polishlisted
Install: claude install-skill inkatze/planwright
# /polish
The autonomous act-then-review loop (REQ-E2.1, D-12): repeat the `/self-review`
pass against the feature branch until it drains every action disposition and
only irreducible Needs-human-judgment forks (if any) remain, then hand off the
audit record. Polish is **local-only**: it never pushes and never creates or
touches a PR; its only remote interaction is the read-only fetch that pins
the base at pre-flight, and iterations never touch the remote (nested
`/self-review` passes reuse the pinned base without fetching). The pending-sign-off
checklist it emits reaches the draft PR through whichever skill owns PR
creation (`/execute-task` per REQ-E1.5, or a standalone `/self-review`).
## Doctrine
Resolve and read the same rule docs as `/self-review` via the
rule-doc resolution convention (`scripts/resolve-rule-doc.sh <doc-name>` or
the documented `PLANWRIGHT_ROOT`/`CLAUDE_PLUGIN_ROOT` chain):
`discovery-rigor`, `validation-rigor`, `finding-categorization`,
`gate-wiring`, `research-rigor`, `refactor-instinct`, `security-posture`,
`proportionality`. All load at run start except `research-rigor`, read
point-of-use inside the nested `/self-review` pass's finding-validation
(the iteration loop below).
Their definitions govern wherever this skill names a concept. If a rule doc
does not resolve, halt with a clear message naming the missing doc and the
chain consulted.
Doctrine manifest (the reading model above in machine-parseable form, per
`doctrine/instruction-hygiene.md`;