m0x6a

Design-system UI building, UX review, WCAG 2.2 AA audits and end-to-end journey checks in a real browser, judged against an explicit craft bar.

4 skills · 1 agent

Issue → spec → approval before code, at the right size: a router picks trivial, small (one spec-and-tasks document, one gate) or full (reviewed system design, then reviewed implementation plan). Mermaid diagrams, caveats checklist, risk map and pattern catalogue on the full track.

3 skills · 1 agent

Investigate production incidents from live Grafana data (metrics, logs, traces) with a trust-check-first procedure, and keep alerts and dashboards as code with a linter, publisher and live verifier.

3 skills · 1 agent

Pull-request review that tells a maintainer with ten minutes where to look first, plus a repeatable architecture audit, a boundary guardian and a docs reconciler.

2 skills · 2 agents

MassTransit consumers (outbox tiers, idempotency, respond-or-publish), thin BFF gateway endpoints over request clients, and safe EF Core migrations.

3 skills

Cloudflare's security-audit skill packaged for Claude Code: a source-first, coverage-led audit with isolated hunters, adversarial verifiers, a schema-validated findings.json and target-neutral reports.

1 skill · 1 agent

Deploy a repository's app to a self-hosted Dockge host over SSH: publish the image to GHCR or build it locally and send it, write a pinned Compose stack with a free port and secrets kept on the host, deploy after a person approves, prove it answers, and keep the previous tag for a rollback.

1 skill

List the open issues of the current repository, pick one, and start Claude on it here or in a new tmux window.

Speak a note; it is transcribed locally and drafted into a structured GitHub issue you review before it is created.