CtrlK
BlogDocsLog inGet started
Tessl Logo

cost-governance

Govern Azure costs with budgets, alerts, tags, and policy restrictions. WHEN: "Azure budget health", "configured budget overrun", "list Azure budgets", "create Azure budget", "budget alerts", "budget coverage", "missing CostCenter tags", "allowed VM SKUs", "allowed Azure regions", "would this SKU be denied", "cost guardrails". DO NOT USE FOR: planning-target forecasts, bill investigations, pricing, rightsizing, or commitments.

73

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Medium

Suggest reviewing before use

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.

An exemplary lean SKILL.md: no filler, only non-obvious operational rules, and a clean one-level-deep reference structure verified against the actual bundle. The shared weaknesses are mild — a couple of vague tool pointers and operational sequencing/validation living in the reference files rather than in the body.

Suggestions

Replace the vague 'Cost tools' pointer in the budget-setup row of the Quick Reference with the concrete tool names (e.g., 'query_costs', 'create_budget') so every row names explicit tools.

Add one short inline example workflow for the most common intent (e.g., budget health check) with an explicit validate/report checkpoint, so the body demonstrates the expected sequence without relying on references.

In the Workflow section, state explicitly that writes must be confirmed against the reference workflow's checklist before execution, giving the write path a visible validation checkpoint.

DimensionReasoningScore

Conciseness

Lean and efficient — every line carries non-obvious, project-specific rules ('Never transform MCP results in a shell or interpreter', 'Report gaps without implying budgets cap spend', 'Never sum or compare across currencies') with zero padding and no explanation of concepts Claude already knows. Nothing to trim.

5 / 5

Actionability

As an instruction-only skill it names concrete tools ('list_budgets', 'forecast_costs', 'query_costs', 'create_budget'), required write parameters ('confirmed scope, amount, thresholds, and recipients'), and a specific error-action table ('Retry once; then stop with the trace ID'). Falls short of 5 because some guidance is vague ('Cost tools' in the setup row) and no inline example covers a common case end-to-end, leaving execution details entirely to references.

4 / 5

Workflow Clarity

The Quick Reference table maps intents to workflows and primary tools, and the 5-step Workflow includes checkpoints ('Distinguish access failures from empty results', 'Retry once; then stop'). Not 5 because the body's steps are general rules rather than a fully sequenced operation — the actual sequences are delegated to references, and there is no explicit validate-before-proceed loop in the body itself.

4 / 5

Progressive Disclosure

A clear overview with a well-signaled Quick Reference linking to four real reference files (budget-health.md, budget-setup.md, guardrails.md, tool-fallback.md — all verified present), each exactly one level deep, with an intent-based navigation table. Matches the anchor-5 structure of concise overview plus well-organized one-level references.

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 description: concrete domain statement, comprehensive natural trigger phrases, explicit when-to-use and when-not-to-use boundaries, and low conflict risk. The only minor weakness is that the capability list is terse rather than enumerating each action. No first/second-person voice is used, so no voice penalty applies.

DimensionReasoningScore

Specificity

Names the domain ('Govern Azure costs') and several concrete capability areas ('budgets, alerts, tags, and policy restrictions'), with operations like 'list Azure budgets', 'create Azure budget', and 'allowed VM SKUs' surfaced via triggers. Falls just short of anchor 5 because the capability list itself is compact rather than comprehensive (e.g., no explicit alert-creation or tag-remediation actions stated as verbs).

4 / 5

Completeness

Explicitly answers both what ('Govern Azure costs with budgets, alerts, tags, and policy restrictions') and when (a 'WHEN:' clause listing concrete trigger phrases), and adds a 'DO NOT USE FOR' exclusion list. Matches the anchor-5 example structure exactly, and no 'when' weakness justifies 4.

5 / 5

Trigger Term Quality

Comprehensive natural phrasings users would actually say: 'Azure budget health', 'configured budget overrun', 'budget alerts', 'missing CostCenter tags', 'allowed VM SKUs', 'would this SKU be denied', and 'cost guardrails' — including question-style variants. Clearly above anchor 4's 'a few natural terms missing'; nothing obvious is absent.

5 / 5

Distinctiveness Conflict Risk

A clear Azure cost-governance niche with distinct triggers, and the explicit exclusion of adjacent skills ('planning-target forecasts, bill investigations, pricing, rightsizing, or commitments') minimizes overlap with pricing/rightsizing/forecasting skills. Minimal conflict risk.

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
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.