super-autopilote-issue
Super Autopilote Issue
Take a folder of local Markdown issue files (the output of a PRD-to-issues breakdown) and drive every issue that can be done to done/, autonomously and AFK. For each issue you run a full quality loop — implement (test-driven) → review → fix → QA → simulate → fix — and you keep going, in dependency order, until the folder is exhausted or only human-gated work remains.
This skill is self-contained. Unlike issue-autopilot, it does not depend on any repo-local skill. The logic of implementation, the strict red-green-refactor TDD loop, the thermo-nuclear quality review, and the QA-plan generation are all inlined into the subagent prompts below — the subagents do NOT invoke execute-issue, thermo-nuclear-code-quality-review, qa-test-plan, or tdd. The only external skill it uses is the code-review skill that ships natively with Claude Code.
Delegate aggressively to subagents. The main thread is the orchestrator: it builds the plan, picks the next issue, spawns subagents for the expensive work (implementation, review, fixing, QA, QA-simulation), reads their structured results, and decides what happens next. The main thread does as little file-editing itself as possible.
AFK contract (non-negotiable)
This skill runs unattended. Therefore:
- Never call
AskUserQuestionand never block waiting on the user. When a real decision is needed, make the best defensible choice, record it, and continue. - Never fabricate a human gate decision. Issues that are inherently HITL (a go/no-go gate, an architectural sign-off, a design approval) cannot be "decided" by the autopilot. Produce the deliverable the issue asks for (e.g. write the memo with a recommendation), but if downstream issues are blocked by a human decision (e.g. "only if go"), stop that branch, flag it, and move to other ready work.
- Fail forward. One issue blocked or failing must not abort the whole run. Skip it with a recorded reason and continue with the rest of the ready set.
- Track progress with
TaskCreate/TaskUpdateso the user can see live state when they return.