运维安装
- 作者仓库星标 5,723
- 叉子 499
- 作者更新于 2026年6月15日 16:05
- 作者仓库 skills
- 领域
- 数据
- 兼容 Agent
-
- Claude Code
- Cursor
- Cline
- Codex
- Windsurf
- Gemini CLI
- +20
- 信任分
- 88 / 100 · 社区维护
- 作者 / 版本 / 许可
- @trailofbits · 未声明 license
- Token 消耗评级
- 低消耗
- 接入复杂程度
- 需简单配置
- 是否需要外部 API Key
- 不需要
- 兼容的系统
- 未声明（默认跨平台）
- 底层运行要求
- Python
- 文件与系统权限
-
- 只读
- 允许写入 / 修改
- 网络行为
- 仅限本地
- 安装命令数
- 26 条
档案由构建时根据 SKILL.md 与安装命令自动衍生，可能与作者实际意图存在差异。
需要注意： 未限定 allowed-tools，默认拥有全部工具权限。
---
name: interpreting-culture-index
description: Interprets Culture Index (CI) surveys, behavioral profiles, and personality assessment data. Sup…
category: 数据
runtime: Python
---
# interpreting-culture-index 输出预览
## PART A: 任务判断
- 适用问题：表格、CSV、数据集、指标或分析流程。
- 输入要求：目标材料、限制条件、期望输出和验收方式。
- 证据边界：围绕“When to Use / When NOT to Use”读取原文规则，不把推断写成作者承诺。
## PART B: 执行结果
- **01** 任务判断：确认你的需求是否属于表格、CSV、数据集、指标或分析流程，并标出输入、限制和预期结果。
- **02** 执行计划：优先按“When to Use / When NOT to Use”拆成步骤，说明每一步会读取什么、修改什么、产出什么。
- **03** 交付结果：给出可复制的命令、文件改动、检查清单或内容草稿，并说明如何继续迭代。
- **04** 风险边界：结合 读取文件、写入/修改文件、主要在本地完成、通常不需要额外 API Key 给出执行前确认项。
## Running Rules
- 读取文件、写入/修改文件；主要在本地完成；通常不需要额外 API Key。
- 先小样例验证，再放大到真实任务。
- 交付时同时给结果、检查口径和下一步迭代建议。原文出现了 `/path` 这类斜杠命令；如果你的 Agent 支持命令触发，优先用命令开场，再补充目标和边界。
告诉 Agent 目标文件或材料、期望结果、不可改范围、是否允许联网或执行命令。本 Skill 的权限画像是：读取文件、写入/修改文件。
先用一个小任务确认它会围绕“When to Use / When NOT to Use”工作；涉及文件或命令时，先看 diff、日志、预览或测试结果。
检查最终产物是否包含明确结果、必要证据和下一步动作；如果输出泛泛而谈，就补充输入、边界和验收标准后重跑。
---
name: interpreting-culture-index
description: Interprets Culture Index (CI) surveys, behavioral profiles, and personality assessment data. Sup…
category: 数据
source: trailofbits/skills
---
# interpreting-culture-index
## 什么时候使用
- interpreting-culture-index 是数据方向的技能，让 Agent 处理结构化文件（Excel / CSV / 表格） 适合处理表格、CSV、指标、数据集、分析和可视化报告，核心价值是把输入、判断、执行、验证和交付边…
- 面向表格、CSV、数据集、指标或分析流程，优先处理能明确输入、步骤和验收标准的工作。
## 需要提供什么
- 目标材料、目录范围、期望结果和不可改动内容。
- 是否允许联网、执行命令、读写文件或调用外部服务。
## 执行规则
- 围绕「When to Use / When NOT to Use」组织步骤，不把推断写成作者事实。
- 读取文件、写入/修改文件；主要在本地完成；通常不需要额外 API Key。
- 先跑小样例，确认结果可检查后再扩大任务范围。
## 输出要求
- 给出最终产物、关键证据、验证方式和下一步动作。
- 信息不足时标记 unknown，不编造命令、平台或依赖。作者原文负责流程事实；仓库文件负责来源和命令；流狐只补充适用场景、限制和质量判断。
skill "interpreting-culture-index" {
输入层 -> 用户目标 + 目标文件 + 禁止范围 + 验收标准
上下文层 -> When to Use / When NOT to Use
规则层 -> SKILL.md 触发条件 / 执行顺序 / 输出格式
运行层 -> Python | 读取文件、写入/修改文件 | 主要在本地完成
安全层 -> 通常不需要额外 API Key + 小任务验证 + diff / 日志复核
输出层 -> 可复制结果 + 检查清单 + 下一步迭代
}Culture Index measures behavioral traits, not intelligence or skills. There is no "good" or "bad" profile.
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?
"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.
| 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.
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.
When to Use
- Interpreting Culture Index survey results (individual or team)
- Analyzing CI profiles from PDF or JSON data
- Assessing team composition using Gas/Brake/Glue framework
- Detecting burnout risk by comparing Survey vs Job graphs
- Defining hiring profiles based on CI trait patterns
- Coaching managers on how to work with specific CI profiles
- Predicting CI traits from interview transcripts
- Mediating team conflict using CI profile data
When NOT to Use
- For non-CI behavioral assessments (DISC, Myers-Briggs, StrengthsFinder, Predictive Index, Enneagram)
- For clinical psychological assessments or diagnoses
- As the sole basis for hiring/firing decisions — CI is one data point among many
JSON (Use if available)
If JSON data is already extracted, use it directly:
import json
with open("person_name.json") as f:
profile = json.load(f)JSON format:
{
"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 [absolute, relative_to_arrow] tuples. Use the relative value for interpretation.
Check same directory as PDF for matching .json file, or ask user if they have extracted JSON.
PDF 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:
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 (brew install uv or pip install uv). Do NOT fall back to vision.
PDF Vision (Reference Only)
Vision may be used ONLY to verify extracted values look reasonable, NOT to extract trait scores.
Step 0: Do you have JSON or PDF?
- If JSON provided or found: Use it directly (skip extraction)
- Check same directory as PDF for
.jsonfile with matching name - Check if user provided JSON path
- Check same directory as PDF for
- If only PDF: Run extraction script with
--verifyflaguv 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.
| Response | Workflow |
|---|---|
| "extract", "parse pdf", "convert pdf", "get json from pdf" | workflows/extract-from-pdf.md |
| 1, "individual", "interpret", "understand", "analyze one", "single profile" | workflows/interpret-individual.md |
| 2, "team", "composition", "gaps", "balance", "gas brake glue" | workflows/analyze-team.md |
| 3, "burnout", "stress", "frustration", "survey vs job", "energy", "flight risk" | workflows/detect-burnout.md |
| 4, "compare", "compatibility", "collaboration", "multiple", "two profiles" | workflows/compare-profiles.md |
| 5, "motivate", "engage", "retain", "communicate" | Read references/motivators.md directly |
| 6, "hire", "hiring profile", "role profile", "recruit", "what profile for" | workflows/define-hiring-profile.md |
| 7, "manage", "coach", "1:1", "direct report", "manager" | workflows/coach-manager.md |
| 8, "transcript", "interview", "predict traits", "guess", "estimate", "recording" | workflows/predict-from-interview.md |
| 9, "debrief", "should we hire", "candidate fit", "proceed", "offer" | workflows/interview-debrief.md |
| 10, "onboard", "new hire", "integrate", "starting", "first 90 days" | workflows/plan-onboarding.md |
| 11, "conflict", "friction", "mediate", "not working together", "clash" | workflows/mediate-conflict.md |
| "conversation starters", "how to talk to", "engage with" | Read references/conversation-starters.md directly |
After reading the workflow, follow it exactly.
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
Domain Knowledge (in references/):
Primary Traits:
primary-traits.md- A (Autonomy), B (Social), C (Pace), D (Conformity)
Secondary Traits:
secondary-traits.md- EU (Energy Units), L (Logic), I (Ingenuity)
Patterns:
patterns-archetypes.md- Behavioral patterns, trait combinations, archetypes
Archetype Deep Profiles (archetype-*.md):
archetype-administrator.md- The Administrator (High A, High B, Low C, Mid D)archetype-coordinator.md- The Coordinator (Low A, High B, Mid C, Low D)archetype-craftsman.md- The Craftsman (Low A, Low B, High C, High D)archetype-daredevil.md- The Daredevil (High A, Low B, Low C, Low D)archetype-debater.md- The Debater (Mid A, Mid-High B, Low C, High D)archetype-facilitator.md- The Facilitator (Low A, Mid B, Mid C, Low D)archetype-influencer.md- The Influencer (Low A, High B, Low C, Low D)archetype-operator.md- The Operator (Low A, Low B, High C, Mid-High D)archetype-persuader.md- The Persuader (High A, High B, Low C, Low D)archetype-philosopher.md- The Philosopher (Low A, Low B, High C, Low D)archetype-rainmaker.md- The Rainmaker (High A, High B, Low C, Low D)archetype-scholar.md- The Scholar (High A, Low B, Low C, High D)archetype-socializer.md- The Socializer (Low A, High B, Low C, Low D)archetype-specialist.md- The Specialist (Low A, Low B, High C, Mid D)archetype-technical-expert.md- The Technical Expert (Low A, Low B, High C, Low D)archetype-traditionalist.md- The Traditionalist (Low A, Low B, High C, High D)archetype-trailblazer.md- The Trailblazer (High A, Mid B, Mid C, Low D)
Application:
motivators.md- How to motivate each trait typeteam-composition.md- Gas, brake, glue frameworkanti-patterns.md- Common interpretation mistakesconversation-starters.md- How to engage each pattern and trait typeinterview-trait-signals.md- Signals for predicting traits from interviews
Workflows (in workflows/):
| File | Purpose |
|---|---|
extract-from-pdf.md |
Extract profile data from Culture Index PDF to JSON format |
interpret-individual.md |
Analyze single profile, identify archetype, summarize strengths/challenges |
analyze-team.md |
Assess team balance (gas/brake/glue), identify gaps, recommend hires |
detect-burnout.md |
Compare Survey vs Job, calculate EU utilization, flag risk signals |
compare-profiles.md |
Compare multiple profiles, assess compatibility, collaboration dynamics |
define-hiring-profile.md |
Define ideal CI traits for a role, identify acceptable patterns and red flags |
coach-manager.md |
Help managers adjust their style for specific direct reports |
predict-from-interview.md |
Analyze interview transcripts to predict CI traits before survey |
interview-debrief.md |
Assess candidate fit using predicted traits from transcript analysis |
plan-onboarding.md |
Design first 90 days based on new hire profile and team composition |
mediate-conflict.md |
Understand and address friction between team members using their profiles |
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 |
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
先判断是否适合
作者设计意图
作者的方法与取舍
边界和复核