Anthropologic published a study in February measuring 11 observable collaboration behaviors across 9,830 Claude conversations. They call it the AI Fluency Index. I read it, recognized maybe four of the behaviors in my own workflow, and had no honest answer about the other seven.
skill-tree pulls your Claude Code session history, runs the same 11-behavior classification against your actual messages, and tells you which behaviors you've touched and which you've never used. The output is a character archetype card — seven possible archetypes, rendered as tarot cards with curated museum art — plus a single growth quest: one behavior from the taxonomy you haven't tried, carried forward into your next session via a SessionStart hook.
The classification runs remotely on Fly.io (Claude Haiku), takes 30–60 seconds end-to-end across seven steps: find session files, extract user messages, classify behaviors, assign archetype, synthesize a narrative, render, return a stable URL. You can see a live example at skill-tree-ai.fly.dev/fixture/illuminator.
Install in Claude Code:
claude plugin marketplace add robertnowell/ai-fluency-skill-cards
claude plugin install skill-tree-ai@ai-fluency-skill-cards
The behaviors come from Dakan & Feller's 4D AI Fluency Framework (Description, Discernment, Delegation — Diligence is the fourth axis but isn't visible in chat logs). The study baseline is 9,830 conversations. Your card tells you where you sit against that population, not just how fast you've gotten at your current habits.
Also works in Claude Cowork via skill-tree-ai.zip, and available as an MCP server (npm: skill-tree-ai) for Cursor, VS Code, and Windsurf.
Top comments (0)