product-operatorlisted

Evidence-governed product operating system that reconciles GitHub implementation and release state, Notion roadmap/tasks/decision docs, product context, and available outcome signals to answer what the team should do next on an existing roadmap or product state. Use for weekly control-loop questions such as what to build/fix/verify next, how to unstick work, what is actually done vs planned, whether roadmap and repo agree, what changed since the last review, or what should wait/stop. Produces bounded BLOCKER/VERIFY NOW/NOW/NEXT/LATER/STOP actions, dependency-aware sequencing, state drift, readiness, immutable snapshots/deltas, confidence, done conditions, and specialist handoffs. Do not use for first-time whole-repo baseline analysis or roadmap creation from scratch — use Repo to Roadmap. Do not use for release-candidate GO/NO_GO gates on a specific build/artifact — use Release Readiness. Read-only by default; delegate deep audits and consequential decisions instead of duplicating specialist skills.
MaciejZet/agent-skills · ★ 1 · AI & Automation · score 74

Install: claude install-skill MaciejZet/agent-skills

# Product Operator Protocol version: **2.0**. Operate as the product control plane, not a generic PM adviser and not a shadow project-management system. Reconstruct product reality from authoritative sources, identify the critical path, preserve uncertainty, and return the smallest defensible set of next actions. Canonical product state: `Intent -> Planned -> Implemented -> Verified -> Shipped -> Outcome` Never collapse stages. Planning is not implementation. Merge is not verification or deployment. Deployment is not outcome evidence. ## 0. Load only the control plane required Always read: - [references/modes.md](references/modes.md) - [references/source-routing.md](references/source-routing.md) - [references/state-model.md](references/state-model.md) - [references/prioritization.md](references/prioritization.md) - [references/control-loop.md](references/control-loop.md) - [references/output-contract.md](references/output-contract.md) - [references/safety.md](references/safety.md) Read only when needed: - [references/delegation.md](references/delegation.md) when specialist work or a consequential decision appears; - [references/connector-playbook.md](references/connector-playbook.md) when GitHub/Notion retrieval must be planned; - [references/evaluation.md](references/evaluation.md) when changing/testing the skill or diagnosing unstable output. When filesystem + code execution are available, use `scripts/operator_kernel.py` for reconciliation, evidence checks, rank