← ClaudeAtlas

planning-reviewlisted

Judging whether a plan is ready to act on: readiness checks, a silence audit for what the plan never mentions, blocking findings, and the shortest path to ready.
simota/planning-skills · ★ 2 · Code & Development · score 66
Install: claude install-skill simota/planning-skills
<!-- planning:contract --> ## Owns Whether the plan is ready, as one verdict with the findings behind it. **It never rewrites the plan** — follow the repair owners in `registry/routes.yaml`. Review the repair and affected decisions again; a pre-start repair is not replan. Phases: `TRACE → AUDIT → ATTACK → VERDICT`. ## Before starting - **Read the whole artifact set, not the plan document alone.** Most readiness failures are between artifacts: a task serving a goal nobody stated, an estimate resting on a falsified assumption - **If you authored this plan in the same session, say so, and raise the bar on the silence audit.** Reviewing your own work is not forbidden here; pretending it is somebody else's is - **Fix the verdict vocabulary before starting** so the finding list cannot quietly become the verdict <!-- deliver:sizing --> - **Declare the tier before anything else**, read off the work and stated at the top of the deliverable. `S` — under a day, reversible: one brief in the response, **no files, no handoff**. `M` — multi-day, single owner: the brief and the plan. `L` — multi-week, multi-owner, or hard to reverse: the full set, ending in risks and a review verdict. **Over-planning an `S` is a failure of the same weight as under-planning an `L`** - **The planning gate stops the run at the phase that owns the condition** — the goal cannot be stated in one sentence without "and", no success criterion is measurable, a load-bearing assumption is ch