azure-artifacts
**UTILITY SKILL** — Artifact template structures, H2 compliance rules, and documentation styling for agent outputs (Steps 1-7). WHEN: "generate artifact", "check H2 structure", "artifact template", "step 7 as-built". USE FOR: generating any agent artifact, checking H2 structure compliance. DO NOT USE FOR: Azure resource configuration (use azure-defaults), Bicep/Terraform patterns (use azure-bicep-patterns or terraform-patterns).
72
87%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a well-structured skill description that excels in completeness and distinctiveness, with explicit WHEN, USE FOR, and DO NOT USE FOR clauses that make routing decisions clear. The trigger terms are specific and natural for the domain. The main weakness is that the specific capabilities could be more concretely articulated — the description tells you the domain but is somewhat vague about exactly what actions it performs beyond generating and checking.
Suggestions
Make the capabilities more concrete by specifying exact actions, e.g., 'Generates artifact documents from templates, validates H2 heading compliance, applies documentation styling' rather than listing abstract nouns like 'structures' and 'rules'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names a domain (artifact templates, H2 compliance, documentation styling) and some actions ('generate artifact', 'check H2 structure'), but the actual concrete actions are somewhat vague — 'artifact template structures' and 'documentation styling for agent outputs' don't clearly specify what operations are performed (e.g., create, validate, format). | 2 / 3 |
Completeness | The description clearly answers both 'what' (artifact template structures, H2 compliance rules, documentation styling for agent outputs Steps 1-7) and 'when' (explicit WHEN clause with trigger phrases, USE FOR clause, and even a DO NOT USE FOR clause that helps with routing). | 3 / 3 |
Trigger Term Quality | The description includes multiple natural trigger terms users might say: 'generate artifact', 'check H2 structure', 'artifact template', 'step 7 as-built'. These are specific phrases that would naturally appear in user requests within this domain, and the WHEN clause explicitly lists them. | 3 / 3 |
Distinctiveness Conflict Risk | The description is highly distinctive with its specific niche (artifact templates, H2 compliance, Steps 1-7) and explicitly includes a DO NOT USE FOR clause that differentiates it from azure-defaults, azure-bicep-patterns, and terraform-patterns, significantly reducing conflict risk. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-crafted skill that provides clear, actionable guidance for generating structured artifacts. Its strengths are the explicit workflow steps, concrete validation commands with documented exit codes, and excellent progressive disclosure via the reference index. Minor verbosity around the repeated 'agents should not invoke lint directly' warnings and some redundancy between sections slightly reduce token efficiency.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient and well-structured with tables and lists, but some sections are slightly verbose — e.g., the 'Automated Validation' section explains the pre-commit hook relationship twice (once in Steps and once in its own section), and the repeated warnings about not invoking lint scripts directly could be consolidated. | 2 / 3 |
Actionability | Provides concrete, executable commands (npm run check:h2-order, specific file paths), clear DO/DON'T rules, exact placeholder syntax, a numbered step-by-step workflow, and a quality checklist. The guidance is specific and copy-paste ready. | 3 / 3 |
Workflow Clarity | The 7-step artifact generation flow is clearly sequenced with explicit validation (step 7 delegates to pre-commit hook, fast H2-order sanity check available). The exit code semantics (0/1/2) provide clear feedback loops, and the revision workflow is referenced for error recovery scenarios. | 3 / 3 |
Progressive Disclosure | Excellent progressive disclosure: the SKILL.md serves as a clear overview with a well-organized Reference Index table pointing to one-level-deep template files. Each step's detailed template lives in `references/` and is loaded on demand, with clear signaling of when to load each reference. | 3 / 3 |
Total | 11 / 12 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 — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- jonathan-vella/azure-agentic-infraops
- Commit
05d7617
- 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.