kagenti

Full release lifecycle for Kagenti — alpha, RC iteration loop, GA, and patch releases with multi-repo coordination

TDD iteration loop across 4 environments (local Kind, custom HyperShift, CI Kind, CI HyperShift) with test matrix tracking and log analysis

Create and manage git worktrees for parallel development and testing

Deploy and manage Kagenti operator, agents, and tools on Kubernetes. Handles installer, CRDs, pipelines, and demo deployments.

Deploy the weather agent and MCP tool demo via CLI (no UI required). Uses pre-built ghcr.io images, deploys to team1. Optimized for speed (~15s).

Manage Kind clusters for local Kagenti testing. Create, destroy, deploy platform, and run E2E tests.

Run full end-to-end test workflows for Kagenti. Supports Kind and HyperShift clusters with automated setup and testing.

Test Kagenti platform locally using Kind. Scripts for deploy, test, and access.

Use this skill when you need to create clear, concise summaries of information. This includes summarizing long documents, articles, meeting notes, technical documentation, research papers, or any text that needs to be condensed while preserving key information. The skill provides techniques for extractive and abstractive summarization, bullet-point formatting, and executive summaries.

Add comprehensive CI workflows to a target repo - lint, test, build, security scanning, dependabot, scorecard, action pinning

Brainstorm and create phased enhancement plan for a target repo - PR sizing, phase selection, task breakdown

Add pre-commit hooks, linting, CLAUDE.md, and foundational .claude/ setup to a target repo

Review all orchestration PRs before merge - per-PR checks, cross-PR consistency, and coordinated approval

Scan and assess a target repository - tech stack, CI maturity, security posture, test coverage, supply chain health

Add security governance to a target repo - CODEOWNERS, SECURITY.md, CONTRIBUTING.md, LICENSE, .gitignore audit

Enhance any repository with CI, tests, skills, and security through phased PRs - self-replicating

Add comprehensive CI workflows to a target repo - lint, test, build, security scanning, dependabot, scorecard, action pinning

Bootstrap orchestrate skills into a target repo - making it self-sufficient for orchestrating its own related repos

Add security governance to a target repo - CODEOWNERS, SECURITY.md, CONTRIBUTING.md, LICENSE, .gitignore audit

Scan a repository to bootstrap new skills or audit and update existing ones

Skill management - create, validate, and improve Claude Code skills

Validate skill files meet the standard format and naming conventions

Create or edit skills with proper structure, task tracking, and naming conventions

Wraps existing Python agent as Kagenti ADK service using kagenti-adk with minimal compatibility changes and no business-logic rewrites. Use when migrating, wrapping, or deploying an existing plain Python or framework-based agent to Kagenti ADK; not for non-Python runtimes or building new agent from scratch.

Creates custom TypeScript UIs for Kagenti ADK agents using the @kagenti/adk SDK and A2A protocol. Use when building a custom frontend, chat interface, or interactive UI for an existing Kagenti ADK agent; not for wrapping Python agents or building agents themselves.

Instructions for debugging adk-server during development

Helps generate release notes to be published on GitHub as well as in a Slack community channel

Draft GitHub issues for kagenti/adk. Use when the user wants to report a bug, request a feature, or draft a general GitHub issue.

Review all orchestration PRs before merge - per-PR checks, cross-PR consistency, and coordinated approval

Scan a repository to bootstrap new skills or audit and update existing ones

Skill management - create, validate, and improve Claude Code skills

Validate skill files meet the standard format and naming conventions

Create or edit skills with proper structure, task tracking, and naming conventions

Start up, tear down, and configure the local Kubernetes development environment for OpenShell. Uses k3d (Docker-backed k3s) + Skaffold + Helm. Covers cluster lifecycle, optional add-ons (Keycloak OIDC, Envoy Gateway), and port mappings. Trigger keywords - local k8s, local cluster, k3d, skaffold, helm dev, start cluster, stop cluster, tear down cluster, delete cluster, create cluster, helm:k3s, helm:skaffold, local dev environment, dev cluster, k8s dev, envoy gateway local, keycloak local.

Debug why an OpenShell gateway deployment is unhealthy, unreachable, or unable to create sandboxes. Use when the user has a gateway health failure, Docker/Podman runtime issue, Helm install failure, Kubernetes scheduling issue, TLS secret issue, VM driver issue, or sandbox startup problem. Trigger keywords - debug gateway, gateway failing, deployment failing, helm install failing, cluster health, gateway health, gateway not starting, health check failed, sandbox pending, docker driver, podman driver, vm driver.

Guide agents through using the OpenShell CLI (openshell) for sandbox management, gateway registration, provider configuration, policy iteration, BYOC workflows, and inference routing. Covers basic through advanced multi-step workflows. Trigger keywords - openshell, sandbox create, sandbox connect, logs, provider create, policy set, policy get, image push, forward, port forward, BYOC, bring your own container, use openshell, run openshell, CLI usage, manage sandbox, manage provider, gateway add, gateway select.

Given a GitHub issue number, plan and implement the work described in the issue. Operates iteratively - creates an implementation plan, responds to feedback, and only builds when the 'state:agent-ready' label is applied. Includes tests, documentation updates, and PR creation. Trigger keywords - build from issue, implement issue, work on issue, build issue, start issue.

Add comprehensive CI workflows to a target repo - lint, test, build, security scanning, dependabot, scorecard, action pinning