CtrlK
BlogDocsLog inGet started
Tessl Logo

m365-agents-dotnet

Microsoft 365 Agents SDK for .NET. Build multichannel agents for Teams/M365/Copilot Studio with ASP.NET Core hosting, AgentApplication routing, and MSAL-based auth.

59

Quality

69%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills/skills/m365-agents-dotnet/SKILL.md

The canonical home for this skill is m365-agents-dotnet in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

68%Scale 1-5

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

This skill excels at actionability with complete, executable code examples covering the full Microsoft 365 Agents SDK workflow from installation through Copilot Studio integration. However, it lacks explicit workflow sequencing with validation checkpoints — there are no steps to verify the agent starts correctly, no auth troubleshooting guidance, and no feedback loops for common failure modes. The content is moderately concise but could be tightened by moving the Copilot Studio client code to a reference file and trimming boilerplate configuration.

Suggestions

Add explicit validation checkpoints: e.g., 'Run `dotnet build` to verify packages resolve', 'Test /api/messages endpoint returns 401 without auth token to confirm auth is configured', and error recovery guidance for common MSAL failures.

Move the Copilot Studio direct-to-engine client section (DelegatingHandler + Console host) into a separate reference file to reduce the main skill's length and improve progressive disclosure.

Add a brief numbered workflow summary at the top (1. Install packages → 2. Configure auth → 3. Create agent host → 4. Implement routing → 5. Verify endpoint) to provide clear sequencing before diving into code blocks.

DimensionReasoningScore

Conciseness

The skill provides substantial code examples that are useful, but the full appsettings.json block with placeholder values and the Copilot Studio client section add significant length. Some sections like the CopilotStudioClientSettings config with empty strings and the 'When to Use' boilerplate are low-value tokens. The 'Before implementation' section telling Claude to verify APIs is reasonable but borderline unnecessary.

3 / 5

Actionability

The skill provides fully executable, copy-paste ready code for the complete workflow: NuGet installation commands, full appsettings.json configuration, complete Program.cs hosting setup, a full AgentApplication subclass with routing, and a complete Copilot Studio client with token acquisition. All code includes proper using statements and is production-realistic.

5 / 5

Workflow Clarity

The skill presents code blocks in a logical sequence (install → configure → host → route → integrate) but lacks explicit numbered workflow steps, validation checkpoints, or feedback loops. There's no guidance on verifying the agent is running correctly, no troubleshooting for common auth failures, and no validation step after configuration. For an SDK involving authentication and service connections, missing verification steps is a notable gap.

3 / 5

Progressive Disclosure

The skill references a 'references/acceptance-criteria.md' file and provides a well-organized reference links table pointing to external documentation. The main content is structured with clear section headers. However, the bundle has no files provided, so the referenced file cannot be verified, and the inline content is quite long — the Copilot Studio client section could potentially be split into a separate reference file.

4 / 5

Total

15

/

20

Passed

Description

70%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 is technically specific and clearly identifies its niche within the Microsoft 365/.NET ecosystem, making it highly distinctive. Its main weakness is the lack of an explicit 'Use when...' clause, which would help Claude know exactly when to select this skill. Adding trigger synonyms like 'bot' or 'Teams bot' would also improve discoverability.

Suggestions

Add a 'Use when...' clause such as 'Use when the user wants to build bots or agents for Microsoft Teams, Microsoft 365, or Copilot Studio using .NET'

Include common synonyms and variations users might say, such as 'bot', 'Teams bot', 'chatbot', 'M365 bot', or 'Azure AD authentication'

DimensionReasoningScore

Specificity

Lists several specific capabilities: 'multichannel agents', 'ASP.NET Core hosting', 'AgentApplication routing', 'MSAL-based auth'. These are concrete technical actions/features, though it could elaborate more on what building these agents entails (e.g., handling activities, managing conversations).

4 / 5

Completeness

The 'what' is clear — build multichannel agents with specific technologies. However, there is no explicit 'when' clause (e.g., 'Use when...'). The absence of a 'Use when' clause caps this at 3 per the rubric guidelines.

3 / 5

Trigger Term Quality

Includes strong natural keywords like 'Microsoft 365', 'Teams', 'Copilot Studio', 'ASP.NET Core', 'MSAL', 'agents', '.NET'. Missing some synonyms or variations users might say like 'bot', 'M365 bot', 'Teams bot', 'chatbot', or 'Azure AD auth'.

4 / 5

Distinctiveness Conflict Risk

Highly distinctive with a clear niche: Microsoft 365 Agents SDK for .NET specifically targeting Teams/M365/Copilot Studio. The combination of platform (M365), SDK, runtime (.NET/ASP.NET Core), and auth framework (MSAL) makes it very unlikely to conflict with other skills.

5 / 5

Total

16

/

20

Passed

Validation

90%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

10

/

11

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
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.