Finops Analysis
Use when analyzing cloud spending, cost attribution, or unit economics. Covers cost allocation tagging, reserved capacity planning, right-sizing, spot/preemptible usage, cost anomaly detection, and showback/chargeback models. Do not use for general infrastructure cost modeling (use cost-analysis) or deployment strategy (use deployment-plan).
Install
$ agentstack add skill-dtsong-my-claude-setup-finops-analysis ✓ 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.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-dtsong-my-claude-setup-finops-analysis) 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
FinOps Analysis
Purpose
Evaluate cloud spending efficiency and produce actionable recommendations for cost optimization across compute, storage, network, and managed services. Align cloud costs with business value through unit economics and cost attribution.
Scope Constraints
Reads cloud billing data, resource configurations, and usage metrics for cost analysis. Does not modify infrastructure or execute provisioning commands. Does not access financial systems beyond cloud cost APIs.
Inputs
- Cloud provider(s) in scope (AWS, GCP, Azure, multi-cloud)
- Current monthly spend breakdown or billing export
- Application architecture overview (compute, storage, databases, networking)
- Business metrics for unit economics (users, transactions, requests)
- Any existing cost optimization efforts or commitments
Input Sanitization
No user-provided values are used in commands or file paths. All inputs are treated as read-only analysis targets.
Procedure
Progress Checklist
- [ ] Step 1: Map cost allocation and tagging
- [ ] Step 2: Analyze compute right-sizing
- [ ] Step 3: Evaluate commitment-based discounts
- [ ] Step 4: Assess spot/preemptible opportunities
- [ ] Step 5: Calculate unit economics
- [ ] Step 6: Detect cost anomalies and waste
Step 1: Map Cost Allocation and Tagging
- Inventory all cloud accounts, projects, and resource groups.
- Verify tagging strategy covers: team, environment, service, cost center.
- Identify untagged or mis-tagged resources.
- Map spend to business units or product features for showback/chargeback.
- Flag shared resources that need allocation rules (e.g., shared databases, networking).
Step 2: Analyze Compute Right-Sizing
- Review CPU and memory utilization for compute instances over 14+ days.
- Identify over-provisioned instances (avg utilization Compaction resilience: If context was lost, re-read the Inputs section to identify the analysis scope, check the Progress Checklist for completed steps, then resume from the earliest incomplete step.
Output Format
Cost Optimization Summary
| Category | Current Spend | Optimized Spend | Savings | Effort | |----------|--------------|-----------------|---------|--------| | Right-sizing | $X/mo | $Y/mo | Z% | Low/Med/High | | Commitments | ... | ... | ... | ... | | Spot/Preemptible | ... | ... | ... | ... | | Waste elimination | ... | ... | ... | ... |
Unit Economics
| Metric | Current | At 2x Scale | At 5x Scale | |--------|---------|-------------|-------------| | Cost per user | ... | ... | ... | | Cost per transaction | ... | ... | ... |
Handoff
- Hand off to cost-analysis for detailed infrastructure cost modeling of new architectures.
- Hand off to deployment-plan if cost optimization requires migration or redeployment.
Quality Checks
- [ ] All cloud accounts and resource groups inventoried
- [ ] Tagging gaps identified with remediation plan
- [ ] Right-sizing recommendations backed by 14+ day utilization data
- [ ] Commitment coverage modeled at multiple levels
- [ ] Spot candidates verified for fault tolerance
- [ ] Unit economics calculated with current business metrics
- [ ] Idle resources and waste identified with estimated savings
- [ ] Total savings opportunity quantified with effort estimates
Evolution Notes
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: dtsong
- Source: dtsong/my-claude-setup
- License: MIT
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.