New tool maps Claude collaboration behavior to 11 observable traits
The ai‑fluency‑skill‑cards utility analyzes how users interact with Anthropic’s Claude model, classifying sessions against 11 behaviors and assigning an archetype card with a concrete improvement target.
A new utility called ai‑fluency‑skill‑cards analyzes collaboration behavior with Claude, Anthropic’s large language model. The tool draws on a study of 9,830 Claude conversations that identified 11 observable behaviors across three axes—Description, Discernment, and Delegation—[devto].
The output includes a tarot‑style archetype card, a skill radar visualizing present versus missing behaviors, and a single target behavior for the user’s next session. The package can be installed directly in Claude Code and is also compatible with Cowork, Cursor, VS Code, and Windsurf[GitHub].
── What shipped ──
The classification system follows the Dakan & Feller 4D AI Fluency Framework and maps sessions to seven archetypes: Illuminator, Navigator, Alchemist, plus four others[devto]. Execution takes roughly 30–60 seconds and returns a stable URL that can be shared.
── Why it matters ──
By translating raw interaction data into a concrete set of behaviors, the tool gives engineers and product builders a measurable way to assess and improve their Claude usage. Users can see which of the 11 behaviors they already exhibit, which archetype they most closely match, and a clear next step to broaden their collaboration skill set.
Subscribe to the broadcast.
Daily digest of the day's most important tech news. No fluff. Engineering signal only.
// delivered via substack · double-opt-in confirmation