install the Yida Skill Evaluator 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/openyida/openyida/tree/main/yida-skills/skills/yida-skill-evaluator
  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/openyida/openyida.git /tmp/openyida
mkdir -p .claude/skills
cp -r /tmp/openyida/yida-skills/skills/yida-skill-evaluator .claude/skills/yida-skill-evaluator
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Yida Skill Evaluator 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 Yida Skill Evaluator 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 Yida Skill Evaluator 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.

触发条件

当用户的意图是「评测/测试/检查某个 openyida 技能的质量」时触发。典型表述:

  • "评测一下 yida-dashboard 技能"
  • "帮我跑一下 skill eval"
  • "检查这个技能的质量"
  • "这个技能能不能准出?"
  • "评估 yida-report 技能"
  • "测试下路由准确率"

前置条件

  1. 确认目标技能名称(如 yida-dashboard)。若用户未指定,列出可用技能供选择:
    bash
    ls yida-skills/skills/
  2. 确认 Node.js 版本 ≥ 18:
    bash
    node --version
  3. 确认依赖已安装:
    bash
    npm install

工作流

Step 1 — 快速评测(默认,无副作用)

大多数情况使用 pipeline 模式,它会自动串联所有评测步骤:

bash
node scripts/eval/pipeline.js --skill <技能名>

该命令自动执行以下全部步骤:

  1. 静态校验(文档规范性 + 可维护性)
  2. 路由测试(命中率 + 混淆对)
  3. 安全合规检查
  4. 覆盖度分析
  5. 10 维度综合评分 + 加权总分
  6. 准出门槛判定 + 自动优化建议

产物目录:project/.cache/eval/pipeline/<run-id>/

读取结果:

bash
cat project/.cache/eval/pipeline/*/pipeline-report.json | tail -1

Step 2 — 解读结果

从 pipeline-report.json 中提取关键信息,向用户报告:

  1. Pipeline 状态:status 字段(pass / fail / warn)
  2. 各步骤结果:steps[] 数组的 step / status / score / detail
  3. 总分:scorecard.overall(0-100 分)
  4. 准出判定:scorecard.gate(pass = 可准出,fail = 不可准出)
  5. 硬门槛详情:scorecard.hardGates 中每项的状态
  6. 优化建议:suggestions[] 中按 priority 排序的改进项

Step 3 — 深度评测(可选,用户要求时)

如果用户要求更深度的评测(如 A/B 对比、JUnit 报告):

bash
# A/B 基线对比(with_skill vs without_skill)
node scripts/eval/runner.js --mode baseline --skill <技能名> --format junit

# 单独维度评测
node scripts/eval/runner.js --mode doc-quality --skill <技能名>
node scripts/eval/runner.js --mode comprehensive --skill <技能名>

Step 4 — Web 控制台(可选)

如果用户希望在浏览器中查看评测结果:

bash
npm run eval:dashboard

然后打开 http://127.0.0.1:4500 查看控制台。

Step 5 — 输出评测报告

向用户呈现结构化报告:

## 技能评测报告:<技能名>

### Pipeline 状态:<PASS/FAIL/WARN>

| 步骤 | 状态 | 分数 | 详情 |
|------|------|------|------|
| 静态校验 | ✔/✗ | xx | ... |
| 路由测试 | ✔/✗ | xx% | ... |
| 安全合规 | ✔/✗ | xx | ... |
| 覆盖度 | ✔/✗ | xx% | ... |
| 综合评分 | ✔/✗ | xx/100 | ... |
| 准出判定 | ✔/✗ | - | ... |

### 评分卡(10 维度)

| 维度 | 得分 | 权重 | 加权得分 |
|------|------|------|----------|
| 规范性 | xx | 10% | x.x |
| 可维护性 | xx | 5% | x.x |
| 路由准确率 | xx | 15% | x.x |
| ... | ... | ... | ... |
| **总分** | **xx** | | |

### 准出门槛

| 门槛 | 要求 | 实际 | 状态 |
|------|------|------|------|
| 触发准确率 | ≥ 85% | xx% | ✔/✗ |
| 步骤完成率 | = 100% | xx% | ✔/✗ |
| 功能测试通过率 | ≥ 95% | xx% | ✔/✗ |
| 输出格式正确率 | ≥ 85% | xx% | ✔/✗ |
| 安全合规 | 0 failures | xx | ✔/✗ |

### 优化建议(前 3 条)

1. [blocker/critical/high] ...
2. ...
3. ...

可用评测模式

模式命令说明
pipeline--mode pipeline全自动闭环(推荐)
doc-quality--mode doc-quality文档规范性
routing--mode routing路由准确率
safety--mode safety安全合规
coverage--mode coverage覆盖度
comprehensive--mode comprehensive10 维度评分
baseline--mode baselineA/B 基线对比
e2e--mode e2e端到端基线(需 OPENYIDA_E2E=1)
generate--mode generate真实生成(需 OPENYIDA_E2E=1)

WHEN NOT

  • 不处理应用搭建、页面开发、数据管理等开发任务
  • 不处理非 openyida 技能的评测
  • 不修改技能文件——仅读取和评测(除非用户明确要求根据建议修改)
  • 不执行需要真实宜搭资源的评测(e2e / generate),除非用户明确要求
  • 不与 yida-dashboard、yida-report、yida-create-process 等搭建类技能混淆

Frequently asked questions

What does the Yida Skill Evaluator AI skill do?

评测指定的 OpenYida 技能质量。输入技能名称,自动执行全链路闭环评测 (静态校验 → 路由测试 → 安全合规 → 覆盖度 → 多维评分 → 准出门槛 → 优化建议), 生成评测报告和改进建议。不要触发本技能来执行其他 OpenYida 开发任务。

Why use Yida Skill Evaluator on TypingMind?

Because you install it once and use it with any model. Yida Skill Evaluator 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 Yida Skill Evaluator in TypingMind?

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

Which AI models can use Yida Skill Evaluator?

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 Yida Skill Evaluator?

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

Is the Yida Skill Evaluator AI skill free?

Yes. It is published on GitHub by openyida 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 👇