Tessl • The management layer for AI agent skills

SkillPublic

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.

Quality

79%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

Quality

Content

82%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.

A well-structured routing skill with excellent actionability — exact tool names, copy-paste library IDs, and concrete query examples — and a clear default-plus-exceptions decision flow. Minor improvements possible: add fallback guidance for failed searches and trim version-pinned detail that will become stale.

Dimension	Reasoning	Score
Conciseness	The body is efficient — compact routing tables with exact tool names and library IDs, assuming Claude already knows what MCP servers and documentation sites are. Minor instances could be trimmed (the PR #14028 link, the "aspire update" command, and version-pinned CLI detail that will age), placing it just below the lean/efficient anchor.	4 / 5
Actionability	Fully actionable for an instruction-only skill: exact MCP tool names (microsoft_docs_search, mcp_context7_resolve-library-id), copy-paste-ready Context7 library IDs (/microsoft/aspire.dev, /websites/code_visualstudio_api), an explicit two-step resolve-then-query sequence, and concrete good vs. bad query examples covering the common cases.	5 / 5
Workflow Clarity	The decision flow is clearly sequenced: default Learn MCP for learn.microsoft.com, an Exceptions section routing each off-Learn product to the right tool, then Context7 setup steps and query-writing guidance. Read-only research needs no destructive-operation validation, but no fallback guidance exists for when a search returns nothing, so it falls just short of the top anchor.	4 / 5
Progressive Disclosure	With no bundle files present, the ~100-line body is well-sectioned with headers and tables, easy to navigate, and appropriately inline for its size. The per-product library ID tables could be split into a one-level-deep reference file to keep SKILL.md a purer overview, keeping it below the top anchor; organization is still clearly good, not merely adequate.	4 / 5
	Total	17 / 20 Passed

Description

66%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.

A concrete, well-scoped description with strong natural trigger terms for the Microsoft ecosystem, written in third person. Its main weakness is the absence of an explicit "Use when..." trigger clause, which caps completeness and leaves the invocation conditions only weakly implied.

Suggestions

Add an explicit trigger clause, e.g. "Use when researching Microsoft technologies, Azure services, .NET APIs, or when the user asks about Microsoft documentation, Learn docs, or MS docs."

Include commonly searched synonyms in the description (Microsoft Learn, M365/Office 365, Power Platform, Windows) to broaden natural keyword coverage.

Mention code-language search (e.g. "find working code snippets by language") explicitly in the description to mirror the concrete capabilities the body provides.

Dimension	Reasoning	Score
Specificity	The description names the domain and several concrete deliverables ("find concepts, tutorials, and code examples across Azure, .NET, Agent Framework, Aspire, VS Code, GitHub"), but the action verbs are essentially limited to query/find rather than a comprehensive set of specific actions, so it falls between the 3 and 5 anchors.	4 / 5
Completeness	The "what" is clear (query Microsoft docs for concepts, tutorials, and code examples with specified tool routing), but there is no "Use when..." clause or equivalent explicit trigger guidance — the second sentence ("Uses Microsoft Learn MCP as the default...") describes tool selection, not when to invoke the skill — so completeness is capped at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	Includes natural keywords users would say — "Azure", ".NET", "Aspire", "VS Code", "GitHub", "Microsoft documentation", "code examples" — but misses common synonyms and variations that appear in the body (M365/Office, Power Platform, Windows, "Microsoft Learn"), keeping it just below comprehensive.	4 / 5
Distinctiveness Conflict Risk	It carves out a clear Microsoft-documentation niche with ecosystem-specific triggers, but naming Context7 and Aspire MCP creates minor overlap risk with a dedicated Context7/library-docs skill, so it fits the "mostly distinct" anchor rather than the fully distinct one.	4 / 5
	Total	15 / 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
Revision: 735e184

Reviewed: 16 days ago

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.

microsoft-docs

Table of Contents

Is this your skill?