monte-carlo-data/mc-agent-toolkit / skills/storage-cost-analysis
monte-carlo-storage-cost-analysis
VerifiedAnalyze a warehouse for stale, unused, or redundant tables via the analyze_storage_costs MCP tool. Classifies waste patterns and table categories, computes safety tiers, and handles category drill-downs and lineage follow-ups.
| File | Kind | Size |
|---|---|---|
| README.md | markdown | 1.9 KB |
| SKILL.md | skill md | 8.7 KB |
| references/output-structure.md | markdown | 4.5 KB |
README.md
View on GitHub# Storage Cost Analysis Skill
Identifies storage waste patterns and recommends safe cleanup actions with cost savings estimates.
## What it does
- Delegates analysis to the `analyze_storage_costs` MCP tool, which fetches candidates, classifies waste patterns and table categories, and computes safety tiers
- Presents the pre-formatted summary + Top-N table verbatim
- Handles follow-ups: drill into a specific category without re-fetching, or run a lineage check for a specific table
- Never recommends removing tables with downstream consumers without explicit verification
## Supported warehouses
Snowflake, BigQuery, Redshift, and Databricks. Other warehouse types are out of scope.
## MCP Tools Required
Connect to Monte Carlo's MCP server (`mcp.getmontecarlo.com/mcp`). The skill uses these tools:
| Tool | Purpose |
|------|---------|
| `analyze_storage_costs` | Runs the full pipeline: candidates → waste patterns → categories → safety tiers → formatted output |
| `get_asset_lineage` | Follow-up lineage checks for a specific table before removal |
## Example prompts
- "Which tables are wasting storage in our Snowflake warehouse?"
- "Find unused tables I can safely drop"
- "How much could we save by cleaning up stale tables?"
- "Are there any zombie tables in the analytics schema?"
- Follow-up: "show me the temporary tables" / "what about production?"
- Follow-up: "is it safe to remove `db.schema.table`?"
## Waste patterns and categories
The `analyze_storage_costs` tool classifies each candidate into:
- A **waste pattern**: Unread, Write-only, Dead-end, Static waste, Zombie, Other stale
- A **table category**: Temporary/Staging, Archive/Snapshot, Production, Other
The skill itself does not re-implement the taxonomy — the server owns it. See `references/output-structure.md` for the output contract (region markers, category keys, safety-signal glossary).
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |