Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
Deploy, monitor, and manage GCP services with battle-tested patterns.
Deploy, monitor, and manage GCP services with battle-tested patterns.
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
Stopped Compute Engine VMs still pay for persistent disks and static IPs โ delete disks or use snapshots for long-term storage Cloud NAT charges per VM and per GB processed โ use Private Google Access for GCP API traffic instead BigQuery on-demand pricing charges for bytes scanned, not rows returned โ partition tables and use LIMIT in dev, but LIMIT doesn't reduce scan cost in prod Preemptible VMs save 80% but can be terminated anytime โ only for fault-tolerant batch workloads Egress to internet costs, egress to same region is free โ keep resources in same region, use Cloud CDN for global distribution
Service accounts are both identity and resource โ one service account can impersonate another with roles/iam.serviceAccountTokenCreator IAM policy inheritance: Organization โ Folder โ Project โ Resource โ deny policies at org level override allows below VPC Service Controls protect against data exfiltration โ but break Cloud Console access if not configured with access levels Default Compute Engine service account has Editor role โ create dedicated service accounts with least privilege Workload Identity Federation eliminates service account keys โ use for GitHub Actions, GitLab CI, external workloads
VPC is global, subnets are regional โ unlike AWS, single VPC can span all regions Firewall rules are allow-only by default โ implicit deny all ingress, allow all egress. Add explicit deny rules for egress control Private Google Access is per-subnet setting โ enable on every subnet that needs to reach GCP APIs without public IP Cloud Load Balancer global vs regional โ global for multi-region, but regional is simpler and cheaper for single region Shared VPC separates network admin from project admin โ host project owns network, service projects consume it
Cloud Functions gen1 has 9-minute timeout โ gen2 (Cloud Run based) allows 60 minutes Cloud SQL connection limits vary by instance size โ use connection pooling or Cloud SQL Auth Proxy Firestore/Datastore hotspotting on sequential IDs โ use UUIDs or reverse timestamps for document IDs GKE Autopilot simplifies but limits โ no DaemonSets, no privileged containers, no host network Cloud Storage single object limit is 5TB โ use compose for larger, parallel uploads for faster
Cloud Logging retention: 30 days default, _Required bucket is 400 days โ create custom bucket with longer retention for compliance Cloud Monitoring alert policies have 24-hour auto-close โ incident disappears even if issue persists, configure notification channels for re-alert Error Reporting groups by stack trace โ same error with different messages creates duplicates Cloud Trace sampling is automatic โ may miss rare errors, increase sampling rate for debugging Audit logs: Admin Activity always on, Data Access off by default โ enable Data Access logs for security compliance
Terraform google provider requires project ID everywhere โ use google_project data source or variables, never hardcode gcloud commands are imperative โ use Deployment Manager or Terraform for reproducible infra Cloud Build triggers on push but IAM permissions on first run confusing โ grant Cloud Build service account necessary roles before first deploy Project deletion has 30-day recovery period โ but project ID is globally unique forever, can't reuse Labels propagate to billing โ use consistent labeling for cost allocation: env, team, service
Primitive roles (Owner/Editor/Viewer) are too broad โ use predefined roles, create custom for least privilege Service account keys are security liability โ use Workload Identity, impersonation, or attached service accounts instead roles/iam.serviceAccountUser lets you run as that SA โ equivalent to having its permissions, grant carefully Organization policies restrict what projects can do โ constraints/compute.vmExternalIpAccess blocks public VMs org-wide
Code helpers, APIs, CLIs, browser automation, testing, and developer operations.
Largest current source with strong distribution and engagement signals.