prd-to-issueslisted

# PRD to Issues Slice a committed **PRD** into vertically-sliced **GitHub issues**: one thin, end-to-end **Vertical Slice** = one issue = one **Strain** candidate. Each issue is a tracer bullet that cuts every layer, narrow but complete and independently grabbable. Read the PRD, draft the slices, run the one slicing quiz, then publish to GitHub in dependency order. This skill is a standalone leaf transform. It names the conceptual pipeline (interrogated plan → PRD → sliced issues) for orientation only; it never references, instructs invoking, or chains to any other skill. Its output is the published issue set — there is no plan, PRD, or handoff side-effect. Load and follow: `${CLAUDE_PLUGIN_ROOT}/governance/definitions.md`, `${CLAUDE_PLUGIN_ROOT}/governance/safety-rails.md`, `${CLAUDE_PLUGIN_ROOT}/governance/security-policy.md`. ## Where this runs This skill MUST run in the **main session**. It is overlord-invocable. The skill may route sub-work (e.g. reading the PRD, drafting slices) to a bioform, but the `Agent` tool is unavailable inside subagents (ADR-0005) — only the top-level orchestrator can spawn agents, so the interrogation loop and `gh` publish stay here in the main session. Routing is intent-based: describe the work to be done; do NOT prose-pin a specific agent or invoke a sibling skill. ## Path-agnostic — producing issues does NOT force a brood This is a path-agnostic artifact transform. Producing a sliced issue set has zero bearing on the execution path. W