CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

cost-optimization

Optimize cloud costs across AWS, Azure, GCP, and OCI through resource rightsizing, tagging strategies, reserved instances, and spending analysis. Use when reducing cloud expenses, analyzing infrastructure costs, or implementing cost governance policies.

64

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

61%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a well-structured, provider-specific catalog with genuinely useful pricing data and several executable Terraform examples, but it reads more as a reference encyclopedia than an operational skill: generic bullets Claude already knows pad the token cost, and there is no sequenced workflow with validation before destructive cost-cutting actions. Splitting per-provider detail into reference files would improve both conciseness and progressive disclosure.

Suggestions

Add a step-by-step workflow with validation checkpoints (e.g., 1. baseline spend via Cost Explorer, 2. verify utilization metrics before downsizing, 3. confirm no production dependency before deleting idle resources, 4. re-check savings after changes) so destructive cost-cutting actions are guarded.

Trim bullets that restate common knowledge ('Use managed services', 'Implement caching', 'Pay only for execution time') and keep only provider-specific figures and limits Claude cannot reliably recall.

Move the per-provider pricing catalogs (AWS/Azure/GCP/OCI sections) into files like `references/aws-pricing.md` and keep SKILL.md as a decision-oriented overview, mirroring the existing well-signaled `references/tagging-standards.md` pattern.

DimensionReasoningScore

Conciseness

Non-obvious data (savings percentages, terms, provider-specific limits like GCP's 57% CUD) earns its tokens, but many bullets restate knowledge Claude already has — 'Use managed services', 'Implement caching', 'Pay only for execution time', 'Auto-scaling included' — pushing it to the 'mostly efficient but could be tightened' anchor rather than 4.

3 / 5

Actionability

The Terraform blocks (S3 lifecycle, tagging locals, budget alert, autoscaling policy) are executable and complete, but sections like 'Right-Sizing' and 'Azure Advisor Recommendations' offer only abstract bullets ('Analyze resource utilization', 'Downsize over-provisioned resources') with no commands or queries, so it is not fully copy-paste ready across sections.

4 / 5

Workflow Clarity

The four-phase framework (Visibility → Right-Sizing → Pricing Models → Architecture) provides a rough sequence and the closing checklist is a light checkpoint, but there is no explicit ordered procedure, no validation before destructive steps (downsizing, deleting idle resources), and no feedback loop, which caps this dimension at 3 per the rubric's guidance on destructive/batch operations.

3 / 5

Progressive Disclosure

Sections are clearly headed and the one reference (`references/tagging-standards.md`, verified to exist) is explicitly signaled and one level deep, but roughly 300 lines of per-provider catalog (AWS/Azure/GCP/OCI pricing details) are inlined in SKILL.md when they could live in per-provider reference files, keeping it between anchors 3 and 4.

4 / 5

Total

14

/

20

Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description in third-person imperative voice that pairs concrete capabilities with an explicit 'Use when' trigger clause and provider names for distinctiveness. The only weakness is slightly thin synonym coverage in its trigger terms.

DimensionReasoningScore

Specificity

Names four concrete actions — 'resource rightsizing, tagging strategies, reserved instances, and spending analysis' — across four named cloud domains, matching the comprehensive-coverage anchor; the only candidate gap (monitoring) is covered by 'spending analysis', so it does not fall to anchor 4.

5 / 5

Completeness

It explicitly answers both: the 'what' ('Optimize cloud costs across AWS, Azure, GCP, and OCI through resource rightsizing, tagging strategies, reserved instances, and spending analysis') and the 'when' ('Use when reducing cloud expenses, analyzing infrastructure costs, or implementing cost governance policies'), exactly matching the anchor-5 exemplar pattern.

5 / 5

Trigger Term Quality

'reducing cloud expenses', 'analyzing infrastructure costs', and 'implementing cost governance policies' are natural user phrases, but common variations like 'lower my cloud bill', 'cut costs', or 'save money on AWS' are missing, placing it between the good (4) and comprehensive (5) anchors rather than clearly at 5.

4 / 5

Distinctiveness Conflict Risk

The cost-optimization niche is well-defined by named providers plus explicit cost triggers, and it is unlikely to fire for neighboring skills (provisioning, architecture) since those triggers concern spending rather than building; residual overlap is minimal.

5 / 5

Total

19

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

wshobson/agents

Path

plugins/cloud-infrastructure/skills/cost-optimization/SKILL.md

Revision

0874a27

Reviewed

Table of Contents

DiscoveryImplementationValidation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.

Claim skill