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.

1.46x

Quality

71%

Does it follow best practices?

Impact

95%

1.46x

Average score across 3 eval scenarios

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/all-skills/skills/microsoft-teams-automation/SKILL.md

Quality

Content

67%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, highly actionable single-file skill whose API specifics (tool slugs, parameter names, ID formats, throttling behavior) are exactly the knowledge Claude lacks. Its weaknesses are redundancy across the pitfalls sections and the lack of example tool-call payloads and post-action verification steps.

Suggestions

Consolidate the pagination and ID-format guidance, each currently repeated in 3-4 sections, into the single "Known Pitfalls" section and reference it from the workflows.

Add one example tool invocation payload (e.g., the RUBE_SEARCH_TOOLS query for the microsoft_teams toolkit, and a filled-in POST_CHANNEL_MESSAGE argument) to make guidance copy-paste ready.

Add an explicit post-action verification step to the messaging workflows (e.g., fetch the posted message via GET_CHAT_MESSAGE or re-list channel messages) to close the validation gap.

Move the 16-row Quick Reference table and the ID-format catalog into a references/ file to slim the main SKILL.md body.

Dimension	Reasoning	Score
Conciseness	The body is dense with API specifics Claude would not know (tool slugs, ID formats, error codes), but pagination guidance is repeated in four places (workflow 1 pitfalls, workflow 4 pitfalls, Common Patterns, Known Pitfalls) and ID-format rules in three. The duplication exceeds the "minor instances" of a 4 and calls for tightening, matching anchor 3.	3 / 5
Actionability	Concrete, executable guidance throughout: exact tool sequences with [Required]/[Optional] markers, named parameters, example ID formats ('19:abc123@thread.tacv2'), and specific backoff timings (1s/2s/4s). It falls short of a 5 because there are no example tool-call payloads (e.g., a sample RUBE_SEARCH_TOOLS query or POST_CHANNEL_MESSAGE argument body).	4 / 5
Workflow Clarity	Setup has a numbered sequence with an explicit validation gate ("Confirm connection status shows ACTIVE before running any workflows"), and pitfalls supply error-recovery feedback (429 with Retry-After/backoff, 403 permission diagnosis, search-index delay with a verification alternative). Not a 5: the messaging workflows lack a post-action verification checkpoint confirming the message was posted.	4 / 5
Progressive Disclosure	A single well-sectioned file with clear headers, a Common Patterns section, and a genuinely useful Quick Reference table; no nested or buried references. Not a 5: at ~207 lines the under-50-line exception does not apply, and the Quick Reference table and ID-format catalog are candidates for a separate reference file.	4 / 5
	Total	15 / 20 Passed

Description

75%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 specific, distinctive description that clearly states what the skill does through five concrete actions. Its main weakness is the complete absence of "when to use" trigger guidance, which caps completeness and limits discoverability.

Suggestions

Add an explicit trigger clause, e.g., "Use when the user wants to send messages or schedule meetings in Microsoft Teams, manage teams/channels, or search Teams messages."

Include natural user phrasings such as "post to a Teams channel", "start a Teams chat", or "set up a Teams meeting" as trigger terms.

Clarify what "handle chats" concretely covers (create chats, list chats, send direct/group messages) to remove the one vaguely-worded action.

Dimension	Reasoning	Score
Specificity	Lists five concrete actions ("send messages, manage channels, create meetings, handle chats, and search messages") covering the domain comprehensively, matching the anchor-5 breadth of the good examples. Coverage gaps are negligible, so it is not a 4.	5 / 5
Completeness	The "what" is clear (automate Teams tasks via the listed actions), but there is no "Use when..." clause or equivalent explicit trigger guidance; the rubric caps completeness at 3 for this. It is not a 2 because the "what" is specific and multi-part.	3 / 5
Trigger Term Quality	"Microsoft Teams", "messages", "channels", "meetings", "chats" are natural terms users would say, giving good keyword coverage. Common variations ("post to a channel", "DM", "team members") are missing, so it does not reach the synonym-level coverage of a 5.	4 / 5
Distinctiveness Conflict Risk	"Microsoft Teams" is a clear niche trigger with distinct platform-specific terms, giving minimal conflict risk with other skills. Only trivial adjacency to generic messaging skills, which does not warrant a 4.	5 / 5
	Total	17 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: davepoon/buildwithclaude
Path: plugins/all-skills/skills/microsoft-teams-automation/SKILL.md
Commit: b90e2de

Reviewed: 4 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.