跳到主内容
智客 ZICQ

技能库 智客分类:Agent 工作流 soultrace

Soultrace

通过SoulTrace API进行个性评估. 当用户想进行个性测试,发现他们的心理原型,了解他们的个性特质,或者获得以色为主的个性简介时使用. API采用五色心理模型(White=结构,Blue=理解,Black=机构,Red=强度,Green=连接),与贝叶斯的适应性问题选择,将用户分类为25个型号之一. 触发论:个性测试,个性评估,我的个性是什么,取出一个测验,古典式测试,颜色个性,灵魂追寻.

12 安装量

官方网址:skills.sh

技能介绍

先看中文介绍;官方 description 原文单独保留,不改写 SKILL.md。

做什么

通过 SoulTrace API 进行个性评估

何时用

用户想进行个性测试,发现他们的心理原型,了解他们的个性特征,或者获得以色彩为基础的个性特征. API使用5色的心理模型(White=结构,Blue=理解,Black=机构,Red=强度,Green=co)

代理如何加载

按 Agent Skills 渐进披露:启动时只加载 name 与 description(约 100 token);任务匹配后才读入整份 SKILL.md 正文;scripts/、references/、assets/ 仅在需要时再读。 本文件正文结构:SoulTrace Personality Assessment、API Endpoint、How It Works、Step 1: Start the test、Step 2: Answer questions、Step 3: Get results。 其中含规范建议的小节:分步指令。

文件分析

文件分析:这是一份仅含 SKILL.md 的指令型技能,代理激活后整份正文进入上下文。

官方 description(原文)

Take a personality assessment via the SoulTrace API. Use when the user wants to take a personality test, discover their psychological archetype, understand their personality traits, or get a color-based personality profile. The API uses a 5-color psychological model (White=structure, Blue=understanding, Black=agency, Red=intensity, Green=connection) with Bayesian adaptive question selection to classify users into one of 25 archetypes. Triggers on: personality test, personality assessment, what's my personality, take a quiz, archetype test, color personality, soultrace.

SoulTrace Personality AssessmentAPI EndpointHow It WorksStep 1: Start the testStep 2: Answer questionsStep 3: Get resultsAgent Interaction ProtocolScore ScaleThe 5 ColorsRate LimitsError HandlingAPI Info

来源分类:skills.sh agent-skill

SKILL.md 与 Agent 调用

官方规范 ↗
name
soultrace
description
Take a personality assessment via the SoulTrace API. Use when the user wants to take a personality test, discover their psychological archetype, understand their personality traits, or get a color-based personality profile. The API uses a 5-color psychological model (White=structure, Blue=understanding, Black=agency, Red=intensity, Green=connection) with Bayesian adaptive question selection to classify users into one of 25 archetypes. Triggers on: personality test, personality assessment, what's my personality, take a quiz, archetype test, color personality, soultrace.
  1. 发现技能客户端向 Agent 提供名称与描述目录。
  2. 匹配与调用用户指定或任务匹配后,载入 SKILL.md 指令。
  3. 按需加载按步骤读取参考文档、使用脚本与素材。

具体调用语法与可用工具以目标 Agent 客户端为准。 查看调用机制说明 ↗

安装这个技能

Skills CLI ↗

先选择目标 Agent 和安装范围,保留技能包的附属文件,安装后检查客户端能否发现该技能。

交给 Agent 安装

复制安装指令给支持 Agent Skills 的代理,确认其中的目标目录与客户端匹配。

把 Agent Skill「soultrace」安装到我的项目:SKILL.md 原文与官方 description 见 https://zicq.com/zh/skills/skl-b53f49be7f4fd559-%E7%81%B5%E9%AD%82.html
请存为 .cursor/skills/soultrace/SKILL.md 或 .claude/skills/soultrace/SKILL.md,frontmatter 的 name 与 description 保持原样,不要改写。

GitHub 完整包 ↗

终端安装 · Skills CLI

需要 Node.js 与 npx。先查看仓库技能列表,确认实际名称。

npx skills add 'https://github.com/soultrace-ai/soultrace-skill' --list

npx skills add 'https://github.com/soultrace-ai/soultrace-skill' --skill 'soultrace'

CLI 会交互选择目标 Agent,默认安装到项目;用户级安装使用 -g。先通过查看命令核对仓库内容,再用 npx skills list 检查已安装技能。

阅读排版

name: soultrace description: "Take a personality assessment via the SoulTrace API. Use when the user wants to take a personality test, discover their psychological archetype, understand their personality traits, or get a color-based personality profile. The API uses a 5-color psychological model (White=structure, Blue=understanding, Black=agency, Red=intensity, Green=connection) with Bayesian adaptive question selection to classify users into one of 25 archetypes. Triggers on: personality test, personality assessment, what's my personality, take a quiz, archetype test, color personality, soultrace."

SoulTrace Personality Assessment

Take an adaptive personality assessment through the soultrace API. Answer 24 questions on a 1-7 Likert scale and receive your personality archetype based on a 5-color psychological model.

API Endpoint

POST https://soultrace.app/api/agent

No authentication required. Rate limited to 100 requests/hour per IP.

How It Works

The API is stateless. You pass all accumulated answers with every request, and the server replays the Bayesian inference to select the next optimal question.

Step 1: Start the test

Send an empty answers array to get the first question:

curl -X POST https://soultrace.app/api/agent \
  -H "Content-Type: application/json" \
  -d '{"answers": []}'

Response:

{
  "status": "in_progress",
  "question": {
    "id": 42,
    "text": "I find deep satisfaction in mastering complex systems."
  },
  "currentDistribution": {
    "white": 0.2,
    "blue": 0.2,
    "black": 0.2,
    "red": 0.2,
    "green": 0.2
  },
  "entropy": 2.322,
  "progress": { "answered": 0, "total": 24 }
}

Step 2: Answer questions

The user answers each question on a scale of 1-7:

  • 1 = Strongly Disagree
  • 4 = Neutral
  • 7 = Strongly Agree

Append the answer and send all answers so far:

curl -X POST https://soultrace.app/api/agent \
  -H "Content-Type: application/json" \
  -d '{"answers": [{"questionId": 42, "score": 6}]}'

Keep accumulating answers. Each response gives the next question.

Step 3: Get results

After 24 answers, the response automatically returns the final result:

{
  "status": "complete",
  "resultId": "abc-123-def",
  "resultUrl": "https://soultrace.app/en/results/abc-123-def",
  "distribution": {
    "white": 0.15,
    "blue": 0.35,
    "black": 0.25,
    "red": 0.10,
    "green": 0.15
  },
  "entropy": 1.89,
  "archetype": {
    "key": "blue-black",
    "name": "Strategist",
    "alignmentScore": 87.3,
    "coreDynamic": "...",
    "strengths": ["..."],
    "weaknesses": ["..."]
  },
  "topMatches": [
    { "key": "blue-black", "name": "Strategist", "alignmentScore": 87.3 },
    { "key": "blue", "name": "Rationalist", "alignmentScore": 82.1 },
    { "key": "black-blue", "name": "Operator", "alignmentScore": 78.5 }
  ],
  "shadowColors": [
    { "color": "red", "score": 0.10 },
    { "color": "green", "score": 0.15 }
  ],
  "progress": { "answered": 24, "total": 24 }
}

Agent Interaction Protocol

When a user asks to take the personality test:

  1. Start by calling the API with {"answers": []}.
  2. Present each question to the user clearly. Tell them to answer 1-7 (1=Strongly Disagree, 4=Neutral, 7=Strongly Agree).
  3. Collect the user's numeric answer (1-7). If they give a non-numeric or descriptive answer, map it to the scale:
    • "strongly disagree" / "not at all" → 1
    • "disagree" / "not really" → 2
    • "slightly disagree" → 3
    • "neutral" / "maybe" / "sometimes" → 4
    • "slightly agree" → 5
    • "agree" / "yes" → 6
    • "strongly agree" / "absolutely" → 7
  4. Accumulate answers and send ALL previous answers plus the new one each time.
  5. After all 24 questions, present the results with:
    • Their archetype name and alignment score
    • Their color distribution (show as percentages)
    • Their top 3 archetype matches
    • The link to their full results page
  6. Never skip questions or auto-answer on behalf of the user.

Score Scale

| Score | Meaning | |-------|---------| | 1 | Strongly Disagree | | 2 | Disagree | | 3 | Slightly Disagree | | 4 | Neutral | | 5 | Slightly Agree | | 6 | Agree | | 7 | Strongly Agree |

The 5 Colors

| Color | Drive | Essence | |-------|-------|---------| | White | Structure, fairness | Order, responsibility | | Blue | Understanding, mastery | Curiosity, precision | | Black | Agency, achievement | Ambition, strategy | | Red | Intensity, expression | Passion, honesty | | Green | Connection, growth | Belonging, patience |

Rate Limits

  • 100 requests per hour per IP
  • Each test requires 25 requests (1 start + 24 answers)
  • Maximum ~4 complete tests per hour

Error Handling

| Status | Meaning | |--------|---------| | 400 | Invalid request body or answers format | | 429 | Rate limit exceeded (check Retry-After header) | | 500 | Server error |

API Info

GET https://soultrace.app/api/agent

Returns API metadata (version, question count, score range).

相关技能

Agent 工作流

Skill Creator

创造有效技能指南。 当用户想创造出新的技能(或更新现有的技能),以专业知识,工作流程,或工具集成来扩展克洛德的能力时,应该使用这种技能.

Agent 工作流

Clawdhub

使用ClawdHub CLI搜索,安装,更新并发布从taladhub.com的代理技能. 需要获取苍蝇上的新技能时使用,将安装的技能同步到最新版本或特定版本,或者发布 npm-instainddhub CLI 的新/更新的技能文件夹.

Agent 工作流

Agent Team Orchestration

管弦乐团多代理团队,任务设定周期,交接协议,审查工作流程. 使用时间: (1)建立2+特派员队伍,具有不同专业,(2)确定任务路线和生命周期(收录框_ spec_建设_审查_完成),(3)在特派员之间制定交接协议,(4)建立审查和质量关口,(5)管理特派员之间的交流和文物共享.

Agent 工作流

Superpowers

Spec-first,TDD,子代理驱动的软件开发工作流程. 当:(1)构建任何新功能或应用——触发脑暴_计划_子代理执行回路,(2)调试出一个bug或测试失败——触发系统性的根起过程,(3)用户说"让我们构建","帮助我计划","我想添加X",或"这个被打破",(4)完成一个功…