Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Configure service mesh (Istio, Linkerd, Consul) with traffic routing, mTLS, observability, and advanced traffic management for microservices.
.claude/skills/williamzujkowski-service-mesh-configurator/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 82% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 70% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 5% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 106% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 164% | 0% |
Trigger conditions:
Not for:
Time normalization:
NOW_ET using NIST/time.gov semantics (America/New_York, ISO-8601): 2025-10-26T01:33:54-04:00NOW_ET for all citation access datesInput validation:
mesh_type must be: istio, linkerd, or consulservices array must contain at least 2 servicesmtls_mode must be: strict, permissive, or disabledtraffic_management if specified must be: canary, blue-green, mirroring, or fault-injectionSource freshness:
Decision thresholds:
Step 1: Enable service mesh sidecar injection
Step 2: Create basic traffic routing
Output:
Abort conditions:
All T1 steps plus:
Step 1: Traffic splitting and canary deployment
Step 2: Resilience patterns
Step 3: Authorization and security
Step 4: Observability integration
Output:
Abort conditions:
All T1 + T2 steps plus:
Step 1: Multi-cluster mesh
Step 2: Advanced security
Step 3: Performance optimization
Output:
Mesh type selection:
mTLS mode:
Traffic management strategy:
Circuit breaker thresholds:
Ambiguity handling:
Required fields (all tiers):
yamlmesh_config: namespace_labels: istio-injection: enabled # or linkerd.io/inject: enabled mtls_mode: "strict | permissive | disabled" traffic_rules: virtual_service: "VirtualService YAML (Istio) or ServiceProfile (Linkerd)" destination_rule: "DestinationRule YAML with load balancing" security_config: peer_authentication: "PeerAuthentication YAML for mTLS" certificates: "certificate management configuration"
Additional T2 fields:
yamladvanced_traffic: canary_config: stable_weight: integer canary_weight: integer circuit_breaker: consecutive_errors: integer interval: "duration" base_ejection_time: "duration" retry_policy: attempts: integer per_try_timeout: "duration" retry_on: "5xx,gateway-error,reset,connect-failure" authorization: authorization_policy: "AuthorizationPolicy YAML" request_authentication: "RequestAuthentication YAML for JWT" observability: distributed_tracing: enabled: boolean sampling_rate: float backend: "jaeger | tempo | zipkin" metrics: prometheus_scrape: boolean custom_metrics: ["array of metric names"] dashboards: grafana_dashboards: ["array of dashboard URLs"]
Additional T3 fields:
yamlmulti_cluster: trust_domain: "cluster.local" cluster_federation: "multi-cluster mesh configuration" egress_control: egress_gateway: "Gateway YAML for external traffic" service_entry: "ServiceEntry for external services" performance_tuning: sidecar_resources: cpu_request: "100m" memory_request: "128Mi" telemetry_optimization: sampling_rate: 0.01 batch_size: integer
yaml# T1 Example: Istio VirtualService and DestinationRule apiVersion: networking.istio.io/v1beta1 kind: VirtualService metadata: name: reviews spec: hosts: - reviews http: - route: - destination: host: reviews subset: v1 weight: 100 --- apiVersion: networking.istio.io/v1beta1 kind: DestinationRule metadata: name: reviews spec: host: reviews trafficPolicy: tls: mode: ISTIO_MUTUAL subsets: - name: v1 labels: version: v1
yaml# T2 Example: Circuit Breaker apiVersion: networking.istio.io/v1beta1 kind: DestinationRule metadata: name: api-circuit-breaker spec: host: api-service trafficPolicy: connectionPool: tcp: maxConnections: 100 http: http1MaxPendingRequests: 50 maxRequestsPerConnection: 2 outlierDetection: consecutiveErrors: 5 interval: 30s baseEjectionTime: 30s maxEjectionPercent: 50
Token budgets (enforced):
Safety checks:
Auditability:
Determinism:
Validation requirements:
istioctl analyze validationlinkerd checkOfficial Documentation (accessed 2025-10-26T01:33:54-04:00):
Best Practices:
Observability Integration:
Advanced Patterns:
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 10,635 | 6,171 | -42% | 1 | 1 | 0% | 2,384 | 4,342 | +82% | 0 | 0 | — |
case-02 | fail→pass | 15,561 | 13,480 | -13% | 1 | 1 | 0% | 3,445 | 5,855 | +70% | 0 | 0 | — |
case-03 | fail→pass | 27,833 | 16,811 | -40% | 1 | 1 | 0% | 6,221 | 6,512 | +5% | 0 | 0 | — |
case-04 | pass→pass | 7,152 | 7,784 | +9% | 1 | 1 | 0% | 1,837 | 4,483 | +144% | 0 | 0 | — |
case-05 | pass→pass | 18,512 | 17,807 | -4% | 1 | 1 | 0% | 3,313 | 6,143 | +85% | 0 | 0 | — |
case-06 | pass→pass | 8,788 | 11,792 | +34% | 1 | 1 | 0% | 2,268 | 5,182 | +128% | 0 | 0 | — |
case-07 | fail→pass | 10,389 | 5,930 | -43% | 1 | 1 | 0% | 2,034 | 4,192 | +106% | 0 | 0 | — |
case-08 | fail→pass | 7,744 | 5,501 | -29% | 1 | 1 | 0% | 1,459 | 3,858 | +164% | 0 | 0 | — |
case-09 | pass→pass | 14,725 | 6,078 | -59% | 1 | 1 | 0% | 2,779 | 4,105 | +48% | 0 | 0 | — |
case-10 | pass→pass | 7,430 | 4,646 | -37% | 1 | 1 | 0% | 1,419 | 3,824 | +169% | 0 | 0 | — |
case-11 | pass→pass | 7,353 | 5,692 | -23% | 1 | 1 | 0% | 1,436 | 4,030 | +181% | 0 | 0 | — |
case-12 | pass→pass | 6,306 | 6,873 | +9% | 1 | 1 | 0% | 1,083 | 4,207 | +288% | 0 | 0 | — |
case-13 | fail→pass | 10,411 | 4,745 | -54% | 1 | 1 | 0% | 2,071 | 3,934 | +90% | 0 | 0 | — |
case-14 | fail→pass | 10,421 | 6,357 | -39% | 1 | 1 | 0% | 1,749 | 4,109 | +135% | 0 | 0 | — |
case-15 | pass→fail | 6,543 | 5,929 | -9% | 1 | 1 | 0% | 1,109 | 3,864 | +248% | 0 | 0 | — |
case-16 | pass→pass | 11,542 | 9,444 | -18% | 1 | 1 | 0% | 2,039 | 4,672 | +129% | 0 | 0 | — |
case-17 | fail→pass | 13,471 | 12,808 | -5% | 1 | 1 | 0% | 2,793 | 5,429 | +94% | 0 | 0 | — |
case-18 | fail→pass | 13,685 | 10,093 | -26% | 1 | 1 | 0% | 2,592 | 4,919 | +90% | 0 | 0 | — |
case-19 | pass→pass | 8,592 | 5,205 | -39% | 1 | 1 | 0% | 1,612 | 3,955 | +145% | 0 | 0 | — |
case-20 | fail→pass | 9,799 | 11,084 | +13% | 1 | 1 | 0% | 1,998 | 5,190 | +160% | 0 | 0 | — |
case-21 | fail→fail | 9,210 | 4,889 | -47% | 1 | 1 | 0% | 1,595 | 3,845 | +141% | 0 | 0 | — |
case-22 | fail→pass | 10,230 | 4,591 | -55% | 1 | 1 | 0% | 1,952 | 3,704 | +90% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +45 percentage points is the difference between those two pass rates over the 22 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.