n-pillai

AI Fluency Assessment Skill — AI skill for Claude Code

AI community

A Claude Code skill for quarterly AI fluency assessment using Anthropic's 4D Framework and Yegge's 8-Stage Developer-Agent Evolution Model.

How to install AI Fluency Assessment Skill

This entry records only its repository, not the path inside it, so there is no exact command to give. Open n-pillai/ai-fluency-assessment-skill and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What AI Fluency Assessment Skill does

A Claude Code skill for quarterly AI fluency assessment using Anthropic's 4D Framework and Yegge's 8-Stage Developer-Agent Evolution Model.

Alternatives in AI

Anthropic SDK TypeScript — Access to Anthropic's safety-first language model APIs in TypeScript 2.1k ★
Claude To ChatGPT — This project converts the API of Anthropic's Claude model to the OpenAI Chat API format 1.3k ★
Claude Code Switch — One-command model switcher for Claude Code (Only for Anthropic API) 655 ★

README

AI Fluency Assessment Skill

A Claude Code skill for quarterly assessment of AI fluency across two frameworks:

Anthropic's 4D AI Fluency Framework — Delegation, Description, Discernment, Diligence
Yegge's 8-Stage Developer-Agent Evolution Model — Stage 1 (zero AI usage) through Stage 8 (own orchestrator)

Tracks progress over time with structured JSON history and generates dated `.docx` reports.

Installation

Copy the full skill directory into your Claude Code skills folder — the skill needs its companion files (`REFERENCE.md`, `templates/`, `assessments/`), so copying `SKILL.md` alone will not work:

# macOS/Linux
cp -r . ~/.claude/skills/ai-fluency-assessment/

# Windows
xcopy /E /I . %USERPROFILE%\.claude\skills\ai-fluency-assessment\

Install the Python dependency for `.docx` report generation:

pip install python-docx

Usage

Ask Claude Code to run your AI fluency assessment (e.g. "assess my AI fluency" or "run a fluency check") — the skill is picked up by description match. The flags below can be given in the same request (e.g. "run a quick fluency assessment").

Command	What it does
`/assess-fluency`	Full assessment: gather data, score frameworks, diff against last, generate report
`/assess-fluency --quick`	Output data-gathering prompts only — no scoring or report
`/assess-fluency --compare`	Diff the two most recent assessments without new data

What the Assessment Covers

The skill guides you through three data-gathering prompts (run in separate sessions):

Prompt A — Claude Code self-assessment: projects, autonomy levels, automations, Yegge stage estimate
Prompt B — Other AI tools: automations, integrations, and AI-generated artifacts (ChatGPT, Copilot, Gemini, n8n, Zapier, etc.)
Checklist C — Claude.ai manual notes: delegation patterns, error-catching, format specifications

Then scores each 4D competency (Developing → Practitioner → Advanced → Expert → Exc