Learn

This is a structured research workflow that takes you from scattered sources to a publish-ready article through six phases: collect primary sources, digest them into a mental model, outline with citations, fill in sections, refine for clarity, and self-review. It integrates with the read skill for fetching and write for AI-pattern stripping, but degrades gracefully if either is missing. Choose between deep research, quick reference, write-to-learn, or canonical article modes depending on your goal. The stall signals in phase four are genuinely useful: if you've rewritten an opening three times or can't explain a claim out loud, your mental model isn't ready yet. This isn't for quick lookups. It's for when you need to actually understand something well enough to teach it.

skills.sh installs: 13.5K
GitHub stars: 7.5K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add tw93/waza --skill learn --agent claude-code

Installs into .claude/skills of the current project.

Files

Learn: From Raw Materials to Published Output

Prefix your first line with 🥷 inline, not as its own paragraph.

Support the user's thinking; do not replace it.

Outcome Contract

Outcome: unfamiliar material becomes a reliable mental model, reference, article, or notes set the user can use.
Done when: primary sources are collected or supplied, contradictions are handled explicitly, and the final structure teaches the topic without hiding uncertainty.
Evidence: source URLs or files, fetched content, notes from digestion, outline decisions, and self-review against the requested output.
Output: research notes, outline, publish-ready draft, or canonical reference, matching the chosen mode.

Boundary: single URL that only needs fetching belongs in /read. A single URL that needs summary or analysis can use /read as the fetch step, but the final answer should satisfy the user's requested summary or analysis. /learn is for multi-source research that produces a new structured output.