Eval Consistency

Community

YIKUAIBANZI

eval-consistency

测试 use-persona 的角色扮演一致性。给定 persona + 10 个对话场景，生成回复并按 5 个维度评分，输出一致性报告。

Overview

Publisher	YIKUAIBANZI
Repository	`forge-skill`
Skill name	`eval-consistency`
Stars	129
Forks	22
Bundled files	Instructions only
License	MIT
Links	Skill source Repository

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 YIKUAIBANZI on GitHub. Read the source before you install it.

Installation

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

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/YIKUAIBANZI/forge-skill/tree/main/evals/eval-consistency
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.

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/YIKUAIBANZI/forge-skill.git /tmp/forge-skill
mkdir -p .claude/skills
cp -r /tmp/forge-skill/evals/eval-consistency .claude/skills/eval-consistency

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Eval Consistency 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 Eval Consistency 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 Eval Consistency 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.

/eval-consistency — 角色扮演一致性评测

你的任务是对 use-persona 的角色扮演质量做一次系统性评测，全程在当前对话中完成，不需要调用任何外部 API。

Step 0：加载测试资源

读取测试用例文件：evals/test_cases/persona_consistency_cases.yaml
根据 persona_name 字段，读取对应 persona： personas/others/{persona_name}/persona.json
从 persona.json 中提取 chat-card 关键内容：
- L0 硬性特征
- L2 表达风格（语言特征 + 沟通模式，重点是 signature_phrases 和消息长度偏好）
- L4 互动模式（关键场景下的表现）


正在加载 {persona_name} 的 persona 和测试用例...
共 {N} 个场景待测试。

Step 1：逐场景测试

对每个测试用例，执行两步：

1a. 生成角色扮演回复

以 persona 的身份回复用户消息。只输出回复本身，不加任何解释。

内部模板（不展示给用户）：


你是 {persona_name}。
[chat-card 关键内容]

用户发来消息："{user_message}"

以你的身份回复，只输出回复本身。

1b. 评分（内部执行，立即给出）

生成回复后，立刻按以下 5 个维度给自己打分（每项 0-20 分）：

维度	评分标准
消息长度	回复长度是否符合 L2 的消息长度偏好？短消息风格但回了长段落扣分
口头禅命中	是否自然用到了 L2 的 signature_phrases？完全没有扣分
标点风格	标点和语气是否符合 persona 的风格描述？
互动模式	在这个具体场景下，互动方式是否符合 L4 的 scene_responses？
边界遵守	有没有违反 L0 的硬性特征？违反则此项得 0 分

给出每项分数 + 一句话说明。

Step 2：输出完整报告

所有场景跑完后，输出评测报告：


===================================
角色扮演一致性评测报告 — {persona_name}
===================================

## 逐场景结果

[c01] {场景简述}
  回复："{生成的回复}"
  得分：{total}/100
  ✅/⚠️ 消息长度：{score}/20 — {说明}
  ✅/⚠️ 口头禅命中：{score}/20 — {说明}
  ✅/⚠️ 标点风格：{score}/20 — {说明}
  ✅/⚠️ 互动模式：{score}/20 — {说明}
  ✅/⚠️ 边界遵守：{score}/20 — {说明}

[c02] ...

---

## 汇总

平均分：{avg}/100  {✅ 通过 / ❌ 未达标（目标 70+）}

各维度平均：
  消息长度    {avg}/20
  口头禅命中  {avg}/20
  标点风格    {avg}/20
  互动模式    {avg}/20
  边界遵守    {avg}/20

## 主要问题
{如果平均分 < 70，列出最常见的失分点}

## 建议
{如果某维度平均分 < 12，给出 1-2 条具体改进建议，指向 persona 的哪一层需要补充}

Step 3：保存结果（可选）

询问用户是否保存：


要把这次结果存入 evals/results/ 吗？
以后优化后可以对比。（y/n）

如果确认，写入 evals/results/consistency_{YYYYMMDD}.md。

注意

全程不需要 API Key：评分是你自己执行的，不是另起一个 LLM
评分要诚实：对自己生成的回复该扣分就扣分，不要因为是自己生成的就打高分
用例是基于小美的，如果用户指定了其他 persona，根据那个 persona 的 L2/L4 调整评分标准

Frequently asked questions

What does the Eval Consistency AI skill do?

测试 use-persona 的角色扮演一致性。给定 persona + 10 个对话场景，生成回复并按 5 个维度评分，输出一致性报告。

Why use Eval Consistency on TypingMind?

Because you install it once and use it with any model. Eval Consistency 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 Eval Consistency in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/YIKUAIBANZI/forge-skill/tree/main/evals/eval-consistency. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Eval Consistency?

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 Eval Consistency?

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

Is the Eval Consistency AI skill free?

Yes. It is published on GitHub by YIKUAIBANZI 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

Clawsweeper

openclaw

OrganizationPopular

Use for all ClawSweeper work: OpenClaw issue/PR sweep reports, repair jobs, cloud fix PRs, @clawsweeper maintainer mention commands, trusted ClawSweeper-reviewed autofix/automerge, GitHub Actions…

Control Ui E2e

Use when designing, testing, fixing, or extending the OpenClaw Control UI GUI, including UI stress-test galleries with feedback inputs, Vitest + Playwright end-to-end checks, mocked Gateway flows,…

Deslop

Diff-scoped AI-slop cleanup pass: strip comment slop, defensive-check slop, type-laundering, and style drift from the current branch diff before autoreview.

Discord Clawd

Use to talk to the Discord-backed OpenClaw agent/session; not for archive search.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

/eval-consistency — 角色扮演一致性评测

Step 0：加载测试资源

Step 1：逐场景测试

1a. 生成角色扮演回复

1b. 评分（内部执行，立即给出）

Step 2：输出完整报告

Step 3：保存结果（可选）

注意

Frequently asked questions

Related AI Skills

Set up your own AI workspace now