wise-reviselisted

Point wise at a scope — a folder, a component, or the whole project — with a free-form improvement intent ("make the API faster", "pay down debt in src/auth", "raise test coverage", or just "improve this"), and it investigates the code read-only, decides what is worth doing, and writes self-contained implementation plans into `docs/plans/` for you to execute later however you choose. The plan is the product: it never edits source and never runs a plan. A panel of read-only roster lenses surfaces findings, the architect vets + ranks them by leverage (impact over effort, weighted by confidence), and each material finding becomes a `PLAN-*.md` in wise's schema — driven straight to a merged PR by the `impl-plan-auto` workflow, run as-is by `/wise-implement-plan-auto`, or filed as a ticket for the `ticket-auto` pipeline. Invoked as `/wise-revise` (bare alias) or `/wise:wise-revise` (canonical). Use when the user says "what should I improve here", "revise this folder / component / project", "find improvements and p
e1024kb/wise-claude · ★ 4 · AI & Automation · score 80

Install: claude install-skill e1024kb/wise-claude

# /wise-revise — investigate a scope, write executable improvement plans Before asking any user question, read and follow the [question lifecycle](../../references/workflow-host-control.md#keep-asynchronous-questions-open). Keep asynchronous prompts open until answered; this rule does not authorize questions in autonomous or otherwise prompt-free procedures. ## Why this skill exists wise has reactive quality tiers (the per-commit simplify pass, the heavyweight branch code-review gate) and autonomous ticket→PR pipelines, but nothing **proactive** — no "study this and tell me what is worth improving, then spec it" step. `/wise-revise` is that planner. It splits the work the way wise tiers models: the expensive brain (the **Lead Architect**, `wise:architect`) understands the code, judges what matters, and writes the spec; **execution is delegated to you**. The plan is the product. The skill investigates read-only and writes only under `docs/plans/` — it never edits source, never runs a mutating command, and never executes a plan. Because each plan is authored in wise's existing `PLAN-*.md` schema, you can later drive it to a merged PR end to end with `/wise-workflow-run impl-plan-auto docs/plans/<NNN>-<slug>.md` (re-plan → implement → review → PR → watch → merge), run it verbatim on this branch with `/wise-implement-plan-auto docs/plans/<NNN>-<slug>.md`, file the finding as a ticket and let the `ticket-auto` workflow build it from the ticket, or hand it to any engineer — you