CtrlK
BlogDocsLog inGet started
Tessl Logo

m365-agents-py

Microsoft 365 Agents SDK for Python. Build multichannel agents for Teams/M365/Copilot Studio with aiohttp hosting, AgentApplication routing, streaming responses, and MSAL-based auth.

55

Quality

63%

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-claude/skills/m365-agents-py/SKILL.md

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

SKILL.md
Quality
Evals
Security

Quality

Content

57%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 content is a rich, mostly lean code reference for the SDK, but it is undermined by non-executable core examples (notably the `AgentApplicationTurnState` instantiation bug) and a referenced bundle file that is missing. Tightening correctness and validating references would most improve it.

Suggestions

Fix `AGENT_APP = AgentApplicationTurnState` to construct the application, e.g. `AGENT_APP = AgentApplication(...)`, and import `Activity` where it is used so the examples run as written.

Either create `references/acceptance-criteria.md` or remove the Reference Files table entry so signaled references resolve to real files.

Add a brief validation/checkpoint step (e.g. locally run the aiohttp app and confirm `/api/messages` responds) before presenting the hosting workflow as production-ready.

DimensionReasoningScore

Conciseness

The body is mostly executable code with little concept over-explanation, but it repeats the same conversation_update/welcome handler across the 'Core Workflow' and 'AgentApplication Routing' sections, a minor trim opportunity.

4 / 5

Actionability

Concrete, extensive code is provided, but the core instantiation `AGENT_APP = AgentApplicationTurnState` is incorrect (it references a state class instead of constructing `AgentApplication(...)`), `Activity` is used without being imported, and `LocalTokenCache` is a stub, so the examples are not reliably copy-paste executable.

3 / 5

Workflow Clarity

Content is organized by topic with a useful 'Before implementation' verification prompt, but it is a pattern reference rather than a sequenced workflow, and there are no validation checkpoints around the auth/streaming/deploy operations.

3 / 5

Progressive Disclosure

Good section headers structure the content and one reference is signaled in a table, but the referenced `references/acceptance-criteria.md` does not exist and large amounts of API pattern content are inlined rather than split into reference files.

3 / 5

Total

13

/

20

Passed

Description

70%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 specific and distinctive, naming concrete SDK capabilities and natural platform trigger terms, but it omits any explicit 'Use when' guidance, which caps its completeness. Adding a trigger clause would lift the strongest remaining weakness.

Suggestions

Append an explicit 'Use when...' clause, e.g. 'Use when building Teams/M365/Copilot Studio agents in Python or when the user mentions the Microsoft 365 Agents SDK.'

Add a couple of natural synonyms like 'bot' or 'M365 bot' to broaden trigger-term coverage.

DimensionReasoningScore

Specificity

Lists several concrete capabilities — 'Build multichannel agents for Teams/M365/Copilot Studio with aiohttp hosting, AgentApplication routing, streaming responses, and MSAL-based auth' — naming five distinct actions; minor gaps in coverage keep it below a 5.

4 / 5

Completeness

The 'what' is clear (build multichannel agents with the listed features) but there is no 'Use when...' clause or equivalent explicit trigger guidance in the description, which caps completeness at 3 per the rubric.

3 / 5

Trigger Term Quality

Includes natural terms users would say ('Microsoft 365', 'Teams', 'Copilot Studio', 'Python', 'agents') with good coverage; a few natural variants (e.g. 'bot', 'M365 bot') are missing, so not a 5.

4 / 5

Distinctiveness Conflict Risk

Targets a clear niche — the Microsoft 365 Agents SDK for Python with Teams/M365/Copilot Studio triggers — that is unlikely to fire for unrelated skills, giving minimal conflict risk.

5 / 5

Total

16

/

20

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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
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.