interpreting-culture-index
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
Chinese<essential_principles>
Culture Index measures behavioral traits, not intelligence or skills. There is no "good" or "bad" profile.
<principle name="never-compare-absolutes">
**Never compare absolute trait values between people.**
The 0-10 scale is just a ruler. What matters is distance from the red arrow (population mean at 50th percentile). The arrow position varies between surveys based on EU.
Why the arrow moves: Higher EU scores cause the arrow to plot further right; lower EU causes it to plot further left. This does not affect validity—we always measure distance from wherever the arrow lands.
Wrong: "Dan has higher autonomy than Jim because his A is 8 vs 5"
Right: "Dan is +3 centiles from his arrow; Jim is +1 from his arrow"
Always ask: Where is the arrow, and how far is the dot from it?
</principle>
<principle name="survey-vs-job">
**Survey = who you ARE. Job = who you're TRYING TO BE.**
"You can't send a duck to Eagle school." Traits are hardwired—you can only modify behaviors temporarily, at the cost of energy.
- Top graph (Survey Traits): Hardwired by age 12-16. Does not change. Writing with your dominant hand.
- Bottom graph (Job Behaviors): Adaptive behavior at work. Can change. Writing with your non-dominant hand.
Large differences between graphs indicate behavior modification, which drains energy and causes burnout if sustained 3-6+ months.
</principle>
<principle name="distance-interpretation">
**Distance from arrow determines trait strength.**
| Distance | Label | Percentile | Interpretation |
|---|---|---|---|
| On arrow | Normative | 50th | Flexible, situational |
| ±1 centile | Tendency | ~67th | Easier to modify |
| ±2 centiles | Pronounced | ~84th | Noticeable difference |
| ±4+ centiles | Extreme | ~98th | Hardwired, compulsive, predictable |
Key insight: Every 2 centiles of distance = 1 standard deviation.
Extreme traits drive extreme results but are harder to modify and less relatable to average people.
</principle>
<principle name="l-and-i-exception">
**L (Logic) and I (Ingenuity) use absolute values.**
Unlike A, B, C, D, you CAN compare L and I scores directly between people:
- Logic 8 means "High Logic" regardless of arrow position
- Ingenuity 2 means "Low Ingenuity" for anyone
Only these two traits break the "no absolute comparison" rule.
</principle>
</essential_principles>
<input_formats>
JSON (Use if available)
If JSON data is already extracted, use it directly:
python
import json
with open("person_name.json") as f:
profile = json.load(f)JSON format:
json
{
"name": "Person Name",
"archetype": "Architect",
"survey": {
"eu": 21,
"arrow": 2.3,
"a": [5, 2.7],
"b": [0, -2.3],
"c": [1, -1.3],
"d": [3, 0.7],
"logic": [5, null],
"ingenuity": [2, null]
},
"job": { "..." : "same structure as survey" },
"analysis": {
"energy_utilization": 148,
"status": "stress"
}
}Note: Trait values are tuples. Use the relative value for interpretation.
[absolute, relative_to_arrow]Check same directory as PDF for matching file, or ask user if they have extracted JSON.
.jsonPDF Input (MUST EXTRACT FIRST)
⚠️ NEVER use visual estimation for trait values. Visual estimation has 20-30% error rate.
When given a PDF:
- Check if JSON already exists (same directory as PDF, or ask user)
- If not, run extraction with verification:
bash
uv run {baseDir}/scripts/extract_pdf.py --verify /path/to/file.pdf [output.json] - Visually confirm the verification summary matches the PDF
- Use the extracted JSON for interpretation
If uv is not installed: Stop and instruct user to install it ( or ). Do NOT fall back to vision.
brew install uvpip install uvPDF Vision (Reference Only)
Vision may be used ONLY to verify extracted values look reasonable, NOT to extract trait scores.
</input_formats>
<intake>
Step 0: Do you have JSON or PDF?
- If JSON provided or found: Use it directly (skip extraction)
- Check same directory as PDF for file with matching name
.json - Check if user provided JSON path
- Check same directory as PDF for
- If only PDF: Run extraction script with flag
--verifybashuv run {baseDir}/scripts/extract_pdf.py --verify /path/to/file.pdf [output.json] - If extraction fails: Report error, do NOT fall back to vision
Step 1: What data do you have?
- CI Survey JSON → Proceed to Step 2
- CI Survey PDF → Extract first (Step 0), then proceed to Step 2
- Interview transcript only → Go to option 8 (predict traits from interview)
- No data yet → "Please provide Culture Index profile (PDF or JSON) or interview transcript"
Step 2: What would you like to do?
Profile Analysis:
- Interpret an individual profile - Understand one person's traits, strengths, and challenges
- Analyze team composition - Assess gas/brake/glue balance, identify gaps
- Detect burnout signals - Compare Survey vs Job, flag stress/frustration
- Compare multiple profiles - Understand compatibility, collaboration dynamics
- Get motivator recommendations - Learn how to engage and retain someone
Hiring & Candidates:
6. Define hiring profile - Determine ideal CI traits for a role
7. Coach manager on direct report - Adjust management style based on both profiles
8. Predict traits from interview - Analyze interview transcript to estimate CI traits
9. Interview debrief - Assess candidate fit based on predicted traits
Team Development:
10. Plan onboarding - Design first 90 days based on new hire and team profiles
11. Mediate conflict - Understand friction between two people using their profiles
Provide the profile data (JSON or PDF) and select an option, or describe what you need.
</intake>
<routing>
| Response | Workflow |
|---|---|
| "extract", "parse pdf", "convert pdf", "get json from pdf" | |
| 1, "individual", "interpret", "understand", "analyze one", "single profile" | |
| 2, "team", "composition", "gaps", "balance", "gas brake glue" | |
| 3, "burnout", "stress", "frustration", "survey vs job", "energy", "flight risk" | |
| 4, "compare", "compatibility", "collaboration", "multiple", "two profiles" | |
| 5, "motivate", "engage", "retain", "communicate" | Read |
| 6, "hire", "hiring profile", "role profile", "recruit", "what profile for" | |
| 7, "manage", "coach", "1:1", "direct report", "manager" | |
| 8, "transcript", "interview", "predict traits", "guess", "estimate", "recording" | |
| 9, "debrief", "should we hire", "candidate fit", "proceed", "offer" | |
| 10, "onboard", "new hire", "integrate", "starting", "first 90 days" | |
| 11, "conflict", "friction", "mediate", "not working together", "clash" | |
| "conversation starters", "how to talk to", "engage with" | Read |
After reading the workflow, follow it exactly.
</routing>
<verification_loop>
After every interpretation, verify:
- Did you use relative positions? Never stated "A is 8" without context
- Did you reference the arrow? All trait interpretations relative to arrow
- Did you compare Survey vs Job? Identified any behavior modification
- Did you avoid value judgments? No traits called "good" or "bad"
- Did you check EU? Energy utilization calculated if both graphs present
Report to user:
- "Interpretation complete"
- Key findings (2-3 bullet points)
- Recommended actions
</verification_loop>
<reference_index>
Domain Knowledge (in ):
references/Primary Traits:
- - A (Autonomy), B (Social), C (Pace), D (Conformity)
primary-traits.md
Secondary Traits:
- - EU (Energy Units), L (Logic), I (Ingenuity)
secondary-traits.md
Patterns:
- - Behavioral patterns, trait combinations, archetypes
patterns-archetypes.md
Application:
- - How to motivate each trait type
motivators.md - - Gas, brake, glue framework
team-composition.md - - Common interpretation mistakes
anti-patterns.md - - How to engage each pattern and trait type
conversation-starters.md - - Signals for predicting traits from interviews
interview-trait-signals.md
</reference_index>
<workflows_index>
Workflows (in ):
workflows/| File | Purpose |
|---|---|
| Extract profile data from Culture Index PDF to JSON format |
| Analyze single profile, identify archetype, summarize strengths/challenges |
| Assess team balance (gas/brake/glue), identify gaps, recommend hires |
| Compare Survey vs Job, calculate EU utilization, flag risk signals |
| Compare multiple profiles, assess compatibility, collaboration dynamics |
| Define ideal CI traits for a role, identify acceptable patterns and red flags |
| Help managers adjust their style for specific direct reports |
| Analyze interview transcripts to predict CI traits before survey |
| Assess candidate fit using predicted traits from transcript analysis |
| Design first 90 days based on new hire profile and team composition |
| Understand and address friction between team members using their profiles |
</workflows_index>
<quick_reference>
Trait Colors:
| Trait | Color | Measures |
|---|---|---|
| A | Maroon | Autonomy, initiative, self-confidence |
| B | Yellow | Social ability, need for interaction |
| C | Blue | Pace/Patience, urgency level |
| D | Green | Conformity, attention to detail |
| L | Purple | Logic, emotional processing |
| I | Cyan | Ingenuity, inventiveness |
Energy Utilization Formula:
Utilization = (Job EU / Survey EU) × 100
70-130% = Healthy
>130% = STRESS (burnout risk)
<70% = FRUSTRATION (flight risk)Gas/Brake/Glue:
| Role | Trait | Function |
|---|---|---|
| Gas | High A | Growth, risk-taking, driving results |
| Brake | High D | Quality control, risk aversion, finishing |
| Glue | High B | Relationships, morale, culture |
Score Precision:
| Value | Precision | Example |
|---|---|---|
| Traits (A,B,C,D,L,I) | Integer 0-10 | 0, 1, 2, ... 10 |
| Arrow position | Tenths | 0.4, 2.2, 3.8 |
| Energy Units (EU) | Integer | 11, 31, 45 |
</quick_reference>
<success_criteria>
A well-interpreted Culture Index profile:
- Uses relative positions (distance from arrow), never absolute values alone
- Identifies the archetype/pattern correctly
- Highlights 2-3 key strengths based on leading traits
- Notes 2-3 challenges or development areas
- Compares Survey vs Job if both are available
- Provides actionable recommendations
- Avoids value judgments ("good"/"bad")
- Acknowledges Culture Index is one data point, not a complete picture
</success_criteria>
<essential_principles>
Culture Index衡量行为特质,而非智力或技能。不存在“好”或“坏”的档案。
<principle name="never-compare-absolutes">
**切勿在个体间比较特质的绝对数值。**
0-10的评分只是一个标尺。重要的是与红色箭头的距离(箭头代表处于第50百分位的人群均值)。不同调研中箭头的位置会根据EU(能量单位)有所变化。
**箭头移动的原因:**EU分数越高,箭头位置越靠右;EU分数越低,箭头位置越靠左。这不会影响评估有效性——我们始终以箭头所在位置为基准衡量距离。
错误示例:“Dan的自主性比Jim高,因为他的A值是8而Jim是5”
正确示例:“Dan的A值比他的箭头高3个百分位;Jim的A值比他的箭头高1个百分位”
始终要问:箭头在哪里?数据点与箭头的距离是多少?
</principle>
<principle name="survey-vs-job">
**调研结果=真实的你。工作表现=你试图成为的样子。**
**“你不能把鸭子送去老鹰学校。”**特质是与生俱来的——你只能暂时调整行为,但会消耗精力。
- 上方图表(调研特质):12-16岁时就已固定,不会改变。就像用惯用手写字。
- 下方图表(工作行为):工作中的适应性行为,可以改变。就像用非惯用手写字。
两张图表的差异过大意味着行为调整,如果持续3-6个月以上会消耗精力并导致倦怠。
</principle>
<principle name="distance-interpretation">
**与箭头的距离决定特质的强度。**
| 距离 | 标签 | 百分位 | 解读 |
|---|---|---|---|
| 与箭头重合 | 常规水平 | 第50位 | 灵活,随情境变化 |
| ±1个百分位 | 倾向 | ~第67位 | 较易调整 |
| ±2个百分位 | 明显倾向 | ~第84位 | 差异显著 |
| ±4+个百分位 | 极端倾向 | ~第98位 | 与生俱来,具有强迫性,可预测 |
**核心要点:**每2个百分位的距离=1个标准差。
极端特质会带来极端结果,但更难调整,也与普通人的契合度更低。
</principle>
<principle name="l-and-i-exception">
**L(逻辑)和I(创造力)使用绝对数值。**
与A、B、C、D不同,你可以直接在个体间比较L和I的分数:
- 逻辑8分意味着“高逻辑能力”,无论箭头位置如何
- 创造力2分意味着“低创造力”,对任何人都是如此
只有这两个特质不遵循“不比较绝对数值”的规则。
</principle>
</essential_principles>
<input_formats>
JSON格式(优先使用)
如果已有提取好的JSON数据,可直接使用:
python
import json
with open("person_name.json") as f:
profile = json.load(f)JSON格式:
json
{
"name": "Person Name",
"archetype": "Architect",
"survey": {
"eu": 21,
"arrow": 2.3,
"a": [5, 2.7],
"b": [0, -2.3],
"c": [1, -1.3],
"d": [3, 0.7],
"logic": [5, null],
"ingenuity": [2, null]
},
"job": { "..." : "same structure as survey" },
"analysis": {
"energy_utilization": 148,
"status": "stress"
}
}注意:特质值为元组。解读时请使用相对数值。
[absolute, relative_to_arrow]检查PDF所在目录是否有对应的文件,或询问用户是否有提取好的JSON。
.jsonPDF输入(必须先提取数据)
⚠️ **切勿通过视觉估算特质数值。**视觉估算的误差率为20-30%。
收到PDF时:
- 检查是否已存在JSON文件(与PDF同目录,或询问用户)
- 如果没有,运行提取脚本并验证:
bash
uv run {baseDir}/scripts/extract_pdf.py --verify /path/to/file.pdf [output.json] - 视觉确认验证摘要与PDF内容一致
- 使用提取得到的JSON进行解读
**如果未安装uv:**停止操作并指导用户安装(或)。切勿使用视觉估算替代。
brew install uvpip install uvPDF视觉识别(仅作参考)
视觉识别仅可用于验证提取的数值是否合理,不可用于提取特质分数。
</input_formats>
<intake>
步骤0:你有JSON还是PDF文件?
- **如果提供或找到JSON:**直接使用(跳过提取步骤)
- 检查PDF所在目录是否有同名的文件
.json - 检查用户是否提供了JSON路径
- 检查PDF所在目录是否有同名的
- **如果只有PDF:**运行带参数的提取脚本
--verifybashuv run {baseDir}/scripts/extract_pdf.py --verify /path/to/file.pdf [output.json] - **如果提取失败:**报告错误,切勿使用视觉估算替代
步骤1:你拥有哪些数据?
- CI调研JSON → 进入步骤2
- CI调研PDF → 先完成步骤0的提取,再进入步骤2
- 仅提供面试 transcript → 进入选项8(从面试中预测特质)
- 暂无数据 → “请提供Culture Index档案(PDF或JSON格式)或面试 transcript”
步骤2:你需要进行什么操作?
档案分析:
- 解读个人档案 - 了解个人特质、优势与挑战
- 分析团队构成 - 评估动力/制动/凝聚的平衡,识别缺口
- 检测倦怠信号 - 对比调研结果与工作行为,标记压力/挫败感
- 对比多个档案 - 了解适配性与协作动态
- 获取激励建议 - 学习如何调动和留住员工
招聘与候选人:
6. 制定招聘档案 - 确定岗位的理想CI特质
7. 辅导管理者对接下属 - 根据双方档案调整管理风格
8. 从面试中预测特质 - 分析面试 transcript 估算CI特质
9. 候选人反馈 - 根据预测的特质评估候选人适配度
团队发展:
10. 规划入职流程 - 根据新员工与团队档案设计前90天计划
11. 调解冲突 - 通过档案理解两人之间的摩擦
请提供档案数据(JSON或PDF)并选择一个选项,或描述你的需求。
</intake>
<routing>
| 响应 | 工作流 |
|---|---|
| "extract", "parse pdf", "convert pdf", "get json from pdf" | |
| 1, "individual", "interpret", "understand", "analyze one", "single profile" | |
| 2, "team", "composition", "gaps", "balance", "gas brake glue" | |
| 3, "burnout", "stress", "frustration", "survey vs job", "energy", "flight risk" | |
| 4, "compare", "compatibility", "collaboration", "multiple", "two profiles" | |
| 5, "motivate", "engage", "retain", "communicate" | 直接阅读 |
| 6, "hire", "hiring profile", "role profile", "recruit", "what profile for" | |
| 7, "manage", "coach", "1:1", "direct report", "manager" | |
| 8, "transcript", "interview", "predict traits", "guess", "estimate", "recording" | |
| 9, "debrief", "should we hire", "candidate fit", "proceed", "offer" | |
| 10, "onboard", "new hire", "integrate", "starting", "first 90 days" | |
| 11, "conflict", "friction", "mediate", "not working together", "clash" | |
| "conversation starters", "how to talk to", "engage with" | 直接阅读 |
阅读工作流后,请严格按照其执行。
</routing>
<verification_loop>
每次解读后,需验证:
- 是否使用了相对位置? 切勿在未说明上下文的情况下直接说“A值为8”
- 是否参考了箭头? 所有特质解读均以箭头为基准
- 是否对比了调研结果与工作行为? 识别出所有行为调整
- 是否避免了价值判断? 切勿将特质称为“好”或“坏”
- 是否检查了EU? 若两张图表均存在则计算能量利用率
向用户报告:
- “解读完成”
- 关键发现(2-3个要点)
- 建议行动
</verification_loop>
<reference_index>
领域知识(位于目录下):
references/核心特质:
- - A(自主性)、B(社交性)、C(节奏/耐心)、D(合规性)
primary-traits.md
次要特质:
- - EU(能量单位)、L(逻辑)、I(创造力)
secondary-traits.md
模式:
- - 行为模式、特质组合、典型类型
patterns-archetypes.md
应用:
- - 如何激励不同特质类型的员工
motivators.md - - 动力/制动/凝聚框架
team-composition.md - - 常见的解读错误
anti-patterns.md - - 如何与不同模式和特质类型的员工沟通
conversation-starters.md - - 从面试中预测特质的信号
interview-trait-signals.md
</reference_index>
<workflows_index>
工作流(位于目录下):
workflows/| 文件 | 用途 |
|---|---|
| 将Culture Index PDF中的档案数据提取为JSON格式 |
| 分析单个档案,识别典型类型,总结优势与挑战 |
| 评估团队平衡(动力/制动/凝聚),识别缺口,推荐招聘方向 |
| 对比调研结果与工作行为,计算EU利用率,标记风险信号 |
| 对比多个档案,评估适配性与协作动态 |
| 确定岗位的理想CI特质,识别可接受的模式与红色预警 |
| 帮助管理者调整风格以适配特定下属 |
| 分析面试 transcript,在调研前预测CI特质 |
| 通过 transcript 分析得到的预测特质评估候选人适配度 |
| 根据新员工档案与团队构成设计前90天入职计划 |
| 通过档案理解并解决团队成员间的摩擦 |
</workflows_index>
<quick_reference>
特质颜色:
| 特质 | 颜色 | 衡量维度 |
|---|---|---|
| A | 栗色 | 自主性、主动性、自信心 |
| B | 黄色 | 社交能力、互动需求 |
| C | 蓝色 | 节奏/耐心、紧迫感 |
| D | 绿色 | 合规性、细节关注度 |
| L | 紫色 | 逻辑、情绪处理 |
| I | 青色 | 创造力、创新性 |
能量利用率公式:
利用率 = (工作EU / 调研EU) × 100
70-130% = 健康状态
>130% = 压力状态(存在倦怠风险)
<70% = 挫败状态(存在离职风险)动力/制动/凝聚:
| 角色 | 特质 | 功能 |
|---|---|---|
| 动力 | 高A值 | 增长、承担风险、推动结果 |
| 制动 | 高D值 | 质量控制、规避风险、完成任务 |
| 凝聚 | 高B值 | 人际关系、士气、文化建设 |
评分精度:
| 数值 | 精度 | 示例 |
|---|---|---|
| 特质(A,B,C,D,L,I) | 整数0-10 | 0, 1, 2, ... 10 |
| 箭头位置 | 小数点后一位 | 0.4, 2.2, 3.8 |
| 能量单位(EU) | 整数 | 11, 31, 45 |
</quick_reference>
<success_criteria>
一份优质的Culture Index档案解读需满足:
- 使用相对位置(与箭头的距离),绝不单独使用绝对数值
- 正确识别典型类型/模式
- 基于主导特质突出2-3个核心优势
- 指出2-3个挑战或发展方向
- 若同时存在调研与工作数据则进行对比
- 提供可执行的建议
- 避免价值判断(“好”/“坏”)
- 承认Culture Index只是一个数据点,并非完整的人员画像
</success_criteria>