- name
SKILL.md
技能檔案保留在發布者的儲存庫中。
在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add trailofbits/skills --skill interpreting-culture-index -a cursor -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add trailofbits/skills --skill interpreting-culture-index -a claude-code -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add trailofbits/skills --skill interpreting-culture-index -a codex -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add trailofbits/skills --skill interpreting-culture-index -a grok -y在 Grok Bot 聊天中傳送複製的訊息。Bot 會從 GitHub 取得這個 SKILL.md,並加入你所有 Bot 共用的技能中。
Install this skill: https://github.com/trailofbits/skills/tree/HEAD/plugins/culture-index/skills/interpreting-culture-index來自發布者
<essential_principles>
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.
Large differences between graphs indicate behavior modification, which drains energy and causes burnout if sustained 3-6+ months.
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:
Only these two traits break the "no absolute comparison" rule.
</essential_principles>
<input_formats>
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:
uv run --no-project {baseDir}/scripts/extract_pdf.py --verify /path/to/file.pdf [output.json]
If uv is not installed: Stop and instruct user to install it (brew install uv or curl -LsSf https://astral.sh/uv/install.sh | sh). 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.
</input_formats>
Step 0: Do you have JSON or PDF?
.json file with matching name--verify flag
uv run --no-project {baseDir}/scripts/extract_pdf.py --verify /path/to/file.pdf [output.json]
Step 1: What data do you have?
Step 2: What would you like to do?
Profile Analysis:
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.
After reading the workflow, follow it exactly.
<verification_loop>
After every interpretation, verify:
Report to user:
</verification_loop>
<reference_index>
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, archetypesArchetype 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</reference_index>
<workflows_index>
Workflows (in workflows/):
</workflows_index>
<quick_reference>
Trait Colors:
Energy Utilization Formula:
Utilization = (Job EU / Survey EU) × 100
70-130% = Healthy
>130% = STRESS (burnout risk)
<70% = FRUSTRATION (flight risk)
Gas/Brake/Glue:
Score Precision:
</quick_reference>
<success_criteria>
A well-interpreted Culture Index profile:
</success_criteria>
Interprets Culture Index (CI) surveys, behavioral profiles, and personality assessment data. Supports individual profile interpretation, team composition analysis (gas/brake/glue), burnout detection,
---name: interpreting-culture-indexdescription: Interprets Culture Index (CI) surveys, behavioral profiles, and personality assessment data. Supports…---# plugins/culture-index/skills/interpreting-culture-index/SKILL.md總覽
Interprets Culture Index (CI) surveys, behavioral profiles, and personality assessment data. Supports individual profile interpretation, team composition analysis (gas/brake/glue), burnout detection, profile comparison, hiring profiles, manager coaching, interview transcript analysis for trait prediction, candidate debrief, onboarding planning, and conflict mediation. Accepts extracted JSON or PDF input via OpenCV extraction script. Use when the user shares a Culture Index PDF or JSON profile, asks what someone's CI traits mean, compares Culture Index profiles across a team or against a hiring profile, or asks about burnout risk from Survey-versus-Job gaps.
常見問題
從發布者下載 plugins/culture-index/skills/interpreting-culture-index/SKILL.md,或複製路徑後開啟儲存庫。PlugMCP 只收錄這項技能,不代管檔案。
發布者將它存放在 https://github.com/trailofbits/skills。
Claude、Cursor、Codex 和 Grok Build 可以讀取你從發布者儲存庫加入的 SKILL.md。在聊天中傳送技能的 GitHub 資料夾連結,Grok Bot 就會安裝它。