platform

Install and verify Ambient Code Platform on an OpenShift cluster using quay.io images. Use when deploying Ambient to any OpenShift namespace — production, ephemeral PR test instances, or developer clusters. Covers secrets, kustomize deploy, rollout verification, and troubleshooting.

Perform any development work on the ambient-ui component. Full workflow instructions.

Deploy, update manifests, and troubleshoot the ambient-ui component. Use when creating or modifying deployment manifests, adding ambient-ui to a new overlay, building images, or debugging cluster issues.

Discover domain-specific skills and context before starting any coding or spec work. This is the mandatory first step for every task — no matter how trivial. Triggers on: any code change, spec change, implementation task, bug fix, refactor, feature work, or documentation update that touches component code or specs.

Deploy a PR's images (api-server, control-plane, runner) to any OpenShift namespace for integration testing. Works on both standard OpenShift clusters and MPP managed clusters. Auto-detects the environment and chooses the right script.

End-to-end development workflow for the Ambient Code Platform. Covers ticket → branch → spec → code → commit → PR → review → deploy → verify. Self-improving: update this skill whenever a failure path is discovered or a shortcut is validated. Git history is the audit trail.

Required context for all frontend work. Loads frontend standards (conventions, React Query patterns, adapter testing requirements) before any code changes. Use when modifying anything under components/frontend/. Triggers on: any frontend code change, UI component work, React Query hooks, API adapter work, frontend bug fix, frontend refactor.

Run a convention alignment check across the codebase to measure adherence to documented standards. Use when you want to check health of the codebase, verify convention compliance, get a scored report, find violations, check alignment before a release, or run periodic quality scans. Triggers on: "check conventions", "alignment scan", "codebase health", "are we following our standards", "convention violations", "quality check", "how aligned are we".

Perform a comprehensive code review using repository-specific standards. Use when reviewing code changes, checking PR quality, auditing convention compliance, or validating changes before merge. Triggers on: "review code", "check changes", "code review", "amber review", "review PR", "audit conventions", "quality check".

Manages Ambient Code Platform development clusters (kind) for testing changes locally. Use when deploying PRs to kind, bringing up local clusters, rebuilding images, troubleshooting pod issues, or running benchmarks. Triggers on: "test in kind", "deploy locally", "kind cluster", "rebuild images", "pod crashing", "bring up cluster", "kind-up", "dev environment", "local dev".

Create a Cypress-based video demo for a feature branch with cursor, click effects, and captions. Use when recording feature demos, creating PR videos, showcasing UI changes, or generating visual walkthroughs. Triggers on: "demo", "record demo", "create demo video", "cypress demo", "feature walkthrough", "PR video", "showcase".

This skill should be used when the user asks to "add a feature flag", "gate a feature", "put this behind a flag", "add a workspace flag", "feature flag this", "make this configurable per workspace", "configure Unleash", or references "flags.json", "useWorkspaceFlag", "useFlag", "SyncFlags", or "controlled rollout" of a feature.

Manage the auto-memory system for this project. Search, audit, prune, and create memories with proper frontmatter. Use when you need to find a past decision, check if memories are stale, clean up duplicates, add a new memory, or understand what context is available. Triggers on: "check memory", "what do we remember about", "find the memory about", "clean up memories", "audit memories", "add to memory", "is there a memory for".

Trigger the Amber Handler to automatically fix a pull request (rebase, address review comments, run lints/tests, push fixes). Posts @ambient-code on the PR to trigger the fix prompt. Use when user types /pr-fixer <number>, says "fix PR", "run pr-fixer", "address PR comments", or "auto-fix pull request".

Generate the complete file set for a new integration, endpoint, or feature flag following established project patterns. Use when adding a new integration (like Jira, CodeRabbit, Google Drive), creating a new API endpoint with full stack, or setting up a new feature flag. Triggers on: "new integration", "add an integration", "scaffold", "create endpoint", "add a new provider", "wire up a new service". Always includes a feature flag. Follows the Jira integration pattern.

Create or modify a spec following the project's spec format and conventions. Use when the user wants to write a new spec, add requirements or scenarios to an existing spec, or restructure spec content. Triggers on: "write a spec", "create a spec", "add a requirement", "spec this out", "define the behavior", "what should the spec look like", "new spec for", "update the spec".

Use when creating or updating Gerrit changes — pushing code for review, amending patch sets, setting reviewers and topics. Triggers on "push to Gerrit", "create a Gerrit change", "upload for review", "update the patch set", "add reviewers to this change".

Use when reviewing a Gerrit change — fetching change details, reading diffs, posting inline comments, and voting with labels. Triggers on "review this Gerrit change", "review change 12345", "look at this Gerrit CL", "code review on Gerrit".

Use when submitting or preparing a Gerrit change for merge — checking submit requirements, rebasing, resolving comments, and submitting. Triggers on "submit this Gerrit change", "merge this CL", "is this change ready to submit", "check submit requirements".