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

references/interview-trait-signals.md

This reference helps predict Culture Index traits from interview transcripts. Candidates don't take CI during interviews - these signals help estimate traits before the actual survey is administered after an offer is signed.

Important caveats:

  • Predictions are estimates, not definitive assessments
  • Interview context affects behavior (stress, performance mode)
  • Always note confidence level for each trait
  • Actual CI survey will confirm or correct predictions

<trait_signals>

<autonomy_a label="Autonomy (A) Signals">

High A indicators (right of arrow):

  • Uses "I" frequently: "I decided...", "I built...", "I led..."
  • Takes personal credit for outcomes
  • Describes situations where they acted independently
  • Pushes back on interviewer questions or reframes them
  • Strategic framing - connects work to business outcomes
  • Confident tone, assertive statements
  • Mentions enjoying autonomy, disliking micromanagement
  • Describes taking initiative without being asked

Low A indicators (left of arrow):

  • Uses "we" predominantly: "We decided...", "Our team..."
  • Deflects credit to the team
  • Asks clarifying questions before answering
  • Seeks validation: "Does that make sense?"
  • Describes collaborative decision-making
  • Mentions appreciating clear direction
  • More tentative language: "I think...", "Maybe..."
  • Waits for prompts rather than driving conversation

Confidence modifiers:

  • HIGH confidence: Multiple consistent signals across different questions
  • MEDIUM confidence: Mixed signals or few data points
  • LOW confidence: Signals only in specific contexts (may be performance mode)

</autonomy_a>

<social_b label="Social Ability (B) Signals">

High B indicators (right of arrow):

  • Builds rapport quickly, asks about interviewer
  • Animated, expressive communication style
  • Tells stories with people as central characters
  • Discusses team dynamics, relationships
  • Uses humor, creates connection
  • Mentions enjoying collaboration, team activities
  • Verbose responses, talks through thinking
  • Mirrors interviewer's energy and style

Low B indicators (left of arrow):

  • Brief, direct answers without elaboration
  • Skips small talk, gets to the point
  • Task-focused: describes what was done, not who was involved
  • Reserved or flat affect
  • Minimal questions about the team/culture
  • Doesn't engage with personal questions
  • Processes internally before responding
  • Technical precision over narrative style

Confidence modifiers:

  • HIGH confidence: Behavior consistent throughout entire interview
  • MEDIUM confidence: Opens up later (may be warming up)
  • LOW confidence: Interviewer-driven variation (some interviewers draw out B)

</social_b>

<pace_c label="Pace/Patience (C) Signals">

High C indicators (right of arrow):

  • Thoughtful pauses before answering
  • Asks for clarification, wants to understand fully
  • Structured, methodical responses
  • Mentions preferring stable environments
  • Describes careful, deliberate decision-making
  • Discomfort with hypotheticals or rapid-fire questions
  • References to planning, preparation
  • Prefers one topic at a time

Low C indicators (left of arrow):

  • Rapid responses, quick wit
  • Interrupts or finishes interviewer's sentences
  • Topic-jumps, tangential connections
  • Mentions thriving under pressure, deadlines
  • Comfortable with ambiguity and pivots
  • Describes multitasking positively
  • Energy increases with urgency
  • Short attention span for detailed questions

Confidence modifiers:

  • HIGH confidence: Consistent pace throughout interview
  • MEDIUM confidence: Interview pressure may affect natural pace
  • LOW confidence: Phone vs in-person may show different C

</pace_c>

<conformity_d label="Conformity/Detail (D) Signals">

High D indicators (right of arrow):

  • Precise language, specific numbers and dates
  • References rules, processes, best practices
  • Structured answers following question format
  • Mentions quality, accuracy, standards
  • Asks about company processes, documentation
  • Describes checking work, seeking feedback
  • Uses technical terms correctly and consistently
  • Follows interview structure carefully

Low D indicators (left of arrow):

  • Big-picture answers, approximations
  • Comfortable with "it depends" responses
  • Creative interpretations of questions
  • Mentions flexibility, adaptability
  • Skeptical of rigid processes
  • Focuses on outcomes over methods
  • May challenge question premises
  • Unstructured, flowing responses

Confidence modifiers:

  • HIGH confidence: Consistent precision (or lack of) across topics
  • MEDIUM confidence: Higher precision in domain expertise areas
  • LOW confidence: May mask natural D to appear more flexible

</conformity_d>

<logic_l label="Logic (L) Signals">

Note: L uses absolute values (not relative to arrow).

High L indicators (7-10):

  • Data-driven reasoning: "The numbers showed..."
  • Logical frameworks: "First... then... therefore..."
  • Emotion-neutral language
  • Focuses on facts over feelings
  • Analytical approach to problems
  • May seem detached when discussing difficult situations
  • Questions based on data or evidence

Low L indicators (0-3):

  • Values-driven language: "It felt right..."
  • Emotional context in stories
  • Empathy-focused responses
  • Describes gut feelings, intuition
  • People-impact framing
  • May get emotional discussing meaningful work
  • Questions based on culture, values, impact

Moderate L (4-6):

  • Blends logic and emotion contextually
  • Adapts framing to situation
  • Can argue both sides

</logic_l>

<ingenuity_i label="Ingenuity (I) Signals">

Note: I uses absolute values (not relative to arrow).

High I indicators (7-10):

  • Novel approaches to problems
  • Questions assumptions, challenges status quo
  • Connects unrelated concepts
  • Describes inventing solutions
  • Mentions boredom with routine
  • Creative reframing of questions
  • Original examples, not textbook answers

Low I indicators (0-3):

  • Conventional approaches, proven methods
  • References industry standards, best practices
  • Prefers established processes
  • Practical, grounded solutions
  • Describes following playbooks successfully
  • May seem less creative but highly reliable

Moderate I (4-6):

  • Creative within constraints
  • Innovates when necessary, follows when appropriate

</ingenuity_i>

</trait_signals>

<pattern_combinations>

Look for trait combinations that suggest patterns:

| Signal Cluster | Likely Pattern | |----------------|----------------| | High A + Low B + rapid pace + big-picture | Architect/Visionary | | High A + High B + rapid pace | Rainmaker/Persuader | | Low B + deliberate pace + precise | Scholar/Specialist | | Low A + High B + deliberate | Accommodator | | Low A + Low B + precise | Technical Expert |

</pattern_combinations>

<transcript_analysis_tips>

When analyzing transcripts:

  1. Count language patterns - "I" vs "we", precise vs approximate
  2. Note energy shifts - What topics animate them? What topics flatten them?
  3. Watch for consistency - Same signals across different questions?
  4. Consider context - Technical questions vs behavioral questions
  5. Flag uncertainties - Note where evidence is weak

Red flags for confidence:

  • Candidate clearly in "interview mode" (performing)
  • Very short interview (insufficient data)
  • Interviewer dominated conversation
  • Technical-only questions (limited behavioral data)

</transcript_analysis_tips>

<output_format>

When predicting traits from transcripts, output:

## Predicted Culture Index Profile: [Candidate Name]

### Trait Predictions
| Trait | Predicted Position | Confidence | Key Evidence |
|-------|-------------------|------------|--------------|
| A | High/Low/Norm | H/M/L | "Quote..." |
| B | High/Low/Norm | H/M/L | "Quote..." |
| C | High/Low/Norm | H/M/L | "Quote..." |
| D | High/Low/Norm | H/M/L | "Quote..." |
| L | Score (0-10) | H/M/L | "Quote..." |
| I | Score (0-10) | H/M/L | "Quote..." |

### Predicted Pattern
[Pattern name] - [Confidence]

### Evidence Summary
[2-3 sentences on strongest signals]

### Uncertainty Areas
[Where more data would help]

### Caveats
- Interview behavior may differ from natural behavior
- Actual CI survey will be administered after offer
- This prediction is a hypothesis, not a diagnosis

</output_format>