← ClaudeAtlas

sumo-qa-planning-qa-rolloutlisted

Use when you have a chunk of QA work (a story, a PR, a strategy phase) that needs to be turned into a written plan of bite-sized, independently-executable tasks before any test code is written. Walks scope → file structure → bite-sized tasks → confirm, one section per turn. Produces docs/qa/plans/YYYY-MM-DD-<feature>.md ready for subagent dispatch via sumo-qa-executing-qa-rollout.
sumithr/sumo-qa · ★ 4 · Testing & QA · score 70
Install: claude install-skill sumithr/sumo-qa
# Planning a QA rollout Help the user turn an amorphous QA ask ("we need test coverage for the new refund flow", "Phase 1 of the strategy") into a written plan a fresh agent or teammate could pick up and execute task-by-task — without you in the room. **Announce at start:** *"Turning this into a dispatchable plan."* ## Output discipline (mandatory) Inherits the global discipline from `using-sumo-qa`: **output discipline** (never surface internal taxonomy labels — say *"behaviour change in pricing"*, not *"Classification: business_logic_change"*), **output economy** (spend output on findings not framing; no preamble or self-narration; one question per turn; no closing pleasantries), knowledge authority hierarchy, internal scaffolding stays internal, and specialty-tool fit. <HARD-GATE> Do NOT start scaffolding tests or dispatching subagents from this skill. This skill's only output is the written plan document. Execution happens in `sumo-qa-executing-qa-rollout` after the plan is signed off. </HARD-GATE> ## The Iron Law **NO EXECUTION FROM THE PLANNER. THE PLAN IS THE DELIVERABLE.** The plan must stand alone — readable by someone who wasn't in the conversation, specific enough that a fresh subagent given just one task could execute it without coming back for clarification. ## When to Use `sumo-qa-deciding-approach` routes here when: - the work spans **3+ tasks** that can be done independently (otherwise: skip planning, route straight to `sumo-qa-implementing-with-tdd`