Name: microsoft-docs
Rating: 80.80000000000001 (1 reviews)
Author: microsoft

microsoft-docs

Query official Microsoft documentation to find concepts, tutorials, and code examples across Azure, .NET, Agent Framework, Aspire, VS Code, GitHub, and more. Uses Microsoft Learn MCP as the default, with Context7 and Aspire MCP for content that lives outside learn.microsoft.com.

1.24x

Quality

83%

Does it follow best practices?

Impact

56%

1.24x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

The canonical home for this skill is microsoft-docs in github/awesome-copilot

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

Highly actionable and clearly organized with concrete tools, library IDs, and query examples, plus well-sequenced workflows. The main weakness is version-sensitive detail living in the main flow rather than a quarantined section, which costs conciseness.

Suggestions

Move CLI-version distinctions (13.2 vs 13.1) and dated PR/blog links into a short 'Older CLI / deprecated' subsection so the primary path stays version-agnostic and token-lean.

Trim or consolidate the per-CLI tables; the 13.1 fallback could be a single line under the 13.2 table rather than its own full table.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean tables and routing guidance, but time-sensitive version numbers ('CLI 13.2', 'CLI 13.1', 'VS Code 1.96') and a PR/blog link sit in the main flow rather than a deprecated/old-patterns section, which the guidelines penalize. It is not a 1 because it avoids explaining concepts Claude already knows, and not a 3 because of the un-quarantined version-specific detail.	2 / 3
Actionability	It provides fully concrete, copy-paste-ready guidance — exact tool names (microsoft_docs_search, microsoft_docs_fetch), specific Context7 library IDs (/microsoft/aspire.dev, /websites/github_en), a CLI command (aspire update --self --channel daily), and worked query examples — matching the 'fully executable' anchor.	3 / 3
Workflow Clarity	Multi-step flows are clearly sequenced: a numbered 2-step Context7 setup (resolve-library-id then query-docs) and an explicit search→fetch progression ('Use microsoft_docs_fetch after search when...'). No validation checkpoint is needed for read-only research, so its absence is not penalized.	3 / 3
Progressive Disclosure	The skill is a single self-contained file with well-organized sections (Default, Exceptions by category, Context7 Setup, Writing Effective Queries) and no nested external references, so the well-organized-sections exception applies. It is not a 2 because nothing that should be split is left inline as a monolithic wall.	3 / 3
	Total	11 / 12 Passed

Description

82%

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, specific description with good natural trigger terms and a clear Microsoft-docs niche, but it omits an explicit 'Use when...' clause, capping completeness. Adding trigger guidance would round it out.

Suggestions

Add an explicit 'Use when...' clause (e.g., 'Use when the user needs official Microsoft documentation for Azure, .NET, Aspire, VS Code, or GitHub') to satisfy the 'when' half of completeness.

The trailing 'and more' is vague; either drop it or list the remaining domains (M365, Power Platform, Windows) to keep trigger terms concrete and reduce conflict ambiguity.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions ('Query official Microsoft documentation to find concepts, tutorials, and code examples') and enumerates specific domains (Azure, .NET, Agent Framework, Aspire, VS Code, GitHub), matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	It clearly states what the skill does but lacks an explicit 'Use when...' trigger clause stating when Claude should invoke it, so completeness caps at 2 per the missing-trigger guideline. It is not a 1 because the 'what' is thorough, and not a 3 because 'when' is only implied by the technology list.	2 / 3
Trigger Term Quality	It includes natural terms users actually say — 'Azure', '.NET', 'Aspire', 'VS Code', 'GitHub', plus 'concepts, tutorials, and code examples' — giving good coverage rather than technical jargon.	3 / 3
Distinctiveness Conflict Risk	The Microsoft documentation niche with named technologies (Aspire, VS Code, GitHub, Agent Framework) and explicit tool routing gives clear, distinct triggers unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 12 Passed

Validation

100%

Warnings & errors only

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/ai-agents-for-beginners
Path: .agents/skills/microsoft-docs/SKILL.md
Commit: 265bf47

Reviewed: about 10 hours ago

Table of Contents

Discovery Implementation Validation

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.