Name: m365-agents-ts
Rating: 53.6 (1 reviews)
Author: administrakt0r

Blog Docs Log in Get started

m365-agents-ts

Microsoft 365 Agents SDK for TypeScript/Node.js.

Quality

60%

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 ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/m365-agents-ts/SKILL.md

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

Quality

Content

72%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.

The body is a strong, executable reference: lean, mostly self-contained, with copy-paste code for the core scenarios. Its weaknesses are a capability-not-sequence layout with no validation checkpoints and a referenced file that is missing from the bundle.

Suggestions

Add the missing references/acceptance-criteria.md (or remove the Reference Files entry) so signaled references resolve to real files.

Reframe the core section as a short ordered workflow (install -> set env vars -> create AgentApplication -> startServer) with explicit validation/verify checkpoints.

Trim the repeated import blocks and consolidate the env-var block to tighten token efficiency toward a 5.

Dimension	Reasoning	Score
Conciseness	The body is code-heavy and lean, avoiding concept explanations Claude already knows, with only minor redundancy (repeated imports per snippet and a verbose env-var block); it fits 'Efficient; minor instances that could be trimmed' rather than a 5.	4 / 5
Actionability	It provides complete, copy-paste-ready TypeScript snippets across the common cases (Express hosting, streaming, invoke handling, Copilot Studio client, WebChat) plus install commands and env vars, matching 'Fully executable; specific examples cover the common cases.'	5 / 5
Workflow Clarity	Sections are organized by capability rather than a sequenced workflow, and 'Before implementation' lists two prep steps with no validation checkpoints; this fits 'sequence present but checkpoints missing or implicit' rather than a 4.	3 / 5
Progressive Disclosure	Section headers and a Reference Files table give some structure, but the referenced references/acceptance-criteria.md does not exist in the bundle, so a signaled reference is dangling; this lands at 'Some structure... references present but not clearly signaled' rather than a 4.	3 / 5
	Total	15 / 20 Passed

Description

48%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.

The description is a terse technology label rather than a capability-and-trigger statement: it names the SDK and stack but says nothing about what it does or when to invoke it. Adding concrete actions and an explicit 'Use when...' clause would move it from adequate to strong.

Suggestions

Add concrete actions to the description, e.g. 'Build and host Microsoft 365/Teams/Copilot Studio agents with Express hosting, AgentApplication routing, and streaming responses.'

Append an explicit trigger clause, e.g. 'Use when building Microsoft 365, Teams, or Copilot Studio agents in TypeScript/Node.js.'

Include natural synonyms users actually say (e.g. 'Teams bot', 'Copilot Studio agent') alongside the SDK name.

Dimension	Reasoning	Score
Specificity	The description names the domain ("Microsoft 365 Agents SDK") but lists no concrete actions, matching the anchor 'Names the domain but actions are minimal or generic'; it is not a 1 because it identifies a specific SDK rather than being pure abstraction, and not a 3 because no actions are enumerated.	2 / 5
Completeness	It gives a clear 'what' (the SDK and platform) but no 'when' or 'Use when...' trigger clause, which per the guidelines caps completeness at 3; the body's generic 'When to Use' line does not live in the description.	3 / 5
Trigger Term Quality	It surfaces real product names ("Microsoft 365", "Agents SDK", "TypeScript", "Node.js") that users may search, but misses natural phrasings like 'build a Teams bot' or 'Copilot Studio', fitting 'Some relevant keywords but missing common variations or synonyms'.	3 / 5
Distinctiveness Conflict Risk	"Microsoft 365 Agents SDK for TypeScript/Node.js" carves a fairly specific niche with low conflict risk against unrelated skills, but lacks explicit trigger phrases that would cement full distinctiveness (a 5).	4 / 5
	Total	12 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	14 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills-claude/skills/m365-agents-ts/SKILL.md
Commit: 57c135b

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.