ai-native-developer-experience

Bootstrap or harden a project's operating model for mixed human and AI delivery teams. Use when starting a repository, adopting an agent harness, defining authority and risk tiers, coordinating parallel agents safely, binding evidence and review to an exact candidate, or correcting fragmented rules that prevent coherent, consistent, complete delivery.

Architecture decisions, trade-off analysis, and ADR authoring. Trigger when a significant technical decision needs to be made, documented, and owned — not when an implementation detail needs a choice.

Decompose an epic into atomic parallelizable tasks and route each task to the right skill. Use this as a meta-router when you have more than one skill available and need to decide which applies. Trigger at the start of any multi-track epic or when the skill count in your harness exceeds ~12.

Check proposed stack, data flows, cloud choices, and delivery controls against declared enterprise policies, compliance frameworks, and security controls. Trigger at R2/R3 risk classification, before locking architecture decisions, or when the operating profile names a governance pointer.

Govern the SemVer release process — versioning discipline, tag-based GitHub releases, changelog hygiene, and the ADR that confirms the release strategy is agreed. Trigger when setting up a release process, before a first public release, or when release practice has become inconsistent. Owned by delivery-orchestrator.

Session-start orientation for this team harness. Load first, before any work. Explains the operating contract, when each skill triggers, and how installed companion plugins supply agent-craft capabilities while this harness supplies the team contract. Trigger at the start of every session and whenever unsure which skill applies.

Use when configuring or optimising GitHub repositories for cost-effective, consistent operations — CI triggers, Actions billing, issue tracking, labelling, branch protection, or release workflow.

Govern discovery, eligibility, and submission of a plugin or skill to official directories, registries, marketplaces, and curated GitHub lists. Use when preparing or sending plugin listings, marketplace forms, directory PRs, or repository recommendations; require current policy evidence and a final human confirmation before every external submission.

Azure expert guardrails — Entra ID least-privilege, policy-first governance, data boundaries, cost, residency, and official-source validation. Trigger when designing or reviewing any Azure workload, especially agents, LLMs (Foundry/OpenAI), or landing-zone systems.

GCP expert guardrails — IAM least-privilege, data boundaries, cost controls, residency, and official-source validation. Trigger when designing or reviewing any Google Cloud workload, especially agents, LLMs (Vertex AI/Gemini), or multi-tenant systems.

Synthesise a status, standup, or situation-report from current work state. Trigger when a team member needs a concise summary of where things stand, what is blocked, and what is next.

Force plan, HLD, ADRs, and constraints to exist BEFORE any code is generated. Trigger when starting a new feature, epic, or significant change.

Alibaba Cloud expert guardrails — RAM least-privilege, data boundaries, residency (mainland/international split), cost, and official-source validation. Trigger when designing or reviewing any Alibaba Cloud workload, especially agents or LLMs (Model Studio/Bailian, Qwen, AgentScope).

AWS expert guardrails — IAM least-privilege, data boundaries, cost controls, residency, and official-source validation. Trigger when designing or reviewing any AWS workload, especially agents, LLMs (Bedrock), or multi-account systems.

Google ADK (Agent Development Kit) orchestration patterns — boundaries, agent composition, and tool seams. Trigger when designing or reviewing multi-agent systems built on ADK. Authoritative source: adk.dev.

JP's signature red-team pass — "how would I break this?" Argue against your own approach before proceeding. Trigger on any high-stakes decision, architecture choice, or before marking work complete.

LLM and cloud cost awareness — model tiering, token budgets, right-sizing, and when a cheaper model suffices. Trigger before finalising any architecture that calls LLMs, before scaling a workload, or when a cost estimate is needed.

Validate agent output against declared domain rules and ground truth before trusting it downstream. Trigger after any agent produces output that will be used in a decision, stored persistently, or passed to another agent.

Scaffold and govern an MCP server as a bounded tool seam. Defines which tools the agent may call, enforces the principle that agents call tools and tools call infrastructure. Trigger when adding or reviewing an MCP server in an agent system.

Review gate for correctness, reuse, and simplification. Produces a structured verdict with actionable findings. Trigger on any PR before merge, or on any agent-generated code before it is committed.

Go / no-go gate before any deployment. Checks failure modes, rollback plan, cost, production bar, and definition of done. Trigger before releasing to any environment that carries real consequences.