Claude Skills by JSchOBL

Reviews a learner's hand-written Claude Code setup for a level of the Agentic AI Learning Journey lab — the CLAUDE.md always, plus any skill, hook, settings.json, subagents, or MCP server the level asks them to write — identifies missing or weak elements against a rubric, challenges the learner to fix them, and records what they learned in a personalized LEARNINGS.md. Use after the learner has finished a level — triggers include "review my CLAUDE.md", "review my level 2", "review my level 3",...

Format Python source files with Black and isort, then report any remaining lint issues. Use when the user asks to format, clean up, tidy, or fix the style of Python code.

Run the pytest suite, report pass/fail counts and coverage, and identify untested code. Use when the user asks to run tests, check test coverage, or verify that changes didn't break anything.