add-teams

Add Microsoft Teams channel integration via Chat SDK.

Quality

67%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/add-teams/SKILL.md

Quality

Content

77%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This is a highly actionable, well-sequenced skill with executable commands and thorough validation and error-recovery loops. Its main weakness is monolithic organization and some verbosity from repeated justifications and inline version pins.

Suggestions

Move the long manual Azure portal path and the full Troubleshooting catalog into referenced files (e.g. ALTERNATIVES.md, TROUBLESHOOTING.md) and link to them from the main body to improve progressive disclosure.

Tighten repeated justifications — the single-tenant-default rationale and the npm/pnpm-config-noise explanation are stated multiple times; state each once.

Relocate or isolate pinned version numbers (e.g. into a single dependency table or a clearly marked section) so inline version pins do not penalize conciseness over time.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and explains only NanoClaw-specific quirks Claude would not know, but repeated justifications, long parenthetical asides, and inline version pins (e.g. @microsoft/teams.cli@3.0.2) add verbosity that could be trimmed.	2 / 3
Actionability	Every step ships fully executable, copy-paste-ready commands — real 'teams app create' invocations, exact curl payloads to Bot Framework, pinned deps, and concrete nc: directives with real file paths.	3 / 3
Workflow Clarity	The process is a clearly numbered sequence with explicit validation (build guards, registration test, sign-in persistence sentinel) and a strong troubleshooting feedback loop (AUTH_REQUIRED, 401 pairing, bot-not-receiving-messages) for a fragile operation.	3 / 3
Progressive Disclosure	Sections are well-organized and clearly headed, but the ~580-line document is monolithic with no progressive-disclosure references, keeping substantial content like the manual Azure portal walk and full troubleshooting catalog inline where splitting would help.	2 / 3
	Total	10 / 12 Passed

Description

57%Weight 40%Scale 1-3

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 in domain but thin on capability detail and entirely lacks explicit trigger guidance. It distinguishes itself well but reads as a label rather than a complete activation statement.

Suggestions

Add concrete actions to the description, e.g. 'Add Microsoft Teams channel integration via Chat SDK — registers the bot, stores credentials, and wires the owner DM.'

Append a 'Use when...' clause with natural trigger terms, e.g. 'Use when the user wants to add Teams, set up a Teams bot, or send/receive messages in Microsoft Teams channels or DMs.'

Replace or contextualize the internal 'Chat SDK' term with user-facing language so trigger terms match what users actually say.

Dimension	Reasoning	Score
Specificity	Names a specific domain and one high-level action ('Add Microsoft Teams channel integration via Chat SDK') but lists no concrete actions like register bot, configure credentials, or send messages, so it falls short of the multiple-specific-actions anchor.	2 / 3
Completeness	It states what the skill does but includes no 'Use when...' trigger guidance for when Claude should invoke it, which caps completeness at 2 per the rubric.	2 / 3
Trigger Term Quality	'Microsoft Teams' and 'channel' are natural user terms, but 'Chat SDK' is internal jargon and common variations like 'Teams bot' or 'send messages to Teams' are absent.	2 / 3
Distinctiveness Conflict Risk	'Microsoft Teams channel integration' is a narrow, clearly-bounded niche unlikely to overlap with or trigger for unrelated skills.	3 / 3
	Total	9 / 12 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
skill_md_line_count	SKILL.md is long (585 lines); consider splitting into references/ and linking	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	14 / 16 Passed

Repository: nanocoai/nanoclaw
Path: .claude/skills/add-teams/SKILL.md
Commit: 641963c

Reviewed: 6 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.