teams-notifications
Microsoft Teams MCP integration for agent-to-human notifications and bi-directional communication. Use when agents need to post progress updates, request approvals, or read user responses via Teams channels and chats.
77
96%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
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 skill description that clearly identifies the platform (Microsoft Teams), the integration mechanism (MCP), and specific use cases (posting updates, requesting approvals, reading responses). It includes an explicit 'Use when' clause with natural trigger terms and is distinctive enough to avoid conflicts with other communication or notification skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'post progress updates', 'request approvals', 'read user responses'. Also specifies the communication pattern ('agent-to-human notifications and bi-directional communication') and the medium ('Teams channels and chats'). | 3 / 3 |
Completeness | Clearly answers both 'what' (Microsoft Teams MCP integration for notifications and bi-directional communication) and 'when' (explicit 'Use when agents need to post progress updates, request approvals, or read user responses via Teams channels and chats'). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'Microsoft Teams', 'Teams', 'notifications', 'approvals', 'channels', 'chats', 'progress updates'. Covers both the platform name and common use-case terms. 'MCP integration' is slightly technical but appropriate for the audience. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — specifically targets Microsoft Teams as the platform, MCP as the integration type, and agent-to-human communication as the use case. Unlikely to conflict with other skills like Slack integrations or general notification skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
92%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, well-crafted skill that provides concrete, actionable guidance for Teams MCP integration. The Human-in-the-Loop approval workflow is particularly well done with clear sequencing, validation, error handling, and timeout behavior. Minor weakness is the vague MCP tools overview and an unverifiable REFERENCE.md link with no bundle files provided.
Suggestions
Expand or link to a complete MCP tools listing rather than the vague 'Covers chats, messages, channels, members, and settings' summary.
Provide the referenced REFERENCE.md bundle file or clarify its expected contents so the progressive disclosure chain is complete.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. It doesn't explain what Teams is, what MCP is conceptually, or how OAuth works. Every section delivers actionable information without padding. The brief auth line is necessary context, not fluff. | 3 / 3 |
Actionability | Provides concrete MCP tool call examples with JSON payloads, executable polling logic in JavaScript, specific regex patterns for approval detection, and clear fallback/retry behavior. The examples are copy-paste ready and include expected response shapes. | 3 / 3 |
Workflow Clarity | The Human-in-the-Loop Approval section is a well-sequenced 3-step workflow with explicit validation (verify message_id confirmation), error handling (retry once, fallback), timeout behavior (5 min → escalation), and a clear feedback loop for polling. The acknowledgment step closes the loop. | 3 / 3 |
Progressive Disclosure | References REFERENCE.md for Adaptive Cards, rate limits, and security considerations, which is good one-level-deep disclosure. However, no bundle files are provided, so the reference cannot be verified. The skill itself is well-structured with clear sections, but the MCP tools section ('Covers chats, messages, channels, members, and settings') is vague and could benefit from a reference to a complete tool listing. | 2 / 3 |
Total | 11 / 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
- monkilabs/opencastle
- Commit
7a69a05
- 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.