Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →nwave-ai/nw-par-critique-dimensions
Platform design review critique dimensions and severity levels. Load when reviewing CI/CD pipelines, infrastructure, deployment strategies, observability, or security designs.
Passed 16 of 22 test cases with the skill, and 5 of 22 without it.
and 10 more in the full report
11 fixed5 passed either way6 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 11 test cases the skill fixed. Same model, same prompt, with and without the skill.
A team configures alert notifications in Slack that point to dashboard links, but no runbook URLs are attached to the alert payloads. What severity is this observability gap?
| Checked | Without skill | With skill |
|---|---|---|
| Rates missing runbook links on alerts as a High severity issue. | Missed | Passed |
The instructions your model reads when the skill loads.
Questions: All stages defined (commit, acceptance, capacity, production)? Quality gates explicit with pass/fail criteria? Parallelization used? Failure recovery/retry documented? Commit stage < 10 min, acceptance < 30 min?
Blocker: Missing critical stage (no acceptance tests) | no quality gates | no security scanning. Critical: Pipeline > 30 min without parallelization | no failure notification | missing artifact versioning. High: No caching strategy | incomplete environment parity | missing matrix testing. Medium: Inconsistent naming | missing documentation for manual steps.
Questions: Infrastructure fully codified? Modules reusable and parameterized? State management secure (encrypted, locked)? Security best practices (least privilege, encryption)? Idempotent and reproducible?
Blocker: Secrets in version control | no state management | production credentials in code. Critical: No encryption at rest | overly permissive IAM | missing network security. High: Hardcoded values | missing resource tagging | no cost estimation. Medium: Inconsistent module structure | missing input variable validation.
Questions: Strategy appropriate for risk profile? Rollback documented? Health checks and readiness probes defined? Gradual traffic shifting with automatic rollback? Database migrations backward compatible?
Blocker: No rollback strategy | no health checks | breaking changes without safeguards. Critical: Single-shot deployment for critical services | no canary/blue-green for high-traffic | missing pod disruption budgets. High: Rollback not tested | no gradual traffic shifting | no pre-deployment validation. Medium: Incomplete manual step documentation | no feature flags for risky features.
Questions: SLOs defined with specific targets? All four golden signals monitored? Distributed tracing configured? Alerts SLO burn-rate based? Dashboards for investigation?
Blocker: No SLOs defined | no error rate monitoring | no alerting strategy. Critical: No latency monitoring (p50/p90/p99) | symptom-based alerts | no log-metric-trace correlation. High: Incomplete metric coverage | alert thresholds misaligned with SLOs | no runbook links. Medium: Unclear dashboard organization | missing error budget tracking.
test cases passed, vs 5 / 22 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.