{"slug": "seven-archetypes-a-skill-radar-and-what-your-claude-sessions-actually-reveal", "title": "Seven archetypes, a skill radar, and what your Claude sessions actually reveal", "summary": "Anthropic's February 2026 study classified 11 collaboration behaviors across 9,830 Claude conversations, forming the AI Fluency Index. A developer built skill-tree, a tool that analyzes Claude Code or Cowork session files against this taxonomy, assigning users one of seven archetypes (e.g., Illuminator, Navigator) and generating a growth quest to address blind spots. The tool runs in 30-60 seconds and is available as a Claude Code plugin, Cowork extension, or MCP server.", "body_md": "Anthropics February 2026 study classified 11 observable collaboration behaviors across 9,830 Claude conversations. The researchers called it the AI Fluency Index. I wanted to run the same classification on my own session history — not to benchmark against other users, but to find out which of the 11 behaviors I never touched.\n\nThe result is skill-tree. It reads your Claude Code or Cowork session files, runs a remote classifier against the same 11-behavior taxonomy from Dakan and Feller's 4D AI Fluency Framework (three observable axes: Description, Discernment, Delegation — the fourth, Diligence, doesn't show up in chat logs), and assigns you one of seven archetype cards rendered as tarot cards with curated museum art.\n\nThe archetypes — Illuminator, Navigator, Alchemist, and four others — aren't just cosmetic. Each maps to a distinct behavioral cluster. The Illuminator front-loads context and over-explains; the Navigator iterates tightly and discards failed directions fast. Seeing which card you land on tells you something your git history doesn't: not what you shipped, but how you collaborated to get there. You can see a live rendered example at skill-tree-ai.fly.dev/fixture/illuminator.\n\nThe growth quest piece is what I actually find useful day-to-day. After classification, the tool picks one behavior from your blind spots and pins it as a quest via the SessionStart hook, so it shows up at the top of your next Claude Code session. The state persists in `~/.skill-tree/`\n\nbetween sessions.\n\nThe full pipeline — find session files, extract user messages, classify remotely via Claude Haiku on Fly.io, assign archetype, synthesize narrative, render the card, return a stable URL — runs in 30 to 60 seconds.\n\nInstall in Claude Code:\n\n```\nclaude plugin marketplace add robertnowell/ai-fluency-skill-cards\nclaude plugin install skill-tree-ai@ai-fluency-skill-cards\n```\n\nAlso works in Cowork via `skill-tree-ai.zip`\n\n, or as an MCP server (npm package `skill-tree-ai`\n\n) for Cursor, VS Code, and Windsurf.", "url": "https://wpnews.pro/news/seven-archetypes-a-skill-radar-and-what-your-claude-sessions-actually-reveal", "canonical_source": "https://dev.to/palo_alto_ai/seven-archetypes-a-skill-radar-and-what-your-claude-sessions-actually-reveal-45cg", "published_at": "2026-07-12 11:00:21+00:00", "updated_at": "2026-07-12 11:14:28.645901+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-agents", "developer-tools", "ai-research"], "entities": ["Anthropic", "Claude", "Claude Code", "Cowork", "Fly.io", "MCP", "Robert Nowell"], "alternates": {"html": "https://wpnews.pro/news/seven-archetypes-a-skill-radar-and-what-your-claude-sessions-actually-reveal", "markdown": "https://wpnews.pro/news/seven-archetypes-a-skill-radar-and-what-your-claude-sessions-actually-reveal.md", "text": "https://wpnews.pro/news/seven-archetypes-a-skill-radar-and-what-your-claude-sessions-actually-reveal.txt", "jsonld": "https://wpnews.pro/news/seven-archetypes-a-skill-radar-and-what-your-claude-sessions-actually-reveal.jsonld"}}