Name: microsoft-docs
Rating: 70.39999999999999 (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

68%

Does it follow best practices?

Impact

56%

1.24x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/microsoft-docs/SKILL.md

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

Quality

Content

75%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.

The body is a well-structured, highly actionable routing guide with concrete tool names, library IDs, and query examples; its main weakness is inline version-sensitive content that hurts conciseness and slightly bloats an otherwise clean overview.

Suggestions

Move version-sensitive Aspire CLI guidance (13.2 vs 13.1, PR #14028) into a 'Deprecated/older CLI' or separate reference section so the main flow stays version-agnostic and concise.

Add an explicit feedback loop for empty/weak search results (e.g., 'If search excerpts are thin, call microsoft_docs_fetch on the top URL; if still nothing, broaden the query with the product + version').

Consider extracting the per-product Context7 library-ID tables into a reference file to keep SKILL.md as a lean overview, which would lift progressive_disclosure toward 5.

Dimension	Reasoning	Score
Conciseness	Mostly lean with well-structured tables and no over-explanation of basics, but version-specific info ('CLI 13.2+', 'CLI 13.1', 'PR #14028') is inline rather than in a deprecated/old-patterns section, which the rubric penalizes.	3 / 5
Actionability	Fully executable guidance: concrete MCP tool names, exact Context7 library IDs (e.g. '/microsoft/aspire.dev'), a real command ('aspire update --self --channel daily'), and copy-paste-ready ❌/✅ query examples covering common cases.	5 / 5
Workflow Clarity	Clear routing logic (Learn MCP default with an exceptions table) and an explicit 2-step Context7 setup sequence; as a non-destructive query skill no validation cap applies, but feedback loops for empty searches are only implicit.	4 / 5
Progressive Disclosure	No bundle files exist, so scoring is on structure alone; sections are well-organized with clear tables and no nested references, though the doc exceeds 50 lines with inline CLI-version branching that could be split out.	4 / 5
	Total	16 / 20 Passed

Description

61%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.

The description clearly scopes a distinct Microsoft-docs research skill with good trigger keywords and a clear 'what', but it omits an explicit 'Use when...' trigger clause and its action verbs are somewhat generic.

Suggestions

Add an explicit 'Use when...' clause (e.g., 'Use when the user asks about Azure, .NET, Aspire, VS Code, or GitHub documentation') to lift completeness above 3.

Replace generic verbs like 'find concepts, tutorials, and code examples' with more concrete, varied actions to improve specificity.

Include a few natural problem-oriented trigger phrases (e.g., 'MS docs', 'official Microsoft docs', 'look up Azure/.NET docs') alongside the product names.

Dimension	Reasoning	Score
Specificity	Names the domain (Microsoft docs across Azure, .NET, etc.) and a few actions ('find concepts, tutorials, and code examples'), but the verbs are generic and not a comprehensive list of concrete actions.	3 / 5
Completeness	Has a clear 'what' (query MS docs via Learn MCP, with Context7/Aspire MCP fallbacks) but no explicit 'Use when...' clause, capping completeness at 3 per the rubric.	3 / 5
Trigger Term Quality	Strong natural product keywords ('Azure, .NET, Agent Framework, Aspire, VS Code, GitHub') that users would actually say, though it lacks problem-oriented phrasing and synonyms beyond product names.	4 / 5
Distinctiveness Conflict Risk	Clearly scoped to the Microsoft documentation ecosystem with specific named MCP tools, distinct from generic web-search skills with only minor overlap risk.	4 / 5
	Total	14 / 20 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: 15ad10c

Reviewed: 10 days 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.