RS AI Learning Lab external drafting workbench

This workbench creates one reviewable candidate lab package for Radar to ingest later. Keep all generated work inside delivery/.

• Use /draft-lab-submission LAB-BRIEF.md for the drafting task.
• Treat LAB-BRIEF.md as the sole assignment source. Stop and report missing required fields; do not invent placement, audience, claims, examples, review needs, owner, or app authorization.
• Do not edit the canonical Learning Lab repository, GitHub Issues, GitHub Projects, branches, deployments, or published sites.
• Do not use real confidential, personal, financial, medical, legal, employment, student, client, or organization-specific material. Use fictional, synthetic, volunteered, or safely redacted inputs only.
• Return a candidate package and delivery/HANDOFF.md; do not claim approval, pilot readiness, or learner availability beyond Drafting.

Keep learning completion estimates only in facilitator guides or facilitator notes, marked provisional and refined with observed participation. Do not add duration metadata or completion estimates to learner pages, catalogs, worksheets, walkthroughs, or notebooks. Preserve timings that define an exercise or media artifact, such as a 45-second speech.

---

Source: contributor-packs/claude-code-lab-drafter/CLAUDE.md