TypingMindTypingMindThe best frontend for AI
Skill Evaluation logo

Skill Evaluation

Community
naodeng
skill-evaluation

Use this skill when designing, running, interpreting, or reporting Agent Skill evaluations, selecting cases or judges, and analyzing trigger, benchmark, or regression evidence; triggers include Skill 评测、评测设计、回归评测。

Overview

Publishernaodeng
Repositoryawesome-qa-skills
Skill nameskill-evaluation
Stars
279
Forks
36
Bundled files
8
Links
Skill sourceRepositoryHomepage
  • 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.

  • 8 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

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

Installation

Install the Skill 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/naodeng/awesome-qa-skills/tree/main/evidence/skill-quality/2026-10-03-codex-pilot/reproduction/packages/skill-evaluation-zh
  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/naodeng/awesome-qa-skills.git /tmp/awesome-qa-skills
mkdir -p .claude/skills
cp -r /tmp/awesome-qa-skills/evidence/skill-quality/2026-10-03-codex-pilot/reproduction/packages/skill-evaluation-zh .claude/skills/skill-evaluation
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Skill 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 Skill 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 Skill 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.

Skill 评测

何时使用

  • 需要为一个 Skill 设计 realistic eval cases、positive/negative trigger 或 regression case。
  • 需要用 skill-up 验证/运行评测并解释结果和限制。
  • 需要选择 deterministic、script 或 semantic judge，或区分 benchmark 与 version regression。

输出格式选项

  • 默认输出简洁的 Markdown 评测报告，用表格呈现 case 结果和 evidence state。
  • 下游脚本需要机器可读结果时才输出 JSON；仍使用同一套证据词汇并保留限制。

如何使用

  1. 读取 Skill 契约、已有 evals/、历史失败和本次变更范围。
  2. 识别关键行为与证据维度：Outcome、Process、Style/Quality、Efficiency；只选择有意义的维度。
  3. 设计 HAPPY、INCOMPLETE、EXPLICIT_TRIGGER、IMPLICIT_TRIGGER、CONTEXTUAL_TRIGGER、NEGATIVE_TRIGGER、BOUNDARY 或 REGRESSION 用例。
  4. 按确定性优先选择 rule_based；可执行工件使用 script；只有需要语义判断时使用校准后的 agent_judge。
  5. 运行 skill-up validate；有授权凭据和目标时再运行 skill-up run 或本地 trace runner。记录 run metadata、trace、judge、产物和限制。
  6. 判断 Eval validity，区分 Skill Defect、Eval Defect、Infrastructure Defect 和 Unknown。
  7. 按固定报告结构输出结果、证据状态、benchmark/regression 结论、blocked checks 和推荐行动；真实失败经根因确认后才添加 regression case。

核心约束

  • skill-up 是主 Eval Engine；trace checks 只是深证据层，不得再造 Engine、Judge、Benchmark 或 Quality Score。
  • 不能把输出相似度写成 observed trigger；缺少 skill.selection trace 时标记 BLOCKED。
  • skill-up validate 不是 runtime 语义验证；静态、CLI smoke、Project Done 和单次语义观察不能自动升级为发布或业务结论。
  • 不自动修改 Skill，不自动无限优化；不把 Benchmark（with/without Skill）和 Version Regression（previous/current）混为一谈。
  • 值未知时写 unknown；证据不足保留 NOT_RUN、UNASSESSED、BLOCKED 或 INSUFFICIENT_EVIDENCE。
  • 即使输入极少、没有可运行目标或没有原始 trace，也先输出最小报告骨架，并显式写出本次适用的 canonical evidence state；不能只写“未验证”等自然语言替代 NOT_RUN、BLOCKED、UNASSESSED 或 INSUFFICIENT_EVIDENCE。

参考文件

  • 完整执行和报告契约见 prompts/skill-evaluation.md。
  • 选择 judge 前先读取目标 Skill 的 evals/ 和 fixtures。
  • 仓库治理契约与 trace rules 只作为可选深资料，复制后的 Skill 不得依赖其私有路径。

常见误区

  • 把 skill-up validate 或 dry-run 当成 runtime 或语义效果证据。
  • 缺少 trigger 事件时写成未触发，而不是 BLOCKED。
  • 把 with/without Skill 的 benchmark 与 previous/current 的版本回归混为一谈。

最佳实践

  • 从能够证明目标行为的最小确定性 case 开始。
  • 记录准确的 run identity、judge、environment、未获得的证据和限制。
  • 只有确认真实失败根因后才转成 regression case，并保留原始证据。

按需加载

  • 产出前读取 prompts/skill-evaluation.md。
  • 先读取目标 Skill 自己的 evals/，再按需读取 fixtures、examples 和脚本。
  • 仓库级 Evaluation Contract 或 local trace rules 只作为可选深资料；独立安装的 Skill 不得硬依赖它们。

交付前自检

  • 每个结论对应具体 case、judge 和 evidence state
  • run metadata、环境、模型和未执行项明确
  • Skill/Eval/Infrastructure/Unknown 分类没有被混淆
  • trigger、benchmark、regression 和 Quality Score 边界清楚

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Skill Evaluation AI skill do?

Use this skill when designing, running, interpreting, or reporting Agent Skill evaluations, selecting cases or judges, and analyzing trigger, benchmark, or regression evidence; triggers include Skill 评测、评测设计、回归评测。

Why use Skill Evaluation on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/naodeng/awesome-qa-skills/tree/main/evidence/skill-quality/2026-10-03-codex-pilot/reproduction/packages/skill-evaluation-zh. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Skill 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 Skill Evaluation?

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

Is the Skill Evaluation AI skill free?

It is published on GitHub by naodeng. Check the repository for licensing terms. 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.

Related AI Skills

View all
affaan-m logo

Competitive Report Structure

affaan-m
CommunityPopular

Use after benchmark-methodology has produced scored competitor profile cards. Assembles findings into a decision-grade report: landscape map, competitor profiles, benchmarking matrix, white-space…

40.4K
270.2K
1 files
View
affaan-m logo

Dmux Workflows

affaan-m
CommunityPopular

Multi-agent orchestration using dmux (tmux pane manager for AI agents). Patterns for parallel agent workflows across Claude Code, Codex, OpenCode, and other harnesses. Use when running multiple agent…

40.4K
270.2K
1 files
View
affaan-m logo

Documentation Lookup

affaan-m
CommunityPopular

Use up-to-date library and framework docs via Context7 MCP instead of training data. Activates for setup questions, API references, code examples, or when the user names a framework (e.g. React,…

40.4K
270.2K
1 files
View
affaan-m logo

Mle Workflow

affaan-m
CommunityPopular

Production machine-learning engineering workflow for data contracts, reproducible training, model evaluation, deployment, monitoring, and rollback. Use when building, reviewing, or hardening ML…

40.4K
270.2K
1 files
View

Set up your own AI workspace now

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