adk-expert
Google ADK (Agent Development Kit) orchestration patterns — boundaries, agent composition, and tool seams. Trigger when designing or reviewing multi-agent…
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
$ npx -y skills add jpantsjoha/ai-native-developer-experience --skill release-manager --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/release-managerContext preview
The summary Claude sees to decide when to auto-load this skill.
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
name: release-manager description: 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.
> **A release without a confirmed process is a deployment. A deployment without a rollback plan is a gamble.**
This skill governs the release process itself — not a specific deployment (that is `release-readiness`) and not the CI infrastructure (that is `github-manager`). It ensures the team has agreed, documented, and is consistently following a versioning and release strategy, anchored by an ADR.
gaps, or no named release owner
Three release-adjacent skills exist in this harness with distinct responsibilities:
| Skill | Responsibility | |---|---| | `github-manager` | CI trigger configuration, runner cost, branch protection, tag-event wiring | | `release-manager` (this skill) | Process governance: SemVer discipline, changelog, ADR, deviation authority | | `release-readiness` | Go/no-go gate for a specific deployment: failure modes, rollback, monitoring |
Use all three in sequence for a new project. Use `release-manager` alone when auditing or repairing an existing process. Always hand off to `release-readiness` before the tag is pushed.
Unless a team ADR explicitly records a different approach, the default is:
builds in CI. No other event produces a release artifact.
[Keep a Changelog](https://keepachangelog.com/en/1.1.0/).
entry as its body.
approves and pushes version tags. No one else pushes `v*` tags to the default branch.
source of truth unless a team ADR explicitly records otherwise.
An ADR must exist that records:
If no ADR exists, create one using `the-architect`. The ADR is the authority record — process enforcement without one is informal and will drift.
Check the repository for evidence of adherence:
Flag every gap between declared ADR and observed practice. Gaps are findings, not acceptable workarounds.
Confirm the following are in place (coordinate with `github-manager` for CI config):
The release owner runs this checklist before every release:
Once the release process confirms the candidate is ready to tag, invoke `release-readiness` for the go/no-go deployment gate. The release checklist above is an input to that gate, not a substitute for it.
reproduced from a tag is not a release.
to users and to future maintainers.
not a decision.
| Excuse | Counter | |---|---| | "We all know the release process" | Tribal knowledge drifts. An ADR does not. | | "The changelog is a nic
A team-project AI harness bootstrap that gives humans and agents a shared operating contract from day one, moving AI leverage from an individual “IC superhero” advantage to a repeatable team capability on an equal playing field.
Google ADK (Agent Development Kit) orchestration patterns — boundaries, agent composition, and tool seams. Trigger when designing or reviewing multi-agent…
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…
Alibaba Cloud expert guardrails — RAM least-privilege, data boundaries, residency (mainland/international split), cost, and official-source validation. Trigger…
AWS expert guardrails — IAM least-privilege, data boundaries, cost controls, residency, and official-source validation. Trigger when designing or reviewing any…
Azure expert guardrails — Entra ID least-privilege, policy-first governance, data boundaries, cost, residency, and official-source validation. Trigger when…
LLM and cloud cost awareness — model tiering, token budgets, right-sizing, and when a cheaper model suffices. Trigger before finalising any architecture that…