microsoft-teams-automation
Automate Microsoft Teams tasks via Rube MCP (Composio): send messages, manage channels, create meetings, handle chats, and search messages. Always search tools first for current schemas.
75
65%
Does it follow best practices?
Impact
95%
1.46xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/all-skills/skills/microsoft-teams-automation/SKILL.mdQuality
Discovery
67%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 does a good job listing specific Microsoft Teams actions and identifying the integration platform, making it distinctive. However, it lacks an explicit 'Use when...' clause, which weakens its completeness for skill selection. The trigger terms cover the basics but miss common user phrasings for Teams-related requests.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about Microsoft Teams messaging, scheduling Teams meetings, managing Teams channels, or searching Teams conversations.'
Include more natural user-facing trigger terms like 'Teams call', 'schedule a meeting in Teams', 'DM on Teams', or 'Teams group chat' to improve keyword coverage.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: send messages, manage channels, create meetings, handle chats, and search messages. Also includes the operational guidance to search tools first for current schemas. | 3 / 3 |
Completeness | Clearly answers 'what does this do' with specific actions, but lacks an explicit 'Use when...' clause or equivalent trigger guidance. The 'when' is only implied by the action list, which caps this at 2 per the rubric guidelines. | 2 / 3 |
Trigger Term Quality | Includes natural terms like 'Microsoft Teams', 'messages', 'channels', 'meetings', 'chats', but misses common user variations like 'Teams call', 'schedule a meeting', 'DM', 'team chat', or 'Teams notification'. Also mentions 'Rube MCP (Composio)' which is technical jargon users wouldn't naturally say. | 2 / 3 |
Distinctiveness Conflict Risk | Clearly scoped to Microsoft Teams via a specific integration (Rube MCP/Composio), making it highly distinct and unlikely to conflict with other communication or messaging skills. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a comprehensive Microsoft Teams automation skill with well-structured workflows, clear sequencing, and useful pitfall documentation. Its main weaknesses are the monolithic structure (everything in one file despite significant length), some redundancy between per-workflow pitfalls and the consolidated 'Known Pitfalls' section, and the lack of concrete executable tool invocation examples with sample parameters.
Suggestions
Add concrete tool invocation examples with sample parameters (e.g., show an actual RUBE_SEARCH_TOOLS call and a TEAMS_POST_CHANNEL_MESSAGE call with realistic parameter values) to improve actionability.
Consolidate pitfalls into either per-workflow sections OR the 'Known Pitfalls' section to eliminate redundancy (e.g., rate limiting, ID formats, and message size limits appear in both places).
Consider splitting the quick reference table and detailed workflow guides into separate referenced files to improve progressive disclosure and reduce the main file's token footprint.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably well-structured but quite lengthy (~200+ lines). There's some redundancy between the 'Known Pitfalls' section and the per-workflow pitfalls sections (e.g., rate limits, ID formats, message size limits are repeated). The quick reference table is useful but adds significant length. Some content like explaining what UUID format looks like could be trimmed. | 2 / 3 |
Actionability | The skill provides clear tool sequences and parameter names, which is good. However, there are no executable code examples — the 'Common Patterns' sections use plain text pseudocode rather than actual tool invocation examples with concrete parameter values. The guidance is specific enough to follow but lacks copy-paste ready examples showing actual tool calls with sample payloads. | 2 / 3 |
Workflow Clarity | Multi-step workflows are clearly sequenced with numbered steps, labeled as [Required], [Optional], and [Prerequisite]. Each workflow includes a 'When to use' trigger, tool sequence, key parameters, and pitfalls. The setup section includes a validation checkpoint (confirm ACTIVE status before proceeding). Error handling guidance is provided (403, 429, pagination). | 3 / 3 |
Progressive Disclosure | The content is entirely monolithic — everything is in a single file with no references to supporting documents. Given the length and breadth of coverage (5 core workflows, common patterns, known pitfalls, quick reference table), this would benefit from splitting detailed workflow guides or the pitfalls/reference table into separate files. The single external link to Composio docs is helpful but insufficient for the volume of content. | 2 / 3 |
Total | 9 / 12 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.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- davepoon/buildwithclaude
- Commit
d065ead
- 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.