CtrlK
BlogDocsLog inGet started
Tessl Logo

cost-estimation

Forecast Azure spend and price planned resources or workloads. WHEN: "forecast Azure spending", "project next month cost", "compare forecast to my planning target", "how much will Azure cost", "estimate VM cost", "compare storage tiers", "compare Azure regions", "retail price", "EA rate card", "negotiated pricesheet". DO NOT USE FOR: configured budget health or alerts, bill analysis, cost spikes, rightsizing, or commitments.

71

Quality

89%

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-structured overview: token-efficient, real one-level-deep references, and concrete tool/error guidance. The minor deductions come from slightly underspecified in-body instructions ("Pricing tools", "label every value type") that rely on referenced files to complete the picture.

Suggestions

Replace the generic "Pricing tools" entry in the Quick Reference table with the specific tool names (e.g., get_retail_prices or the pricesheet tools) so the overview is self-contained.

Briefly define what "label every value type" means in the Workflow section (or one example), so the instruction is actionable before the referenced workflow file is loaded.

DimensionReasoningScore

Conciseness

The ~40-line body is all tables and terse operational steps — no concept explanations, no padding; every line (tool table, workflow steps, error actions) earns its place.

5 / 5

Actionability

Names concrete tools (forecast_costs, get_retail_prices, start_pricesheet_download) and concrete error actions ("Retry once; then report the trace ID", "Never combine currencies"), but "Pricing tools" in the Quick Reference is generic and "label every value type" is underspecified within the body — minor gaps consistent with anchor 4.

4 / 5

Workflow Clarity

A clear 4-step sequence with an Error Handling table providing per-failure recovery actions (a retry/report feedback loop), but checkpoints are terse and validation detail is delegated to referenced workflow files — most checkpoints present with minor gaps, anchor 4.

4 / 5

Progressive Disclosure

A short overview with a Quick Reference table mapping intent to workflow file to tools; all three referenced paths (references/cost-forecast/workflow.md, references/pricing-estimate.md, references/tool-fallback.md) exist and are one level deep — clear overview with well-signaled references, anchor 5.

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: explicit what/when with rich natural trigger phrases and effective negative-boundary exclusions. The only gap is that the capability statement itself lists just two actions, keeping specificity at the 1-2-actions anchor.

DimensionReasoningScore

Specificity

"Forecast Azure spend and price planned resources or workloads" names the domain with exactly two concrete actions, matching the anchor for 1-2 concrete actions but not comprehensive coverage; the remaining detail lives in trigger phrases rather than stated capabilities.

3 / 5

Completeness

It explicitly answers what ("Forecast Azure spend and price planned resources or workloads") and when (a WHEN clause with concrete trigger phrases), and adds DO NOT USE FOR exclusions — matching the anchor that requires both what and when with concrete triggers.

5 / 5

Trigger Term Quality

The WHEN list gives comprehensive natural user phrasings — "forecast Azure spending", "project next month cost", "how much will Azure cost", "estimate VM cost", "compare storage tiers" — plus synonym variants covering retail, EA rate card, and negotiated pricesheet.

5 / 5

Distinctiveness Conflict Risk

A clear Azure-cost niche with distinct triggers, and the "DO NOT USE FOR: configured budget health or alerts, bill analysis, cost spikes, rightsizing, or commitments" list explicitly fences off adjacent cost-management skills, minimizing wrong-skill triggering.

5 / 5

Total

18

/

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.