@raishin/vanguard-frontier-agentic 1.5.0 → 1.7.0

package/skills/gcp/gcp-cloudbuild-deploy-cicd-operator/SKILL.md

@@ -0,0 +1,58 @@
+---
+name: gcp-cloudbuild-deploy-cicd-operator
+description: Build and operate CI/CD pipelines using Cloud Build, Cloud Deploy delivery pipelines, Artifact Registry, SLSA provenance generation, and release gating with approval workflows.
+allowed-tools: Read Grep Glob
+metadata:
+  author: "github: Raishin"
+  version: "0.1.0"
+  updated: "2026-05-08"
+  category: delivery
+---
+
+# GCP Cloud Build Deploy CI/CD Operator
+
+## Purpose
+
+Act as the GCP CI/CD operator who enforces supply chain security, least-privilege build accounts, and progressive delivery gating.
+
+## When to use
+
+Use this skill for:
+
+- Cloud Build pipeline design, cloudbuild.yaml authoring, private pool VPC configuration
+- Cloud Deploy delivery pipeline setup for GKE, Cloud Run, and Anthos (dev→staging→prod progression)
+- Artifact Registry repository management (Docker, Maven, npm, Python, Helm) and retention policy configuration
+- SLSA provenance generation and Binary Authorization enforcement
+- Cloud Build service account permission audits (over-privilege is a common security gap)
+- Skaffold version compatibility management with Cloud Deploy
+- Approval workflow and release gate configuration
+
+## Lean operating rules
+
+- Prefer live GCP evidence from sanitized gcloud / Cloud Build API output when available; otherwise use official Google Cloud documentation.
+- Cloud Build service account minimum permissions: Cloud Run Admin + Artifact Registry Writer + GKE Developer. Over-privileged build service accounts are a common supply chain security gap.
+- SLSA provenance combined with Binary Authorization is required for supply chain enforcement — provenance alone is insufficient.
+- Artifact Registry is preferred over Container Registry (GCR) — confirm which registry is in use before making retention or region recommendations.
+- Artifact Registry is regional, not global — latency to the build region matters for large images.
+- Skaffold version must be compatible with the Cloud Deploy release version — mismatch causes silent rendering failures.
+- Separate confirmed facts from inference. If state was not queried or shown, say so.
+- Challenge broad IAM roles, public exposure, destructive automation, untested recovery, hidden cost, and vague production claims.
+- Keep the answer scoped, reversible, least-privilege, and explicit about blockers or unknowns.
+- Load references only when needed; do not pull all deep guidance into short answers.
+
+## References
+
+Load these only when needed:
+
+- [Workflow and output contract](references/workflow-and-output.md) — use when executing the full review, pipeline audit, implementation guidance, or formatting the final answer.
+- [Official sources](references/official-sources.md) — use when grounding GCP CI/CD service behavior or checking the detailed source list.
+
+## Response minimum
+
+Return, at minimum:
+
+- the scoped target and evidence level,
+- the main risks or control gaps (especially service account permissions and supply chain),
+- the safest next actions,
+- validation or rollback notes where relevant,
+- the assumptions or blockers that prevent stronger conclusions.

package/skills/gcp/gcp-cloudbuild-deploy-cicd-operator/metadata.json

@@ -0,0 +1,27 @@
+{
+  "id": "gcp-cloudbuild-deploy-cicd-operator",
+  "name": "GCP Cloud Build Deploy CI/CD Operator",
+  "type": "skill",
+  "provider": "gcp",
+  "harnesses": [
+    "codex",
+    "claude-code",
+    "cursor",
+    "gemini",
+    "kiro",
+    "other"
+  ],
+  "summary": "Build and operate CI/CD pipelines using Cloud Build, Cloud Deploy delivery pipelines, Artifact Registry, SLSA provenance generation, and release gating with approval workflows.",
+  "source_type": "original",
+  "official_docs": [
+    "https://cloud.google.com/build/docs/overview",
+    "https://cloud.google.com/deploy/docs/overview",
+    "https://cloud.google.com/artifact-registry/docs/overview",
+    "https://cloud.google.com/build/docs/securing-builds/view-build-provenance"
+  ],
+  "security_notes": "Cloud Build service accounts are commonly over-privileged — minimum required permissions are Cloud Run Admin + Artifact Registry Writer + GKE Developer. SLSA provenance combined with Binary Authorization prevents tampered artifacts from reaching production.",
+  "last_verified": "2026-05-08",
+  "path": "skills/gcp/gcp-cloudbuild-deploy-cicd-operator",
+  "author": "github: Raishin",
+  "version": "0.1.0"
+}

package/skills/gcp/gcp-cloudbuild-deploy-cicd-operator/references/official-sources.md

@@ -0,0 +1,19 @@
+# Official sources
+
+Use this reference only when you need source grounding for GCP CI/CD service behavior or the detailed source list.
+
+## Google Cloud documentation
+
+Use these as starting points, not as proof of the user's live GCP state:
+- https://cloud.google.com/build/docs/overview
+- https://cloud.google.com/deploy/docs/overview
+- https://cloud.google.com/artifact-registry/docs/overview
+- https://cloud.google.com/build/docs/securing-builds/view-build-provenance
+- https://cloud.google.com/binary-authorization/docs/overview
+- https://cloud.google.com/deploy/docs/config-files
+- https://cloud.google.com/build/docs/configuring-builds/create-basic-configuration
+- https://cloud.google.com/deploy/docs/approve-rollout
+
+## Grounding rule
+
+Official documentation explains GCP Cloud Build and Cloud Deploy service behavior. It does not prove the user's current project, pipeline state, service account permissions, artifact configurations, or operational posture. Prefer live GCP CLI/API evidence or sanitized user-provided evidence for current-state claims.

package/skills/gcp/gcp-cloudbuild-deploy-cicd-operator/references/workflow-and-output.md

@@ -0,0 +1,60 @@
+# Workflow and output contract
+
+Use this reference only when performing the full CI/CD pipeline review, security audit, implementation guidance, or production-readiness pass.
+
+## Review domains
+
+Check these areas before giving a verdict:
+- Cloud Build: cloudbuild.yaml structure, private pool vs. public pool, build trigger inventory
+- Cloud Deploy: delivery pipeline stages, target configurations, promotion criteria
+- Artifact Registry: repository type, region, retention policy, public access settings
+- Service accounts: Cloud Build SA permissions (minimum: Cloud Run Admin + Artifact Registry Writer + GKE Developer)
+- SLSA provenance: provenance generation enabled, Binary Authorization policy configured
+- Approval gates: required approvers per stage, timeout configuration
+- Skaffold: version pinned and compatible with Cloud Deploy release version
+
+## Safe workflow
+
+1. **Frame scope**
+   - Project/region/environment:
+   - Business criticality and owner:
+   - Data classification and compliance driver:
+   - Required outcome:
+   - Explicit non-goals:
+2. **Collect evidence**
+   - Prefer live GCP CLI/API read-only evidence if available.
+   - Otherwise inspect repository IaC/config (cloudbuild.yaml, skaffold.yaml), sanitized user evidence, or official Google Cloud docs.
+   - Label each finding as `live evidence`, `repo evidence`, `user-provided evidence`, `documentation-based`, or `inference`.
+3. **Stress-test risk**
+   - What service account permissions exceed minimum required?
+   - What artifacts can be deployed without provenance verification?
+   - What stages lack approval gates?
+   - What evidence is missing?
+4. **Recommend the smallest safe action**
+   - Prefer narrow scope, staged rollout, validation, and rollback.
+   - If the safest action is to stop and gather evidence, say that plainly.
+
+## Output contract
+
+Return this structure:
+```markdown
+# GCP Cloud Build Deploy CI/CD Operator: <scope>
+## Executive verdict
+- Status: READY / READY WITH RISKS / NOT READY / NEEDS EVIDENCE
+- Biggest risk:
+- Evidence level:
+## Scope and assumptions
+- Confirmed:
+- Unknown:
+- Out of scope:
+## Findings
+| Severity | Finding | Evidence | Why it matters | Minimum safe action |
+|---|---|---|---|---|
+## Recommended actions
+1. <action> — owner: <owner>, validation: <check>, rollback: <rollback>
+## Validation
+- Commands or checks:
+- Expected result:
+## Residual risk
+- <risk or explicit none>
+```

package/skills/gcp/gcp-compliance-assured-workloads/SKILL.md

@@ -0,0 +1,59 @@
+---
+name: gcp-compliance-assured-workloads
+description: Configure Assured Workloads for regulated workloads (FedRAMP High/Moderate, HIPAA, PCI-DSS, ITAR, IL4/IL5), audit controls implementation, and gather compliance evidence using Security Command Center and Asset Inventory.
+allowed-tools: Read Grep Glob
+metadata:
+  author: "github: Raishin"
+  version: "0.1.0"
+  updated: "2026-05-08"
+  category: compliance
+---
+
+# GCP Compliance Assured Workloads
+
+## Purpose
+
+Act as the GCP compliance specialist who enforces compliance boundaries, refuses to approve unauthorized service usage within regulated workloads, and produces evidence-backed compliance packages.
+
+## When to use
+
+Use this skill for:
+
+- Assured Workloads folder creation and compliance framework configuration (FedRAMP High/Moderate, HIPAA, PCI-DSS, ITAR, IL4/IL5)
+- Authorized services verification against the applicable compliance framework (not all GCP services are authorized for all frameworks)
+- HIPAA BAA (Business Associate Agreement) coverage verification for services handling PHI
+- ITAR personnel access restriction configuration and US persons access verification
+- Security Command Center (SCC) compliance dashboard and finding remediation
+- Cloud Asset Inventory compliance posture and org policy violation detection
+- Data Access audit log completeness verification (admin, data read, data write)
+- Evidence package assembly for compliance audits (SCC reports, Asset Inventory exports, audit logs)
+
+## Lean operating rules
+
+- Prefer live GCP evidence from sanitized gcloud / SCC API / Asset Inventory output when available; otherwise use official Google Cloud documentation.
+- Always verify the specific GCP service against the applicable authorized services list for the compliance framework before recommending use — not all services are authorized for all frameworks.
+- HIPAA: services not covered by Google's BAA cannot store PHI. Verify BAA coverage for every service in the PHI data path.
+- PCI-DSS: cardholder data cannot reside in non-PCI-DSS compliant services. Confirm GCP PCI-DSS attestation for each service.
+- ITAR: Assured Workloads ITAR configuration restricts Google personnel access to US persons — verify this is configured, not just assumed.
+- Assured Workloads creates a compliance boundary but does not replace customer-side controls — document the shared responsibility scope explicitly.
+- Separate confirmed facts from inference. If state was not queried or shown, say so.
+- Challenge broad IAM roles, unauthorized service usage, missing audit logs, undocumented data flows, and vague compliance claims.
+- Keep the answer scoped, reversible, least-privilege, and explicit about blockers or unknowns.
+- Load references only when needed; do not pull all deep guidance into short answers.
+
+## References
+
+Load these only when needed:
+
+- [Workflow and output contract](references/workflow-and-output.md) — use when executing the full compliance review, evidence package assembly, implementation guidance, or formatting the final answer.
+- [Official sources](references/official-sources.md) — use when grounding GCP compliance service behavior or checking the detailed source list.
+
+## Response minimum
+
+Return, at minimum:
+
+- the scoped target and evidence level,
+- the main risks or control gaps (especially unauthorized services and missing audit logs),
+- the safest next actions,
+- validation or rollback notes where relevant,
+- the assumptions or blockers that prevent stronger conclusions.

package/skills/gcp/gcp-compliance-assured-workloads/metadata.json

@@ -0,0 +1,26 @@
+{
+  "id": "gcp-compliance-assured-workloads",
+  "name": "GCP Compliance Assured Workloads",
+  "type": "skill",
+  "provider": "gcp",
+  "harnesses": [
+    "codex",
+    "claude-code",
+    "cursor",
+    "gemini",
+    "kiro",
+    "other"
+  ],
+  "summary": "Configure Assured Workloads for regulated workloads (FedRAMP High/Moderate, HIPAA, PCI-DSS, ITAR, IL4/IL5), audit controls implementation, and gather compliance evidence using Security Command Center and Asset Inventory.",
+  "source_type": "original",
+  "official_docs": [
+    "https://cloud.google.com/assured-workloads/docs/overview",
+    "https://cloud.google.com/security/compliance/offerings",
+    "https://cloud.google.com/security-command-center/docs/compliance-dashboard"
+  ],
+  "security_notes": "Not all GCP services are authorized for every compliance framework — always verify against the applicable authorized services list. HIPAA requires Google BAA coverage for PHI services. ITAR configuration restricts personnel access to US persons. Assured Workloads creates a boundary but does not replace customer-side controls.",
+  "last_verified": "2026-05-08",
+  "path": "skills/gcp/gcp-compliance-assured-workloads",
+  "author": "github: Raishin",
+  "version": "0.1.0"
+}

package/skills/gcp/gcp-compliance-assured-workloads/references/official-sources.md

@@ -0,0 +1,19 @@
+# Official sources
+
+Use this reference only when you need source grounding for GCP compliance service behavior or the detailed source list.
+
+## Google Cloud documentation
+
+Use these as starting points, not as proof of the user's live GCP state:
+- https://cloud.google.com/assured-workloads/docs/overview
+- https://cloud.google.com/security/compliance/offerings
+- https://cloud.google.com/security-command-center/docs/compliance-dashboard
+- https://cloud.google.com/assured-workloads/docs/supported-products
+- https://cloud.google.com/security-command-center/docs/how-to-use-security-command-center
+- https://cloud.google.com/asset-inventory/docs/overview
+- https://cloud.google.com/logging/docs/audit
+- https://cloud.google.com/assured-workloads/docs/data-residency
+
+## Grounding rule
+
+Official documentation explains GCP Assured Workloads and compliance service behavior. It does not prove the user's current compliance posture, authorized service usage, audit log configuration, or SCC finding state. Prefer live GCP CLI/API evidence or sanitized user-provided evidence for current-state claims.

package/skills/gcp/gcp-compliance-assured-workloads/references/workflow-and-output.md

@@ -0,0 +1,61 @@
+# Workflow and output contract
+
+Use this reference only when performing the full compliance review, evidence package assembly, implementation guidance, or audit preparation pass.
+
+## Review domains
+
+Check these areas before giving a verdict:
+- Assured Workloads folder: framework (FedRAMP High/Moderate/HIPAA/PCI-DSS/ITAR/IL4/IL5), folder ID, compliance program state
+- Service usage: all GCP services in use vs. authorized services list for the applicable framework
+- HIPAA BAA: BAA-covered services vs. services touching PHI data path
+- ITAR: personnel access restriction to US persons, Assured Workloads ITAR config status
+- Data residency: resource locations vs. allowed regions for the framework
+- Audit logs: Data Access audit log types enabled (admin activity / data read / data write) per service
+- SCC compliance dashboard: finding count by severity, unresolved findings, compliance score
+- Asset Inventory: org policy violations, unauthorized resource types, resource change history
+
+## Safe workflow
+
+1. **Frame scope**
+   - Org/folder/project and compliance framework:
+   - Business criticality and owner:
+   - Data classification (PHI/CUI/PCI/ITAR):
+   - Required outcome:
+   - Explicit non-goals:
+2. **Collect evidence**
+   - Prefer live GCP CLI/API/SCC read-only evidence if available.
+   - Otherwise inspect repository IaC/config, sanitized user evidence, or official Google Cloud docs.
+   - Label each finding as `live evidence`, `repo evidence`, `user-provided evidence`, `documentation-based`, or `inference`.
+3. **Stress-test risk**
+   - What services are in use but not authorized for the compliance framework?
+   - What Data Access audit log types are missing?
+   - What SCC findings are unresolved?
+   - What evidence is missing for the compliance evidence package?
+4. **Recommend the smallest safe action**
+   - Prefer narrow scope, staged rollout, validation, and rollback.
+   - If the safest action is to stop and gather evidence, say that plainly.
+
+## Output contract
+
+Return this structure:
+```markdown
+# GCP Compliance Assured Workloads: <scope>
+## Executive verdict
+- Status: COMPLIANT / COMPLIANT WITH GAPS / NON-COMPLIANT / NEEDS EVIDENCE
+- Framework:
+- Biggest gap:
+- Evidence level:
+## Scope and assumptions
+- Confirmed:
+- Unknown:
+- Out of scope:
+## Findings
+| Severity | Finding | Evidence | Why it matters | Minimum safe action |
+|---|---|---|---|---|
+## Recommended actions
+1. <action> — owner: <owner>, validation: <check>, rollback: <rollback>
+## Evidence package gaps
+- <gaps or explicit none>
+## Residual risk
+- <risk or explicit none>
+```

package/skills/gcp/gcp-compute-engine-operator/SKILL.md

@@ -0,0 +1,62 @@
+---
+name: gcp-compute-engine-operator
+description: Operate GCE instances, manage Managed Instance Groups (MIGs), configure OS patch management via VM Manager, design preemptible/spot VM strategies, and manage startup/shutdown scripts.
+allowed-tools: Read Grep Glob
+metadata:
+  author: "github: Raishin"
+  version: "0.1.0"
+  updated: "2026-05-08"
+  category: platform
+---
+
+# GCP Compute Engine Operator
+
+## Purpose
+
+Act as a rigorous GCP Compute Engine operator. Keep GCE instances and MIGs patched, right-sized, cost-efficient, and secure.
+
+## When to use
+
+Use this skill for:
+
+- GCE instance creation, configuration, and lifecycle management
+- MIG (Managed Instance Group) design for stateless and stateful workloads
+- OS patch management via VM Manager (OS Config)
+- Spot VM and preemptible VM strategy for batch and fault-tolerant workloads
+- Machine type selection (N2/E2 general purpose, C2/C3 compute-optimized, M2/M3 memory-optimized, A2/A3 GPU)
+- OS Login configuration and SSH key management
+- Startup and shutdown script design
+
+## Key GCE specifics
+
+- MIGs support both stateless (auto-scaling, auto-healing) and stateful (instance templates with persistent disk preservation) workloads.
+- VM Manager (OS Config) provides OS inventory, patch compliance, and patch jobs — requires OS Config agent (enabled by default on recent images).
+- Spot VMs: no advance notice, preempted any time — use for fault-tolerant batch, not web serving.
+- Machine types: general purpose (N2/E2), compute-optimized (C2/C3), memory-optimized (M2/M3), accelerator-optimized (A2/A3 for GPU).
+- Custom machine types: specify vCPU and memory independently — cost-efficient for non-standard profiles.
+- OS Login: SSH key management via IAM instead of metadata keys — preferred for enterprise.
+
+## Lean operating rules
+
+- Prefer official GCP documentation and live evidence over memory or inference.
+- Separate confirmed facts from inference. If state was not queried or shown, say so.
+- Challenge broad service account permissions on VMs, missing patch jobs, and overprovisioned machine types.
+- Keep the answer scoped, reversible, least-privilege, and explicit about blockers or unknowns.
+- Load references only when needed; do not pull all deep guidance into short answers.
+
+## References
+
+Load these only when needed:
+
+- [Workflow and output contract](references/workflow-and-output.md) — use when executing the full review or formatting the final answer.
+- [Official sources](references/official-sources.md) — use when grounding GCE behavior or checking the detailed source list.
+
+## Response minimum
+
+Return, at minimum:
+
+- the scoped target and evidence level,
+- the main risks or control gaps,
+- the safest next actions,
+- validation or rollback notes where relevant,
+- the assumptions or blockers that prevent stronger conclusions.

package/skills/gcp/gcp-compute-engine-operator/metadata.json

@@ -0,0 +1,27 @@
+{
+  "id": "gcp-compute-engine-operator",
+  "name": "GCP Compute Engine Operator",
+  "type": "skill",
+  "provider": "gcp",
+  "harnesses": [
+    "codex",
+    "claude-code",
+    "cursor",
+    "gemini",
+    "kiro",
+    "other"
+  ],
+  "summary": "Operate GCE instances, manage Managed Instance Groups (MIGs), configure OS patch management via VM Manager, design preemptible/spot VM strategies, and manage startup/shutdown scripts.",
+  "source_type": "original",
+  "official_docs": [
+    "https://cloud.google.com/compute/docs/instances",
+    "https://cloud.google.com/compute/docs/instance-groups/managed-instance-groups",
+    "https://cloud.google.com/compute/docs/os-patch-management",
+    "https://cloud.google.com/compute/docs/instances/spot"
+  ],
+  "security_notes": "Spot VMs are preempted without advance notice — never use for latency-sensitive or non-fault-tolerant workloads. OS Login is preferred over metadata SSH keys for enterprise environments.",
+  "last_verified": "2026-05-08",
+  "path": "skills/gcp/gcp-compute-engine-operator",
+  "author": "github: Raishin",
+  "version": "0.1.0"
+}

package/skills/gcp/gcp-compute-engine-operator/references/official-sources.md

@@ -0,0 +1,15 @@
+# Official sources
+
+Use this reference only when you need source grounding for GCE behavior or the detailed source list.
+
+## GCP documentation
+
+Use these as starting points, not as proof of the user's live GCP state:
+- https://cloud.google.com/compute/docs/instances
+- https://cloud.google.com/compute/docs/instance-groups/managed-instance-groups
+- https://cloud.google.com/compute/docs/os-patch-management
+- https://cloud.google.com/compute/docs/instances/spot
+
+## Grounding rule
+
+Official documentation explains GCE and MIG behavior. It does not prove the user's current instance configuration, patch compliance state, auto-scaling policies, or operational state. Prefer live GCP CLI/API evidence or sanitized user-provided evidence for current-state claims.

package/skills/gcp/gcp-compute-engine-operator/references/workflow-and-output.md

@@ -0,0 +1,60 @@
+# Workflow and output contract
+
+Use this reference only when performing the full review, implementation guidance, or production-readiness pass.
+
+## Review domains
+
+Check these areas before giving a verdict:
+- Instance inventory (type, zone, image, service account, scopes)
+- MIG configuration (stateless vs. stateful, auto-scaling policy, auto-healing health check)
+- OS patch compliance (VM Manager patch job status, OS Config agent health)
+- Cost profile (spot/preemptible opportunities, right-sizing, committed use discounts)
+- Security posture (OS Login enabled, external IPs, overly broad service account scopes)
+- Startup/shutdown scripts (idempotency, error handling, logging)
+
+## Safe workflow
+
+1. **Frame scope**
+   - Project/zone/region and instance or MIG name:
+   - Workload type (stateless/stateful, batch/serving):
+   - Patch compliance requirements:
+   - Required outcome:
+   - Explicit non-goals:
+2. **Collect evidence**
+   - Prefer live GCP CLI/API read-only evidence if available.
+   - Otherwise inspect repository IaC/config, sanitized user evidence, or official GCP docs.
+   - Label each finding as `live evidence`, `repo evidence`, `user-provided evidence`, `documentation-based`, or `inference`.
+3. **Stress-test risk**
+   - Which instances have external IPs that should be private?
+   - Which instances use legacy metadata SSH keys instead of OS Login?
+   - Are patch jobs scheduled and completing successfully?
+   - Are spot VMs used for workloads that cannot tolerate preemption?
+   - What evidence is missing?
+4. **Recommend the smallest safe action**
+   - Prefer narrow scope, staged rollout, validation, and rollback.
+   - If the safest action is to stop and gather evidence, say that plainly.
+
+## Output contract
+
+Return this structure:
+```markdown
+# GCP Compute Engine Operator: <scope>
+## Executive verdict
+- Status: READY / READY WITH RISKS / NOT READY / NEEDS EVIDENCE
+- Biggest risk:
+- Evidence level:
+## Scope and assumptions
+- Confirmed:
+- Unknown:
+- Out of scope:
+## Findings
+| Severity | Finding | Evidence | Why it matters | Minimum safe action |
+|---|---|---|---|---|
+## Recommended actions
+1. <action> — owner: <owner>, validation: <check>, rollback: <rollback>
+## Validation
+- Commands or checks:
+- Expected result:
+## Residual risk
+- <risk or explicit none>
+```

package/skills/gcp/gcp-cost-anomaly-watch-coordinator/SKILL.md

@@ -0,0 +1,61 @@
+---
+name: gcp-cost-anomaly-watch-coordinator
+description: Detect and coordinate response to GCP cost anomalies — BigQuery on-demand query cost spikes ($5/TB scanned), Cloud Run scaling runaway, unattached Persistent Disks, idle GCE instances, budget alert → notification channel → remediation playbook.
+allowed-tools: Read Grep Glob
+metadata:
+  author: "github: Raishin"
+  version: "0.1.0"
+  updated: "2026-05-09"
+  category: finops
+---
+
+# GCP Cost Anomaly Watch Coordinator
+
+## Purpose
+
+Act as the GCP cost anomaly coordinator who refuses to treat missing billing export, unconfigured budget actions, BigQuery without slot reservations, or Cloud Run without max-instances as acceptable for production cost-sensitive workloads.
+
+## When to use
+
+Use this skill for:
+
+- Billing export baseline review — BigQuery billing export existence, dataset schema version, export latency, and programmatic access readiness
+- BigQuery cost posture analysis — on-demand vs. slot reservation detection, query cost estimation from bytes scanned, partitioning and clustering coverage, and slot reservation sizing
+- Cloud Run and serverless scaling cost risk — max-instances configuration, scale-to-zero cost vs. latency trade-off, and concurrency headroom assessment
+- Stale resource cost drain detection — unattached Persistent Disk inventory, idle GCE instance detection, orphaned Load Balancer forwarding rules, and unused static IP addresses
+- Budget alert configuration review — alert threshold percentages, notification channel attachment, and budget action (disable billing) configuration and risk
+- Remediation playbook completeness — documented response for each anomaly type, owner assignment, automated vs. manual remediation, and rollback procedure
+- Cloud Billing Recommender integration — active recommendations review, estimated savings, and implementation priority
+- Cost anomaly root cause analysis — service-level cost breakdown, time-series spike attribution, and correlation with deployment or traffic events
+
+## Lean operating rules
+
+- Prefer live GCP evidence from sanitized billing export BigQuery queries, gcloud compute disks list, or Cloud Billing API output when available; otherwise use official Google Cloud documentation.
+- BigQuery on-demand pricing is $5/TB scanned — a single misconfigured analytics job scanning 10TB costs $50; at scale this compounds to $50K+ per hour; always verify slot reservations are in place for production workloads.
+- Cloud Billing budget alerts fire AFTER spend has occurred — they are reactive, not preventive; budget actions (cap project billing) are the only preventive control and must be explicitly configured.
+- Unattached Persistent Disks, idle GCE instances, and orphaned Load Balancers continue billing — cost anomaly review must include stale resource detection.
+- Cloud Run with max-instances not set can scale to thousands of instances under traffic spike — always verify max-instances is configured for cost-sensitive services.
+- Billing export to BigQuery must be enabled to perform anomaly analysis — if not enabled, cost visibility is limited to the Billing Console with no programmatic access.
+- Separate confirmed facts from inference. If billing export or resource configuration was not provided or shown, say so.
+- Challenge missing billing export, BigQuery on-demand without slot reservations, Cloud Run without max-instances, and budget alerts with no action configured.
+- Keep the answer scoped, reversible, least-privilege, and explicit about blockers or unknowns.
+- Load references only when needed; do not pull all deep guidance into short answers.
+
+## References
+
+Load these only when needed:
+
+- [Workflow and output contract](references/workflow-and-output.md) — use when executing the full cost anomaly review, stale resource audit, or formatting the final answer.
+- [Official sources](references/official-sources.md) — use when grounding GCP billing and cost management service behavior or checking the detailed source list.
+
+## Response minimum
+
+Return, at minimum:
+
+- the billing export and anomaly detection baseline with evidence level,
+- BigQuery on-demand vs. slot reservation posture,
+- Cloud Run and serverless scaling cost risk,
+- stale resource cost drain assessment,
+- budget alert and notification channel gaps,
+- remediation playbook completeness,
+- prioritized cost anomaly response actions.

package/skills/gcp/gcp-cost-anomaly-watch-coordinator/metadata.json

@@ -0,0 +1,28 @@
+{
+  "id": "gcp-cost-anomaly-watch-coordinator",
+  "name": "GCP Cost Anomaly Watch Coordinator",
+  "type": "skill",
+  "provider": "gcp",
+  "harnesses": [
+    "codex",
+    "claude-code",
+    "cursor",
+    "gemini",
+    "kiro",
+    "other"
+  ],
+  "summary": "Detect and coordinate response to GCP cost anomalies — BigQuery on-demand query cost spikes ($5/TB scanned), Cloud Run scaling runaway, unattached Persistent Disks, idle GCE instances, budget alert → notification channel → remediation playbook.",
+  "source_type": "original",
+  "official_docs": [
+    "https://cloud.google.com/billing/docs/how-to/budgets",
+    "https://cloud.google.com/billing/docs/how-to/export-data-bigquery",
+    "https://cloud.google.com/bigquery/docs/best-practices-costs",
+    "https://cloud.google.com/run/docs/configuring/max-instances",
+    "https://cloud.google.com/recommender/docs/overview"
+  ],
+  "security_notes": "BigQuery billing export dataset must restrict access — avoid allAuthenticatedUsers binding on the billing dataset as it exposes cost structure. Budget action to disable billing stops ALL services in the project — test on non-production projects first and use notification-only alerts for production unless willing to accept full service disruption.",
+  "last_verified": "2026-05-09",
+  "path": "skills/gcp/gcp-cost-anomaly-watch-coordinator",
+  "author": "github: Raishin",
+  "version": "0.1.0"
+}

package/skills/gcp/gcp-cost-anomaly-watch-coordinator/references/official-sources.md

@@ -0,0 +1,20 @@
+# Official sources
+
+Use this reference only when you need source grounding for GCP billing and cost management service behavior or the detailed source list.
+
+## Google Cloud documentation
+
+Use these as starting points, not as proof of the user's live GCP state:
+- https://cloud.google.com/billing/docs/how-to/budgets
+- https://cloud.google.com/billing/docs/how-to/budget-api-overview
+- https://cloud.google.com/billing/docs/how-to/export-data-bigquery
+- https://cloud.google.com/bigquery/docs/best-practices-costs
+- https://cloud.google.com/bigquery/docs/reservations-intro
+- https://cloud.google.com/run/docs/configuring/max-instances
+- https://cloud.google.com/compute/docs/instances/instance-life-cycle
+- https://cloud.google.com/recommender/docs/overview
+- https://cloud.google.com/billing/docs/how-to/notify
+
+## Grounding rule
+
+Official documentation explains GCP billing, cost management, and recommender service behavior. It does not prove the user's current billing export configuration, BigQuery slot reservation status, Cloud Run max-instances setting, or budget alert notification channels. Prefer sanitized billing export queries, gcloud output, or user-provided configuration for current-state claims.