Works with
Packaged from the source skill for Claude, Codex and 4 more.
About this skill
Cloud FinOps helps an engineering or finance team investigate cloud costs from exported billing data. Alireza Rezvani’s skill includes local Python checks for allocation, commitment economics, anomalies and cost per business unit, using explicit columns and assumptions rather than cloud-account write access.
Provide a compatible CSV export, required allocation tags and any daily business-unit counts. The reports identify rows and groups to investigate. They are not invoice reconciliation, guaranteed savings or instructions to buy commitments; export quality, currency consistency and negotiated pricing affect the interpretation.
Use this skill when
- Cloud spend needs an owner and the team wants to distinguish missing tags from genuinely shared costs.
- Existing commitments may be under-used before any new purchase is considered.
- A cost increase needs comparison with historical variation and the amount of business activity it supported.
What it can do
- Measure allocation coverage using effective cost, highlight inconsistent tag values and list unallocated resources.
- Compare commitment utilization, coverage and effective savings, including unused commitment cost and a conservative uncovered-usage floor.
- Flag daily anomalies using a rolling median, median absolute deviation and explicit relative and monetary thresholds, then compare cost per unit across the period.
Typical workflows
- Validate the export columns, dates and currency, and agree which tags and shared-cost allocation rules are meaningful for the organization.
- Review allocation and commitment reports with the relevant owners; treat targets and threshold defaults as policy choices.
- Investigate anomaly groups against deployments and workload changes, using enough history for a baseline. Have the responsible team approve any remediation or purchasing decision separately.
What is inside the skill
Section headings from the original SKILL.md (about 499 words of instructions). Read the full text in the source repository before installing.
- Workflow
- Hard rules
- Scripts
- References and assets
Bundled files
assets/finops_review_template.mdassets/focus_export.example.csvreferences/anomalies_and_unit_economics.mdreferences/commitments_and_esr.mdreferences/focus_and_allocation.mdscripts/allocation_check.pyscripts/commitment_check.pyscripts/cost_anomaly.pyscripts/focus_common.pyLICENSE
Example prompts
- Review this FOCUS-shaped export for missing team and environment tags. Separate shared costs from unowned resources and report coverage using effective cost without changing tags.
- Analyze our existing commitment rows for utilization, unused cost and coverage. Show all pricing assumptions and explain why a coverage gap alone is insufficient to justify a purchase.
- Compare daily cloud cost with our orders-per-day CSV. Identify anomalies using a 14-day baseline, show the thresholds and distinguish growth in workload from worsening cost per order.
How to install Cloud Finops
Claude Packaged
- Download the Claude package from the skill page. The ZIP contains one folder named after the skill, with SKILL.md and any bundled reference files.
- For Claude Code, unpack the folder into ~/.claude/skills/ to use it in every project, or into .claude/skills/ inside a repository to share it with your team.
- For Claude apps, upload the ZIP in the Skills section of the capabilities settings.
- Start a new session and describe the task in your own words. Claude picks the skill when the request matches its description.
Codex Packaged
- Download the Codex package. The ZIP contains one folder named after the skill, with SKILL.md and bundled resources.
- Unpack the complete folder into .agents/skills/ inside your repository, or into ~/.agents/skills/ for personal use. Preserve its relative reference-file paths.
- Start a new Codex session and invoke the skill by name or with $skill-name, or describe a matching task.
- AGENTS.md is separate project guidance. The ZIP does not generate or modify that file.
GPT Packaged
- Download the GPT package from the skill page.
- Create or edit a custom GPT (or a ChatGPT project) and paste the contents of SKILL.md into the instructions field.
- Upload the bundled reference files as knowledge so the GPT can consult them.
- Test with one of the example prompts from the skill page and adjust the instructions if your use case differs.
Gemini Packaged
- Download the Gemini package from the skill page.
- For a project, unpack the complete folder into .gemini/skills/ or .agents/skills/. For personal use, use ~/.gemini/skills/ or ~/.agents/skills/.
- Run /skills reload in Gemini CLI, then /skills list to check discovery. There is no need to paste the skill into GEMINI.md.
- Test a matching task and verify the referenced tools and files are available.
Cursor Packaged
- Download the Cursor package from the skill page.
- Unpack the complete skill folder into .cursor/skills/ or .agents/skills/ in your project. For personal local use, ~/.cursor/skills/ and ~/.agents/skills/ are also supported.
- Start a new Cursor session. Type / in Agent chat and select the skill name, or describe a matching task.
- Commit the skill folder and resources for team use. Personal local skills are not automatically available to remote agents or automation runs.
OpenCode Packaged
- Download the OpenCode package from the skill page.
- Unpack the complete folder into .opencode/skills/ in your project, or ~/.config/opencode/skills/ for personal use. OpenCode also supports .agents/skills/ and .claude/skills/ compatibility locations.
- Keep supporting files at their original relative paths. AGENTS.md is separate project-wide guidance and is not generated by this ZIP.
- Start OpenCode in the project and test a matching task with the model and permissions you use.
Permissions & security
Inspect the source, license and declared permissions before use. Read the scripts before running them. Review method
Cloud Finops FAQ
What does the Cloud Finops skill do?
Inspect FOCUS-shaped cloud billing exports for allocation gaps, unused commitments and unusual spend without changing cloud resources or purchasing commitments.
Which AI agents can use Cloud Finops?
Packages for Claude, Codex and 4 more are built from the same source instructions.
How do I install Cloud Finops in Claude?
Download the Claude package from the skill page. The ZIP contains one folder named after the skill, with SKILL.md and any bundled reference files. For Claude Code, unpack the folder into ~/.claude/skills/ to use it in every project, or into .claude/skills/ inside a repository to share it with your team.
Who made Cloud Finops and what is the license?
Cloud Finops is published by Alireza Rezvani under the MIT license. The source is https://github.com/alirezarezvani/claude-skills/tree/main/engineering/cloud-finops/skills/cloud-finops. The catalog keeps the original attribution.
What permissions does Cloud Finops need?
Declared permissions: read project files, write generated skill files. Risk level: low. Check the scripts in the source before running them.