code-handofflisted

# Code Handoff (Chat → Coding Agent) The failure mode this skill prevents: Claude Code starts a fresh session with no memory of the design conversation, re-derives requirements from scratch, re-explores an approach that was already ruled out, and quietly makes a decision the user thought was already settled. The fix is a handoff document that contains decisions, not vibes. ## What to extract from the conversation Pull these out explicitly — don't paraphrase into vaguer language, keep the actual constraints as stated: 1. **Goal** — one line, the actual deliverable. 2. **Decisions already locked** — bullet list of choices already made in this conversation (stack, approach, architecture, format). These are not up for re-litigation by Claude Code. 3. **Explicitly open items** — anything still undecided. Mark these clearly as "needs input" so Claude Code doesn't silently pick an answer and present it as settled. 4. **Dead ends already ruled out, and why** — this is the highest-value section and the one most often skipped. If an approach was considered and rejected, say so and say why, or Claude Code will burn time re-discovering the same dead end. 5. **Environment / stack constraints** — language, framework, existing repo conventions, dependencies that are fixed vs. flexible. 6. **File/repo layout** — if one exists or is expected, state it; if none exists yet, say so explicitly rather than leaving it ambiguous. 7. **Acceptance criteria / definition of done** — testable, not as