Skill Profile Manager logo

Skill Profile Manager

OrganizationPopular
ZJU-REAL
skill-profile-manager

管理账号画像全生命周期:创建空白画像、编辑六维字段、更新记忆、切换、导出和对比。 当用户说“新建/编辑/更新/切换/导出/对比画像、写进画像记忆”时使用。 首次从社媒数据生成画像用 skill-profile-builder;只提炼语言风格用 skill-voice-builder;品牌首次入驻引导用 skill-brand-onboarding。

Overview

PublisherZJU-REAL
RepositoryEasel
Skill nameskill-profile-manager
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 Profile Manager 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-profile-manager
  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-profile-manager .claude/skills/skill-profile-manager
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Skill Profile Manager 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 Profile Manager 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 Profile Manager 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.

账号画像管理器

创建、编辑、记忆更新、导出、对比 — 画像的全生命周期管理

输入

字段必填说明
action是操作类型:create / edit / memory-update / export / diff / list / switch
profile_name视操作画像名称(create 时必填,list 时不需要)
field否要编辑的文件:identity / style / audience / platforms / preferences / memory
content否要写入的内容(edit / memory-update 时使用)
profile_b否第二个画像名称(diff 操作时必填)
data_source否记忆更新的数据来源:用户口述 / 数据报告 / 帖子反馈

输出

create 操作

输出新画像目录结构确认:

markdown
## 画像创建完成

**画像名称**: {profile_name}
**目录**: profiles/{profile_name}/

### 已创建文件
| 文件 | 状态 | 说明 |
|------|------|------|
| identity.md | ✅ 已填写 | 定位、差异化、内容方向 |
| style.md | ✅ 已填写 | 语气、开头结构、视觉风格 |
| audience.md | ✅ 已填写 | 人口统计、兴趣、痛点 |
| platforms.md | ⬜ 待补充 | 平台账号、内容格式 |
| preferences.md | ⬜ 待补充 | 合规规则、红线 |
| memory.md | ⬜ 空 | 将随使用积累 |

diff 操作

输出两个画像的逐文件对比表:

markdown
## 画像对比:{profile_a} vs {profile_b}

| 维度 | {profile_a} | {profile_b} | 差异摘要 |
|------|-------------|-------------|----------|
| 定位 | ... | ... | ... |
| 风格 | ... | ... | ... |
| 受众 | ... | ... | ... |
| 平台 | ... | ... | ... |
| 偏好 | ... | ... | ... |

list 操作

markdown
## 当前画像列表

| 画像 | 完整度 | 最后更新 | 记忆条数 |
|------|--------|----------|----------|
| 科技数码达人 | 85% | 2026-07-15 | 12 |
| 搞笑整活博主 | 60% | 2026-07-10 | 3 |

执行步骤

操作路由

  1. 解析用户意图:从用户输入识别 action 类型
    • "创建画像" / "新建账号" → create
    • "编辑画像" / "改一下画像" → edit
    • "写进画像" / "画像记忆" / "记住这个" → memory-update
    • "导出画像" → export
    • "画像对比" / "两个画像比较" → diff
    • "有哪些画像" / "画像列表" → list
    • "切换画像" / "用另一个画像" → switch

create 流程

  1. 检查画像是否已存在:读取 profiles/ 目录,确认同名画像不存在
  2. 复制模板:将 profiles/_template/ 复制为 profiles/{profile_name}/
  3. 引导填写核心信息:依次向用户提问,收集以下信息
    • identity.md:你是谁?做什么内容?和别人有什么不同?
    • style.md:你的语言风格是什么?正式/轻松/搞笑?常用口头禅?
    • audience.md:你的目标受众是谁?年龄、兴趣、痛点?
  4. 写入文件:将收集到的信息按模板格式写入对应文件
  5. 提示后续:告知用户可后续补充 platforms.md 和 preferences.md

edit 流程

  1. 定位文件:根据 field 参数确定要编辑的文件路径 profiles/{profile_name}/{field}.md
  2. 读取当前内容:展示该文件的当前内容给用户确认
  3. 应用修改:根据用户指示修改指定字段,保持文件其他部分不变
  4. 确认变更:输出修改前后的 diff 摘要

memory-update 流程

  1. 读取现有记忆:读取 profiles/{profile_name}/memory.md
  2. 格式化新记忆条目:按以下格式追加
    ### {日期} — {来源标签}
    - 发现:{具体发现}
    - 行动建议:{可执行的建议}
  3. 去重检查:与已有记忆条目比对,避免重复记录
  4. 追加写入:将新条目追加到 memory.md 末尾

export 流程

  1. 汇总画像:读取画像目录下所有 .md 文件
  2. 生成摘要卡片:合并为一份结构化的画像摘要(Markdown 格式)
  3. 输出到 outputs/:保存为 outputs/<画像名-导出日期>/profile-export.md

diff 流程

  1. 读取两个画像:分别读取 profiles/{profile_a}/ 和 profiles/{profile_b}/ 下所有文件
  2. 逐维度对比:按 identity / style / audience / platforms / preferences 五个维度对比
  3. 生成差异表:输出结构化对比表,高亮关键差异点

list 流程

  1. 扫描 profiles/ 目录:列出所有子目录(排除 _template)
  2. 计算完整度:检查每个画像的 6 个文件是否有实质内容(非空非模板)
  3. 输出列表:按完整度排序输出

Profile 感知

这个 SKILL 本身就是 Profile 的管理工具:

  • 有 Profile 上下文时:默认操作当前激活的画像,edit / memory-update 不需要再指定 profile_name
  • 无 Profile 上下文时:list 操作展示所有可用画像,其他操作必须显式指定 profile_name
  • 首次使用时:如果 profiles/ 目录下没有任何画像(只有 _template),自动进入 create 流程

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 Profile Manager AI skill do?

管理账号画像全生命周期:创建空白画像、编辑六维字段、更新记忆、切换、导出和对比。 当用户说“新建/编辑/更新/切换/导出/对比画像、写进画像记忆”时使用。 首次从社媒数据生成画像用 skill-profile-builder;只提炼语言风格用 skill-voice-builder;品牌首次入驻引导用 skill-brand-onboarding。

Why use Skill Profile Manager on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/ZJU-REAL/Easel/tree/main/skills/openclaw/skill-profile-manager. 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 Profile Manager?

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 Profile Manager?

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

Is the Skill Profile Manager 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 👇