microsoft-skill-creator
Create agent skills for Microsoft technologies using Learn MCP tools. USE FOR: generating skills that teach agents about Azure services, .NET libraries, Microsoft 365 APIs, VS Code extensions, Bicep modules, or any Microsoft technology. DO NOT USE FOR: general skill scaffolding without Microsoft tech focus (use make-skill-template), Azure infrastructure deployment, Bicep/Terraform code generation.
83
78%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./.github/skills/microsoft-skill-creator/SKILL.mdQuality
Discovery
100%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 strong description that clearly defines its scope, provides rich trigger terms across multiple Microsoft technology domains, and explicitly delineates both positive and negative use cases. The 'DO NOT USE FOR' clause with a redirect to an alternative skill is particularly effective for disambiguation. The description uses proper third-person voice and is concise yet comprehensive.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and domains: 'generating skills that teach agents about Azure services, .NET libraries, Microsoft 365 APIs, VS Code extensions, Bicep modules.' Also specifies the tooling involved ('Learn MCP tools'). | 3 / 3 |
Completeness | Clearly answers both 'what' (create agent skills for Microsoft technologies using Learn MCP tools) and 'when' (explicit 'USE FOR' clause with specific triggers, plus a 'DO NOT USE FOR' clause that further clarifies boundaries). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural keywords users would say: 'Azure services', '.NET libraries', 'Microsoft 365 APIs', 'VS Code extensions', 'Bicep modules', 'Microsoft technology', 'agent skills'. These are terms users would naturally use when requesting this kind of skill generation. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with clear niche (Microsoft technology skill generation via Learn MCP tools). The explicit 'DO NOT USE FOR' clause with references to alternative skills ('use make-skill-template') and exclusions (Azure deployment, Bicep/Terraform code generation) sharply reduces conflict risk. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a moderately well-structured meta-skill for creating Microsoft technology skills. Its strengths are the clear progressive disclosure with well-signaled references and the useful local-vs-dynamic content decision framework. Its weaknesses are unnecessary explanatory content about what skills are (which Claude knows), lack of concrete inline examples of generated output, and a validation step that lacks specificity and feedback loops.
Suggestions
Remove or drastically shorten the 'About Skills' section — Claude already understands what skills are; keep only the skill structure diagram if it defines a project-specific convention.
Add a concrete, complete example of a generated SKILL.md snippet (even a small one) inline so the skill is actionable without requiring reference file lookups.
Strengthen Step 5 (Validate) with specific validation commands or checks and a feedback loop (e.g., 'If search queries return poor results, broaden terms and re-run Phase 1').
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill includes some unnecessary explanations (e.g., 'About Skills' section explaining what skills are, which Claude already knows), and the general skill structure description is redundant context. However, the MCP tool tables and local-vs-dynamic guidance are genuinely useful and well-structured. | 2 / 3 |
Actionability | The skill provides concrete MCP tool calls and CLI commands, which is good. However, the actual skill generation process relies heavily on templates in external reference files without showing any inline examples of what a generated skill looks like. The investigation queries are pseudocode-like placeholders rather than fully concrete examples. | 2 / 3 |
Workflow Clarity | The 5-step process is clearly sequenced and includes a validation step (Step 5) and an investigation checklist. However, the validation step is vague ('Do code samples run without errors?' — how?), and there are no feedback loops for error recovery. The note about using make-skill-template afterward is helpful but could be better integrated into the workflow. | 2 / 3 |
Progressive Disclosure | Content is well-organized with a clear overview in SKILL.md and appropriate references to external files (skill-templates.md, investigation-patterns.md). The reference index table at the bottom provides clear navigation. References are one level deep and clearly signaled. | 3 / 3 |
Total | 9 / 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.