☁️ Infrastructure Knowledge Brain — Self-wiring knowledge graph for infra topology, incident history and runbooks. Derived from gbrain (garrytan/gbrain). CI/CD pipelines, container orchestration, IaC, monitoring.
Build and operation support for n8n-cli. Guides remote status checks, imports, dry-runs, apply, and linter execution. Auto-build recommended for new sessions.
Review an Apache Doris PR from a local clone with the same multi-agent, shared-ledger convergence workflow as the CI Code Review Runner. Use when the user supplies a PR to /doris-repo-review, asks to review a Doris PR locally, or asks for the CI-style review flow. Safely align only the current worktree to the exact PR…
Cross-cloud commitment portfolio specialist. Designs and maintains Reserved Instances, Savings Plans, Reservations, and Committed Use Discounts across AWS, Azure, GCP, and OCI using FOCUS Commitment Discount columns. Maximizes effective discount without bleeding on unused commitment.
The operating contract for any scheduled or unattended agent session — a cron job, a Routine, a CI-triggered agent, a nightly sweep. Use when writing, reviewing, debugging or scheduling automation that runs without a human present, and whenever a scheduled job reports success but you cannot find what it produced.…
Fix CI failures and performance regressions for a Julia package PR by iterating - triage the latest CI results, fix one root cause, verify locally, push. Use when a PR's GitHub Actions or Buildkite CI is failing, or when CI jobs run slower than they do on the main branch. Verifies CPU and GPU compilation locally…
Set up monitoring, logging, and observability for applications and infrastructure. Use when implementing health checks, metrics collection, log aggregation, or alerting systems. Handles Prometheus, Grafana, ELK Stack, Datadog, and monitoring best practices.
Guide for building, configuring, and deploying microfrontends on Vercel. Use this skill when the user mentions microfrontends, multi-zones, splitting an app across teams, independent deployments, cross-app routing, incremental migration, composing multiple frontends under one domain, microfrontends.json…
Set up a web app on a single cheap, hardened VPS the "levels.io" way — one Hetzner/DigitalOcean box running Next.js (or any Node app) on SQLite + Caddy (auto-HTTPS) + systemd, secured with Tailscale, put behind a Cloudflare domain, and set up to charge money with Stripe. The whole "idea → app that makes money on a…
Install, configure, and use routeup for stable local HTTPS routes, public development tunnels, webhook and OAuth callbacks, and browser-agent access to local services. Use when the user mentions routeup, wants to replace localhost ports with named HTTPS URLs, needs a development service reachable from another machine…
Generate production-ready Kubernetes manifests (Deployment, Service, ConfigMap, Secret, ServiceAccount, optional HPA) for a containerized application. Use AFTER a Dockerfile exists and has been validated by fix-dockerfile. Triggers include "generate kubernetes manifests", "deploy this to k8s", "write k8s yaml"…
Move one experiment through RUN → VERIFY → DELIVER with the least control work that safely advances the user's outcome. This is the compute/control layer and owns one compute attempt. When the task spans several runs, nodes, independent side-effect lanes, or paper-wide closeout, route scheduling and state projection…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: