CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

azure-advisor-cost-optimization

Analyze Azure Advisor Cost/IdleResources findings and prevalidate deletion safety, including Service Groups. WHEN: "find unused Azure resources", "what resources am I paying for but no longer using", "idle-resource savings", "historical idle-resource savings", "are these idle resources safe to delete". Generic Cost, other subcategories, and cross-category requests use azure-advisor.

Quality

90%

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.

An exemplary instruction-only router skill: lean shared rules, verified one-level-deep references, and safety gating for deletion-related work. The lower scores reflect that executable detail (worked examples, per-flow step sequences with feedback loops) is fully delegated to reference files rather than surfaced even briefly in the body.

Suggestions

Inline one minimal worked example in the body (e.g., a one-line discovery call with category=Cost, sub-category=IdleResources and its expected savings fields) so the body is self-sufficient for the most common case.

Add a short enumerated step list per major flow (e.g., Discovery: read workflow.md → expand types → read scope-resolution.md → run scoped query) so the top-level sequence is explicit rather than implied by the routing table.

DimensionReasoningScore

Conciseness

The body is dense, imperative, and assumes competence: "Never substitute billing, inventory or runtime KQL", "Missing amounts are Unavailable, not zero; numeric zero stays zero" — every line is a domain rule Claude could not infer, with no padding or explanations of known concepts. Nothing can be trimmed without losing rule content.

5 / 5

Actionability

Concrete, executable directives are present: exact tool parameters (`category=Cost` and `sub-category=IdleResources`), named legacy fields to avoid ("legacy annualSavingsAmount/savingsAmount"), a required output token ("`Pricing basis: <basis>`"), and a routing table mapping each flow to a specific reference file. It is not a 5 because the body itself contains no worked example — examples are deferred entirely to references/examples.md — so the body alone is not copy-paste ready.

4 / 5

Workflow Clarity

A clear sequence is present (read matching reference per flow → apply shared rules → format response) with explicit checkpoints: "If a required file is unavailable, report it and stop the affected flow", "Visibly show results/proposals before dependent questions", and deletion safety is gated through the Read-only prevalidation reference. It is not a 5 because the per-flow step sequences and validate/retry feedback loops live in the reference files rather than being laid out in the body, leaving the top-level sequence implicit rather than enumerated.

4 / 5

Progressive Disclosure

The body is a lean overview with a quick-reference table routing each flow to a well-signaled, one-level-deep reference; all 10 referenced paths exist in the bundle, the `#read-only-prevalidation` anchor matches a real heading in selection-and-handoff.md, and references link only to siblings or back to SKILL.md (verified: no nested second-level references). Navigation is easy via the table and the README index.

5 / 5

Total

18

/

20

Passed

Description

90%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: third-person voice, an explicit WHEN clause with five natural trigger phrasings, and explicit boundary routing to a sibling skill. The only weakness is that the 'what' covers just two actions, leaving the full capability set (savings reporting, tables, lifecycle, state updates) implicit in the body.

DimensionReasoningScore

Specificity

The description states exactly two concrete actions — "Analyze Azure Advisor Cost/IdleResources findings and prevalidate deletion safety" — with a scope detail ("including Service Groups"), matching the anchor for naming a domain with 1-2 concrete actions but not comprehensive coverage. It is not a 4 because it does not list several actions (e.g., savings summarization, table/report formatting, state updates that the body actually covers).

3 / 5

Completeness

It explicitly answers both what ("Analyze Azure Advisor Cost/IdleResources findings and prevalidate deletion safety") and when (explicit "WHEN:" clause with concrete trigger phrases). This matches the top anchor exactly; a 4 would require the when-clause to be less explicit or lack concrete triggers.

5 / 5

Trigger Term Quality

The WHEN clause quotes five natural user phrasings — "find unused Azure resources", "what resources am I paying for but no longer using", "idle-resource savings", "historical idle-resource savings", "are these idle resources safe to delete" — covering synonyms and variations users would actually say. It does not fall to 4 because no common natural phrasing for this need is obviously missing.

5 / 5

Distinctiveness Conflict Risk

It carves a clear niche (Advisor Cost/IdleResources findings and deletion-safety prevalidation) and actively reduces conflict by routing "Generic Cost, other subcategories, and cross-category requests use azure-advisor". Trigger phrases are distinct to this niche, so conflict risk is minimal.

5 / 5

Total

18

/

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

Path

plugins/azure-advisor/skills/azure-advisor-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.