Cost optimization
Skill CloudChef/atlasclaw-providers/providers/SmartCMP-Provider/skills/cost-optimization
atlasclaw-providers are the integration with enterprise systems through skills and webhook.
npx -y skills add CloudChef/atlasclaw-providers --skill cost-optimizationAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 14 stars14 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Cost optimization skill. Review SmartCMP FinOps recommendations or analyze one cloud, software, hardware, virtualized, VM, or database resource for platform-confirmed and LLM-inferred savings opportunities. Use active policy evidence, bounded resource cost facts, risk assessment, and conservative saving estimates; remediate only existing findings through native day2 repair and track remediation state.
SKILL.md
7.9 KB, as published. Nobody here has run it
cost-optimization
Use this skill to work through cost optimization recommendations from discovery to remediation tracking.
Workflow
Choose the entry path that matches the user's object:
- Analyze an existing recommendation:
- List recommendations with
list_recommendations.py - Optional:
--with-related-policiesto show related policy counts - Analyze a recommendation with
analyze_recommendation.py - Silently resolve the related
resourceIdthrough datasource../datasource/scripts/list_resource.py - Merge normalized resource
type + propertiesinto the analysis facts - Returns multi-dimensional recommendations (P0/P1/P2 priority)
- Includes risk assessment and best practice guidance
- Shows saving contribution, policy history, and resource operational context
- List recommendations with
- Analyze a resource directly:
- Call
analyze_resource_cost.pywith an exact visible name or recent list#selection - Read resource facts, enabled applicable policy configurations, latest resource executions, and active violations without triggering policy execution
- Use the returned
analysisContractto keep platform facts separate fromllm_potential - Read references/RESOURCE_ANALYSIS.md for VM, AWS RDS, and generic resource reasoning rules
- Call
- Remediate an existing finding through the native day2 repair in
execute_optimization.pyonly after the user explicitly requests it - Track remediation state with
track_execution.py
Analysis Output Enhancement
The analyze_recommendation.py now provides:
- P0 Primary Action: Core recommendation (remediate / configure_platform_policy / manual_review)
- P1 Risk Assessment: Risk level (high/medium/low) with specific warnings
- P1 Configuration Guide: When fixType is missing, explains how to configure day2 repair
- P1 Saving Priority: Contribution percentage to global optimizable amount
- P2 Policy History: Compliance rate trend and violation recurrence count
- Resource Context: Resource type, component type, status, OS, and normalized datasource facts
Safety Boundary
The skill only performs platform-native remediation through:
POST /compliance-policies/violations/day2/fix/{id}
It does not call AWS or Azure APIs directly.
Resource-first analysis is read-only. It must not call:
POST /compliance-policies/executePOST /compliance-policies/violations/day2/fix/{id}
Only an existing platform violation may enter the separate remediation flow. An
llm_potential result is never executable.
Resource Enrichment
This skill should internally reuse the datasource skill's shared
../datasource/scripts/list_resource.py helper whenever a recommendation includes
resourceId.
- Pull resource details before rendering the final analysis output.
- Merge resource status/type/OS and normalized facts into
factsand downstream recommendations. - If resource lookup is unavailable, continue with policy/violation analysis as a best-effort degradation path.