Anthropics February 2026 study classified 11 observable collaboration behaviors across 9,830 Claude conversations and published the distribution as the AI Fluency Index. I read it and immediately wanted to know: which of these behaviors show up in my sessions, and which ones am I skipping entirely.
The answer, when I actually looked, was embarrassing. I was hitting maybe 4 of the 11 behaviors on repeat. The others — things like iterative delegation and active discernment — I hadn't touched in months of daily use.
skill-tree plugs into Claude Code (or Cowork, or Cursor via MCP) and runs a 7-step orchestration against your actual session history: find session files, extract your messages, classify the 11 behaviors via a remote Haiku classifier on Fly.io, assign one of seven archetype cards, synthesize a narrative, render it, and return a stable URL. End-to-end takes 30–60 seconds.
The archetype cards are rendered as tarot cards with curated museum art — you can see a live example at skill-tree-ai.fly.dev/fixture/illuminator. But the part I actually use daily is the growth quest: one behavior you haven't tried, persisted across sessions via a SessionStart hook so Claude reminds you at the top of your next conversation.
The behavior taxonomy comes from Dakan & Feller's 4D AI Fluency Framework (Description, Discernment, Delegation — Diligence is the fourth axis but isn't visible in chat logs, so it's excluded).
Install in Claude Code:
claude plugin marketplace add robertnowell/ai-fluency-skill-cards
claude plugin install skill-tree-ai@ai-fluency-skill-cards
Or as an MCP server for Cursor, VS Code, Windsurf:
npm install -g skill-tree-ai
Top comments (0)