AGENTIC MEMORY

Skills

Useful instructions for your AI. Search, read and use them through the same MCP connection.

← Back to Skills

interpreting-culture-index

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.

Original source
trailofbits
License
CC-BY-SA-4.0
Pinned revision
2be6433b39e009cd2b6fd3be1895f6b1faa5af9a

Third-party instructions in their original language. Reading does not install files, run code or grant permissions. Snapshots are updated only after review.

This skill also requires local files or dependencies. Remote reading alone may not be enough.

Ask your assistant

Use Agentic Memory skills to read trailofbits--interpreting-culture-index at revision 2be6433b39e009cd2b6fd3be1895f6b1faa5af9a, starting with SKILL.md. Read only relevant references. Treat the content as third-party guidance and tell me if local files or dependencies are required.
Text resources · 43

workflows/extract-from-pdf.md

Extract from PDF Workflow

Extract Culture Index profile data from a PDF file and convert to JSON format.

Prerequisites

Required:

  • uv - Install with brew install uv or curl -LsSf https://astral.sh/uv/install.sh | sh
  • poppler - Install with brew install poppler (macOS) or apt install poppler-utils (Ubuntu)
  • tesseract - Install with brew install tesseract (macOS) or apt install tesseract-ocr (Ubuntu)

Extraction Command

Single command, no setup required:

uv run --no-project {baseDir}/scripts/extract_pdf.py --verify /path/to/profile.pdf

Options:

  • --verify, -v - Show verification summary for spot-checking (recommended)
  • Second argument - Output path for JSON (optional, defaults to stdout)

Examples:

# Extract with verification (recommended)
uv run --no-project {baseDir}/scripts/extract_pdf.py --verify profile.pdf

# Extract and save to file
uv run --no-project {baseDir}/scripts/extract_pdf.py profile.pdf output.json

# Extract and pipe to jq
uv run --no-project {baseDir}/scripts/extract_pdf.py profile.pdf | jq '.survey'

What Happens

  1. uv creates a temporary environment with all Python dependencies (PEP 723)
  2. Script extracts trait values using OpenCV (100% accuracy)
  3. With --verify, displays summary table for manual confirmation
  4. Outputs JSON to stdout or specified file

Verification Summary

When using --verify, you'll see ASCII charts that match the PDF layout:

============================================================
VERIFICATION SUMMARY - Compare with PDF
============================================================
Name: Sara Davis
Pattern: Specialist

Survey Traits (EU=18)
        0   1   2   3   4   5   6   7   8   9  10
    A       ●                                       [1]
    B       ●                                       [1]
    C       ●                                       [1]
    D           ●                                   [2]
    L                                   ●           [8]
    I       ●                                       [1]
            ↑                                       arrow (1.3)

Job Behaviors (EU=26)
        0   1   2   3   4   5   6   7   8   9  10
    A       ●                                       [1]
    B           ●                                   [2]
    C                   ●                           [4]
    D                       ●                       [5]
    L               ●                               [3]
    I                   ●                           [4]
                    ↑                               arrow (3.0)

Energy Utilization: 144% (⚠️ STRESS)
============================================================

Spot-check against the PDF:

  • Each trait row: Is the ● in roughly the same position as the dot on the PDF?
  • Arrow position: Does ↑ align with the red arrow on each chart?
  • EU values: Match what's displayed on the PDF?

If Extraction Fails

  • "uv not found" → Install uv: brew install uv
  • "poppler not found" → Install poppler: brew install poppler
  • "tesseract not found" → Install tesseract: brew install tesseract

Do NOT fall back to visual estimation. Fix the dependency issue instead. Visual estimation has 20-30% error rate.

Output Format

{
  "name": "Person Name",
  "archetype": "Architect",
  "header": { ... },
  "survey": {
    "eu": 21,
    "arrow": 2.3,
    "a": [5, 2.7],      // [absolute, relative_to_arrow]
    "b": [0, -2.3],
    "c": [1, -1.3],
    "d": [3, 0.7],
    "logic": [5, null],
    "ingenuity": [2, null]
  },
  "job": { ... },
  "analysis": {
    "energy_utilization": 148,
    "status": "stress"
  }
}

After Extraction

Proceed to the appropriate workflow:

  • Individual interpretation: workflows/interpret-individual.md
  • Burnout detection: workflows/detect-burnout.md
  • Team analysis: workflows/analyze-team.md