Install
$ agentstack add skill-kentoshimizu-sw-agent-skills-cost-optimization-cloud ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Cost Optimization Cloud
Overview
Use this skill to produce actionable cloud cost reductions that preserve service quality and operational safety.
Scope Boundaries
- Use this skill when the task matches the trigger condition described in
description. - Do not use this skill when the primary task falls outside this skill's domain.
Inputs To Gather
- Cost breakdown by service/account/environment/tag.
- Utilization telemetry (CPU, memory, I/O, request profile, idle windows).
- Reliability and performance guardrails (SLO, latency, availability).
- Contractual/compliance constraints and migration limits.
Deliverables
- Prioritized optimization backlog with savings estimate and confidence.
- Risk-assessed rollout sequence.
- Verification plan for savings and regression detection.
- Reversal plan for harmful optimizations.
Optimization Decision Buckets
waste removal: idle resources, overprovisioned instances, orphaned storage.efficiency: rightsizing, autoscaling policy tuning, query/request optimization.pricing: reservations/savings plans, spot usage where safe.architecture: storage tiering, cache strategy, async/off-peak processing.
Quick Example
- Observation: cluster CPU < 15% for 14 days, memory < 25%.
- Action: downsize node class + adjust autoscaling floor.
- Guardrail: p95 latency and error rate must remain within pre-change bounds.
- Rollback: revert size within one deployment window if guardrail breaches.
Quality Standard
- Every recommendation includes expected savings, confidence, and risk.
- Recommendations explicitly state SLO/compliance impact.
- Rollout uses low-blast-radius sequence.
- Post-change metrics and rollback triggers are pre-defined.
Workflow
- Identify top cost drivers with workload attribution.
- Generate candidate actions by decision bucket.
- Quantify savings, risk, and implementation effort.
- Sequence actions by ROI and operational safety.
- Execute incrementally with guardrail monitoring.
- Validate realized savings and capture lessons.
Failure Conditions
- Stop when savings action violates SLO/compliance constraints.
- Stop when cost attribution confidence is too low for safe action.
- Escalate when forecast variance remains unexplained after top-driver analysis.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: KentoShimizu
- Source: KentoShimizu/sw-agent-skills
- License: Apache-2.0
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.