interpreting-culture-index

Files (54)

• SKILL.md
• openai.yaml · agents/
• trail-of-bits-mark.svg · assets/
• anti-patterns.md · references/
• archetype-administrator.md · references/
• archetype-coordinator.md · references/
• archetype-craftsman.md · references/
• archetype-daredevil.md · references/
• archetype-debater.md · references/
• archetype-facilitator.md · references/
• archetype-influencer.md · references/
• archetype-operator.md · references/
• archetype-persuader.md · references/
• archetype-philosopher.md · references/
• archetype-rainmaker.md · references/
• archetype-scholar.md · references/
• archetype-socializer.md · references/
• archetype-specialist.md · references/
• archetype-technical-expert.md · references/
• archetype-traditionalist.md · references/
• archetype-trailblazer.md · references/
• conversation-starters.md · references/
• interview-trait-signals.md · references/
• motivators.md · references/
• patterns-archetypes.md · references/
• primary-traits.md · references/
• secondary-traits.md · references/
• team-composition.md · references/
• check_deps.py · scripts/
• __init__.py · scripts/culture_index/
• constants.py · scripts/culture_index/
• extract.py · scripts/culture_index/
• models.py · scripts/culture_index/
• opencv_extractor.py · scripts/culture_index/
• extract_pdf.py · scripts/
• pyproject.toml · scripts/
• uv.lock · scripts/
• burnout-report.md · templates/
• comparison-report.md · templates/
• hiring-profile.md · templates/
• individual-report.md · templates/
• predicted-profile.md · templates/
• team-report.md · templates/
• analyze-team.md · workflows/
• coach-manager.md · workflows/
• compare-profiles.md · workflows/
• define-hiring-profile.md · workflows/
• detect-burnout.md · workflows/
• extract-from-pdf.md · workflows/
• interpret-individual.md · workflows/
• interview-debrief.md · workflows/
• mediate-conflict.md · workflows/
• plan-onboarding.md · workflows/
• predict-from-interview.md · workflows/

SKILL.md (first lines)

<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>

## 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

<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 `[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:
1. Check if JSON already exists (same directory as PDF, or ask user)
2. If not, run extraction with verification:
   ```bash
   uv run --no-project {baseDir}/scripts/extract_pdf.py --verify /path/to/file.pdf [output.json]

From trailofbits/skills, CC-BY-SA-4.0.

More from trailofbits/skills