upstream-contribute

# /upstream-contribute — meta-loop: rockie users improve rockie `/upstream-contribute` covers two contribution modes: - **Local harness patch** — package an improvement against the user's own local rockie clone as a reviewed patch proposal. - **Public upstream PR** — generalize the pattern and dispatch a PR against `Rockielab/rockie-claude` so the next release ships it to everyone. This is the meta-loop. Researchers using rockie-claude in their own work uncover patterns that generalize — a tighter `[DEAD-END]` query, a hook that catches a stuck-detector edge case, a skill that helps across disciplines. The skill captures one of those, generalizes it, and opens a reviewable PR. The maintainers merge; the next user benefits. ## When to run - The user says "upstream this", "contribute back", "anything generalizable here", "open-source this", "propose a harness change", or "write a PR for rockie". - `/clean` finishes an audit and emits the post-audit nudge (see `clean/SKILL.md` → "Post-audit hook"). - A `[LEARN harness-upstream]` or `[LEARN cross-discipline]` block was written this session and the user wants to act on it. Run **at most once** per session, near the end. Don't dispatch the writer sub-agent during active work — the user wants to review the candidates before any forking happens. ## Method The skill uses **Scout / Generator / Verifier / Updater** separation. The proposing agent never verifies and commits its own change. ### 1. Scout (this skill,...