CtrlK
BlogDocsLog inGet started
Tessl Logo

cost-analysis

Analyze actual Azure spend, bill changes, and AKS or AI costs. WHEN: "Azure cost breakdown", "most expensive resources", "why did my bill increase", "cost spike", "unexpected charge", "Cosmos DB charges", "Foundry model costs", "AKS cluster cost", "namespace cost", "enable AKS cost analysis", "idle AKS capacity". DO NOT USE FOR: forecasts, pricing estimates, rightsizing, commitments, or budgets.

72

Quality

91%

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

86%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 lean, well-routed router skill: the body is a tight index of intents to verified, one-level-deep workflow references with concrete tool routing and per-error handling. The main gap is that the body contains no worked example of an actual tool call, leaving the first concrete invocation detail one file away.

Suggestions

Add one minimal example of a concrete tool invocation (e.g., a representative query_costs request with scope, timeframe, and groupBy) directly in the body so the most common case is actionable without loading a reference file.

Make the workflow's verification step explicit as a checkpoint (e.g., a 'verify completeness: check row counts against top limits and label incomplete results' step) instead of spreading validation across steps 3-4 and the error table.

State in the Quick Reference which workflow to load for the unreferenced-from-SKILL.md paths (aks-anomaly.md, aks-enablement.md) or mention that AKS anomaly/enablement guidance is nested inside the AKS workflow, so the router table covers the full bundle surface.

DimensionReasoningScore

Conciseness

The ~35-line body is entirely operational: an intent-to-workflow routing table, tool-preference rules, a 5-step workflow, and an error table. No concept explanations, no padding; every token earns its place, matching the lean-and-efficient anchor.

5 / 5

Actionability

Concrete tool names ("query_costs", "query_aks_costs", Resource Graph) and specific executable rules ("Never transform MCP results in a shell or interpreter; request tool-side totals, grouping, sorting, or bounded follow-up queries") plus per-error actions. It is short of anchor 5 because the body itself contains no example invocation or request shape — those details are deferred entirely to the reference files — while clearly exceeding anchor 3's pseudocode/vague level.

4 / 5

Workflow Clarity

A clear 5-step sequence (confirm scope → load matching workflow → avoid shell transforms → respect row limits → separate measured from inferred) with an error-handling table acting as checkpoints ("Retry once; then stop with the trace ID"). This is a read-only query skill so the destructive/batch validation cap does not apply, but steps 3-5 are constraints rather than explicit validate-and-recover feedback loops, placing it at anchor 4 rather than 5.

4 / 5

Progressive Disclosure

The Quick Reference table routes each intent to a one-level-deep workflow file; all five referenced paths were verified to exist, and every bundle file is reachable (including aks-anomaly.md and aks-enablement.md via the workflow files, and the cost-query sub-files via cost-query/workflow.md, which itself contains real content rather than being a pointer-only stub). Content is appropriately split with easy navigation, matching the clear-overview anchor.

5 / 5

Total

18

/

20

Passed

Description

95%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 third-person description: concrete WHAT, explicit WHEN with natural trigger phrases covering services and synonyms, and an explicit exclusion boundary. The only minor gap is the limited action-verb variety ("Analyze") covering what is otherwise comprehensive domain coverage.

DimensionReasoningScore

Specificity

"Analyze actual Azure spend, bill changes, and AKS or AI costs" names the domain plus several concrete analysis targets (spend, bill changes, AKS, AI costs) and specific sub-services ("Cosmos DB charges", "Foundry model costs"). It falls short of anchor 5 because the action vocabulary is narrow (only "Analyze") rather than a comprehensive set of distinct actions, and exceeds anchor 3 because more than 1-2 concrete actions/domains are explicitly listed.

4 / 5

Completeness

It explicitly answers both WHAT ("Analyze actual Azure spend, bill changes, and AKS or AI costs") and WHEN (concrete "WHEN:" trigger phrases), and further adds explicit exclusions ("DO NOT USE FOR: forecasts, pricing estimates, rightsizing, commitments, or budgets"). This clearly matches the anchor for explicit what-and-when with concrete trigger phrases.

5 / 5

Trigger Term Quality

The WHEN clause provides comprehensive natural user phrases with synonyms and service-specific variants: "why did my bill increase", "cost spike", "unexpected charge", "most expensive resources", "AKS cluster cost", "namespace cost", "enable AKS cost analysis", "idle AKS capacity". These are exactly the phrases a user would naturally say, matching the comprehensive-coverage anchor.

5 / 5

Distinctiveness Conflict Risk

A clear Azure-cost niche with service-specific triggers (Cosmos DB, Foundry, AKS) and an explicit DO-NOT-USE boundary separating it from forecasting/rightsizing/budget skills. Conflict risk is minimal, matching the distinct-niche anchor rather than anchor 4 (which requires residual overlap with closely related skills).

5 / 5

Total

19

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 1 deeper-than-1-level

Warning

referenced_paths_exist

Referenced path issues: 1 deeper-than-1-level

Warning

Total

14

/

16

Passed

Repository
microsoft/GitHub-Copilot-for-Azure
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.