CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

cost-optimization

Audit and reduce infrastructure and tooling costs without sacrificing reliability or velocity. Use this skill when reviewing monthly cloud or SaaS spend, finding unused resources, rightsizing infrastructure, negotiating vendor contracts, deciding what to consolidate, or planning for budget cuts. Triggers on cost optimization, cloud spend, SaaS spend, rightsizing, unused resources, FinOps, infrastructure audit, vendor consolidation, budget cut, cost review. Also triggers when finance flags rising costs or when a contract renewal is up.

Quality

88%

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

The canonical home for this skill is cost-optimization in rampstackco/claude-skills

SKILL.md
Quality
Evals
Security

Quality

Content

75%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.

A strong, well-structured instructional skill: a coherent 5-lever framework, a 10-step sequenced workflow with checkpoints, concrete thresholds, and a properly linked one-level reference file. The main improvements are removing cross-section repetition, adding an explicit error-recovery step for risky changes, and moving the category-opportunities and failure-patterns detail into reference files.

Suggestions

Consolidate duplicated guidance: reserved/spot pricing, dev/staging shutdown, and renewal negotiation each appear in the lever definitions, the workflow, and 'Common opportunities by category' — state each once and let the category section reference the levers instead of restating them.

Add an explicit error-recovery step to the execute/plan workflow (e.g., 'if monitoring shows degraded performance or errors after a rightsizing change, revert to the previous configuration and re-plan'), which would close the feedback-loop gap for destructive/batch changes.

Move 'Common opportunities by category' and 'Failure patterns' into references/ files (like the existing cloud-audit-checklist.md) and keep SKILL.md to the framework and workflow, trimming the inline body well under 300 lines.

DimensionReasoningScore

Conciseness

The prose is lean and assumes Claude's competence (no CDN or reserved-instance tutorials), but items repeat across sections — reserved/spot pricing appears in Lever 3 and again under Hosting; dev/staging shutdown in Step 6 and again under Hosting; renewal negotiation in Lever 4, Step 9, and SaaS. The 'Pre-pandemic... Post-pandemic' aside is time-sensitive commentary that could also be trimmed.

4 / 5

Actionability

Concrete specifics throughout ('Start the conversation 60-90 days before renewal', '12 months minimum', '1-3 year commitments at 30-70% discount', the 2x2 effort/savings prioritization), but the data-pull step stays at the hint level ('the billing console and cost-explorer tools') rather than naming executable commands, leaving a minor gap.

4 / 5

Workflow Clarity

Ten clearly sequenced steps with real checkpoints ('Monitor for unexpected impact', 'Confirm cost reduction in next billing cycle', 'Test in staging', risk-tiered rightsizing guidance). It falls short of the 5-anchor only because no explicit error-recovery loop states what to do when monitoring reveals unexpected impact from a change.

4 / 5

Progressive Disclosure

Well-sectioned body with one clearly signaled, one-level-deep reference (references/cloud-audit-checklist.md, present in the bundle, accurately described). Minor gap: roughly 340 lines inline, with the ~50-line 'Common opportunities by category' and 'Failure patterns' sections being prime candidates to offload to reference files.

4 / 5

Total

16

/

20

Passed

Description

96%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.

An exemplary description: explicit what and when clauses, comprehensive natural trigger terms including synonyms, and a list of concrete capabilities spanning the skill's full framework. The only weakness is slight overlap risk between 'infrastructure audit'/'negotiating vendor contracts' and adjacent skills such as vendor evaluation or performance optimization.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — 'Audit and reduce infrastructure and tooling costs', 'reviewing monthly cloud or SaaS spend', 'finding unused resources', 'rightsizing infrastructure', 'negotiating vendor contracts', 'deciding what to consolidate', 'planning for budget cuts' — covering all of the skill's levers comprehensively, matching the 5-anchor for multiple specific concrete actions.

5 / 5

Completeness

It explicitly answers both questions: the 'what' ('Audit and reduce infrastructure and tooling costs without sacrificing reliability or velocity') and the 'when' ('Use this skill when reviewing monthly cloud or SaaS spend, finding unused resources, rightsizing infrastructure, negotiating vendor contracts...') with concrete trigger phrases — the exact 5-anchor pattern.

5 / 5

Trigger Term Quality

'Triggers on cost optimization, cloud spend, SaaS spend, rightsizing, unused resources, FinOps, infrastructure audit, vendor consolidation, budget cut, cost review' provides comprehensive natural-term coverage including synonyms (FinOps, cost review, budget cut), plus scenario triggers ('finance flags rising costs', 'when a contract renewal is up').

5 / 5

Distinctiveness Conflict Risk

The cost niche is clear with distinct triggers (FinOps, rightsizing, cloud spend), but 'infrastructure audit' and 'negotiating vendor contracts' carry minor overlap risk with closely related skills — the body itself names vendor-evaluation and performance-optimization as neighbors. Fits the 4-anchor 'mostly distinct; minor overlap risk' better than the 5-anchor.

4 / 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

rampstackco/claude-skills

Path

dist/codex/.agents/skills/cost-optimization/SKILL.md

Reviewed

Table of Contents

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.