Skip to content
SkillMixed3,566 tokens in use

Interpreting Culture Index

Interprets Culture Index surveys from PDF or JSON: individual traits, team gas-brake-glue balance, burnout signals, hiring profiles and manager coaching.

8,319 stars on the repository CC-BY-SA-4.0trailofbits/skills · plugins/culture-index/skills/interpreting-culture-index
/plugin marketplace add trailofbits/skills
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing Interpreting Culture Index costs

133tokens idle
3,566tokens in use
27,230tokens, up to

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Up to adds the files its instructions link. Counts are approximate, made offline with cl100k_base.

Model dependence Mixed

Script-ledMixedModel-led

Scripts do part of the work and the model's judgement does the rest.

This describes the skill's structure, how much of it is scripts. It does not say how well it works. Scripts: scripts/check_deps.py, scripts/culture_index/__init__.py, scripts/culture_index/constants.py, scripts/culture_index/extract.py, scripts/culture_index/models.py, scripts/culture_index/opencv_extractor.py, scripts/extract_pdf.py.

Touches

shelldeclared and detectednetworkdetectedwrites filesdeclared and detected

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Excellent
  • Frontmatter12/15
  • Structure17/25
  • Examples15/15
  • Output15/15
  • Size15/15
  • Resources10/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Good
  • Runs shell commands−2

    does this on the machine, as the frontmatter declares

    SKILL.md, line 125
  • Reaches the network−10

    does this on the machine, and the frontmatter does not say so

    scripts/check_deps.py, line 98
  • Writes files−4

    does this on the machine, as the frontmatter declares

    scripts/culture_index/extract.py, line 163
  • File that was not read−15

    a file the skill ships that was not read, so what it does is unknown

    scripts/uv.lock

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Good
  • Development activity100
  • Maintenance52
  • Community64
  • Maturity32
  • Momentum40

Interpreting Culture Index helps an agent read Culture Index (CI) behavioral profiles correctly. It teaches the method that trips most readers up: never compare absolute trait values between people, read each trait as distance from the person’s own arrow, and treat Survey as who someone is and Job as who they are trying to be.

It supports individual interpretation, team composition, burnout detection from Survey-versus-Job gaps, profile comparison, hiring profiles, manager coaching, trait prediction from interview transcripts, candidate debriefs, onboarding plans and conflict mediation. PDF profiles are extracted by an OpenCV script, never estimated by eye.

What You Get

  • An interpretation anchored to distance from the arrow, with labels from normative to extreme
  • JSON extracted from a Culture Index PDF, with a verification summary to check against the original
  • Team views using the gas, brake and glue framework
  • Burnout flags from gaps between the Survey and Job graphs

Common Use Cases

  • Interpreting one person’s Culture Index profile for a manager
  • Comparing a team’s profiles or a candidate against a hiring profile
  • Spotting burnout risk when Job behavior differs sharply from Survey traits
  • Preparing a candidate debrief or an onboarding plan

What Makes It Unique

Most personality-assessment prompts compare raw scores. This skill forbids that for four of the six traits, allows it only for Logic and Ingenuity, and bans visual estimation of PDF values in favor of an extraction script. It also states that Culture Index must not be the sole basis for hiring or firing decisions and excludes DISC, Myers-Briggs and clinical use.

Under The Hood

The skill loads an instruction file with reference, template, workflow and script folders. For a PDF it runs a Python script through uv, which downloads the declared Python packages (OpenCV, pdf2image, pytesseract and others) on first use and needs poppler and tesseract installed on the machine. A dependency check script reports what is missing, and the extraction can save the JSON next to your file. The agent also reads your profile files and can write analysis output to disk. The skill makes no API calls of its own and fetches no web pages. Profile data is processed by the model in your session.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers