azure-artifacts
Artifact template structures, H2 compliance rules, and documentation styling for agent outputs (Steps 1-7). USE FOR: generating any agent artifact, checking H2 structure compliance. DO NOT USE FOR: Azure resource configuration (use azure-defaults), Bicep/Terraform patterns (use bicep-patterns or terraform-patterns).
85
81%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
75%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 description does well on completeness and distinctiveness by providing explicit USE FOR and DO NOT USE FOR clauses with named alternative skills. However, the specific capabilities could be more concretely listed (e.g., what 'Steps 1-7' entails), and the trigger terms lean toward internal jargon rather than natural user language.
Suggestions
Expand 'Steps 1-7' into brief concrete action descriptions so Claude and users understand the full scope without needing external context.
Add more natural trigger terms a user might say, such as 'format agent output', 'heading structure', 'template for documentation', or 'compliance check'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (artifact templates, H2 compliance, documentation styling) and mentions some actions (generating agent artifacts, checking H2 structure compliance), but the specific actions are not comprehensively listed—'Steps 1-7' is opaque without context. | 2 / 3 |
Completeness | Clearly answers both 'what' (artifact template structures, H2 compliance rules, documentation styling) and 'when' (USE FOR: generating any agent artifact, checking H2 structure compliance), and even includes explicit negative triggers (DO NOT USE FOR) to reduce misuse. | 3 / 3 |
Trigger Term Quality | Includes some relevant terms like 'agent artifact', 'H2 structure compliance', and 'documentation styling', but these are somewhat specialized/internal jargon. Missing more natural user-facing terms a user might say (e.g., 'format output', 'heading structure', 'template'). | 2 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with explicit boundary-setting via DO NOT USE FOR clauses that redirect to specific alternative skills (azure-defaults, bicep-patterns, terraform-patterns), making it very unlikely to conflict with neighboring skills. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
87%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 efficiently communicates artifact generation rules, constraints, and reference navigation. Its strengths are conciseness, actionable rules/checklists, and excellent progressive disclosure via the reference index. The main weakness is the lack of an explicit end-to-end generation workflow with validation feedback loops, which would help Claude sequence the steps correctly and recover from errors.
Suggestions
Add an explicit numbered workflow section (e.g., '## Generation Workflow') that sequences: load template → generate artifact → run validation → fix errors if any → update README, with a clear feedback loop on validation failure.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and well-structured. Every section serves a clear purpose—rules table, DO/DON'T list, placeholder syntax, validation commands, checklist, and reference index. No unnecessary explanations of concepts Claude already knows. | 3 / 3 |
Actionability | Provides concrete, actionable guidance: exact rules in table format, specific DO/DON'T instructions, executable validation commands (`npm run lint:artifact-templates`), a detailed quality checklist, and a clear reference index mapping steps to template files. | 3 / 3 |
Workflow Clarity | The workflow is implicit rather than explicitly sequenced. While individual rules and checklists are clear, there's no explicit step-by-step generation workflow (e.g., 1. Load template → 2. Generate → 3. Validate → 4. Update README) with validation checkpoints and error recovery loops. The validation commands exist but aren't integrated into a feedback loop. | 2 / 3 |
Progressive Disclosure | Excellent progressive disclosure: the SKILL.md serves as a concise overview with a clear reference index pointing to step-specific templates in `references/`. All references are one level deep and clearly signaled with a when-to-load mapping table. | 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
ec7b8ff
- 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.