Skill Persona Check logo

Skill Persona Check

OrganizationPopular
ZJU-REAL
skill-persona-check

人设一致性检查与品牌调性检查:对比内容与创作者画像的账号定位、内容赛道、形式、受众、 风格和偏好, 输出一致性评分和具体偏离点。当用户说"符合我的人设吗"、"一致性检查"、"风格对不对"、 "像我写的吗"、"品牌一致"、"调性检查"、"这是我的风格吗"、"人设偏了没"、 "语气对不对"、"品牌声音检查"时触发。 必须有 Profile 才能工作;无 Profile 时提示先创建。

Overview

PublisherZJU-REAL
RepositoryEasel
Skill nameskill-persona-check
Stars
3.5K
Forks
535
Bundled files
1
LicenseApache-2.0
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.

  • 1 bundled files

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

  • Open source

    Published by ZJU-REAL on GitHub. Read the source before you install it.

Installation

Install the Skill Persona Check 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/ZJU-REAL/Easel/tree/main/skills/openclaw/skill-persona-check
  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/ZJU-REAL/Easel.git /tmp/Easel
mkdir -p .claude/skills
cp -r /tmp/Easel/skills/openclaw/skill-persona-check .claude/skills/skill-persona-check
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Skill Persona Check 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 Persona Check 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 Persona Check 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.

人设一致性检查

检查内容是否符合创作者人设和品牌调性,输出一致性评分与偏离诊断。

与其他 SKILL 的区别

SKILL定位关注点
persona-check(本 SKILL)人设/品牌一致性账号定位、题材、形式、受众、风格是否匹配画像
skill-quality-gate深度合规 + 质量审核平台规则、内容质量
skill-publish-checklist完整性检查有没有漏标题、漏封面等

前提条件

本 SKILL 必须有 Profile 才能工作。Profile 中应包含以下信息(部分或全部):

  • identity.md:账号定位、主线赛道、内容方向
  • style.md:语气、叙事、视觉和内容形式
  • audience.md:目标受众及其需求
  • preferences.md:要做、不做和明确红线
  • memory.md:当前画像已验证的经验与踩坑

如果没有 Profile,直接返回提示,不做检查。

输入

  • 待检查内容:文案文本或产物路径
  • Profile:通过 === EASEL ACCOUNT PROFILE === 标记注入,或指定画像名称

输出

输出结构化一致性报告,JSON 格式:

json
{
  "overall_score": 85,
  "verdict": "consistent | minor_drift | major_drift",
  "publish_allowed": true,
  "warning": "",
  "dimensions": [
    {
      "dimension": "检查维度名",
      "score": 90,
      "status": "aligned | drifted",
      "evidence": "具体证据文本",
      "suggestion": "调整建议"
    }
  ],
  "drift_summary": ["偏离点概述列表"],
  "rewrite_hints": ["具体修改建议"],
  "summary": "一句话总结"
}

评分标准:

  • 80-100:一致(consistent),无需人设警告
  • 60-79:轻微偏离(minor_drift),明确警告并给出修改建议
  • 0-59:明显偏离(major_drift),醒目警告账号定位/题材/形式偏离

人设评分只做提醒,不是发布权限。 publish_allowed 始终为 true;低分不得阻断发布、 不得要求用户为了通过评分而强制改稿。用户已经明确要发布时,展示警告后继续发布。内容安全、 平台合规、敏感信息等独立硬门禁不在本 SKILL 范围内,仍按对应规则处理。

执行步骤

Step 1 — 解析 Profile 画像

  1. 检测是否有 Profile 上下文(=== EASEL ACCOUNT PROFILE === 标记)
  2. 无 Profile → 直接输出提示信息并终止:
    未检测到账号 Profile,无法进行人设一致性检查。
    请先创建 Profile:用 skill-profile-builder 引导创建,或复制 profiles/_template/ 手动填写。
    Profile 的 style.md 应包含:写作风格、语气基调、人格特征、标志性表达。
  3. 有 Profile → 必须读取当前画像的 identity.md、style.md、audience.md、 preferences.md、memory.md;发布场景再读取 platforms.md。先提取账号主线、允许题材、 内容形式和受众,再提取语气、用词和平台习惯。不得只读 style.md 后凭语言相似度评分。

Step 2 — 分析待检查内容

对输入内容进行多维度语言分析:

  1. 题材与意图:这条内容在讲什么,是否属于账号主线或合理延展
  2. 内容形式:小说、动画、口播、测评、图文等是否匹配账号定位
  3. 目标受众:内容解决的问题、情绪价值和阅读门槛是否面向画像受众
  4. 语言风格:语气、用词、句式、叙事视角和情感色彩
  5. 平台与偏好:是否适合目标平台,是否触碰画像明确的“不做”项

Step 3 — 逐维度对比

将内容特征与 Profile 特征逐维度对比,每个维度独立评分:

维度对比内容权重
账号定位与内容赛道题材/主题 vs identity.md 主线、内容方向、选题池30%
内容形式一致性小说/动画/图文/口播等 vs 画像规定的主要内容形式15%
目标受众匹配内容价值与阅读/观看人群 vs audience.md15%
语气与叙事风格语气、节奏、视角 vs style.md15%
人格与用词表达人格、词汇、标志性表达 vs 画像10%
平台适配内容形态和表达 vs platforms.md(无目标平台时给中性分)10%
偏好与经验preferences.md 与当前画像 memory.md5%

每个维度评分 0-100,加权计算总分。

为防止语言相似掩盖根本性错位,计算后应用以下上限:

  • 账号定位与内容赛道 < 40:总分最高 59,必须判定 major_drift。
  • 内容形式一致性 < 40:总分最高 69,至少判定 minor_drift。
  • 触碰画像已确认的“不做”项或红线:总分最高 39,并明确指出证据;但仍只警告,不代替用户决定是否发布。
  • 用户主动要求跨赛道,只代表这是有意识的选择,不能因此虚增一致性分;报告中注明“用户主动跨赛道”即可。

示例:2D 搞笑动画博主 发布纯恐怖文字小说,即使同样口语化、有画面感、有反转, 账号赛道和内容形式仍严重不符,总分必须低于 60,不能因语言技巧给出 80+。

Step 4 — 定位偏离点

对于 score < 80 的维度,给出具体偏离证据:

  1. 引用原文:指出内容中偏离人设的具体段落或句子
  2. 对比说明:说明 Profile 期望的表达方式 vs 实际表达
  3. 严重程度:标记该偏离是否影响整体人设感知

Step 5 — 生成修改建议

针对每个偏离点,给出可操作的修改建议:

  • 具体到词级别:建议替换的词汇
  • 具体到句级别:建议调整的句式
  • 具体到段级别:建议重写的方向

Step 6 — 输出报告

汇总所有维度评分,生成结构化报告:

  1. 计算加权总分并应用严重偏离上限
  2. 判定 verdict(consistent / minor_drift / major_drift)
  3. 列出所有偏离点摘要
  4. 给出优先级排序的修改建议
  5. publish_allowed 固定输出 true;低于 80 分时填写醒目的 warning
  6. 生成一句话总结,明确“这是人设提醒,不阻止用户发布”

Profile 感知

  • 有 Profile:从 Profile 提取完整人设特征,进行全维度对比。这是本 SKILL 的标准工作模式。
  • 无 Profile:无法工作。直接提示用户创建 Profile,说明所需内容(style、tone、personality),并终止执行。本 SKILL 是 Easel 中唯一强制要求 Profile 的 SKILL。

自研溯源与参考项目见同目录 EASEL-META.md。

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 Persona Check AI skill do?

人设一致性检查与品牌调性检查:对比内容与创作者画像的账号定位、内容赛道、形式、受众、 风格和偏好, 输出一致性评分和具体偏离点。当用户说"符合我的人设吗"、"一致性检查"、"风格对不对"、 "像我写的吗"、"品牌一致"、"调性检查"、"这是我的风格吗"、"人设偏了没"、 "语气对不对"、"品牌声音检查"时触发。 必须有 Profile 才能工作;无 Profile 时提示先创建。

Why use Skill Persona Check on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/ZJU-REAL/Easel/tree/main/skills/openclaw/skill-persona-check. 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 Persona Check?

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 Persona Check?

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

Is the Skill Persona Check AI skill free?

Yes. It is published on GitHub by ZJU-REAL under the Apache-2.0 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 👇