CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

add-teams

Add Microsoft Teams channel integration via Chat SDK.

Quality

74%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

Quality

Content

85%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.

This is a strong operational skill: fully executable commands with pinned versions, explicit validation and re-run safety at every fragile step, and deep project-specific rationale that Claude could not infer. Its main weaknesses are moderate length with some repeated rationale and a monolithic single-file layout that inlines troubleshooting and alternative paths which would be better split into reference files.

DimensionReasoningScore

Conciseness

The body is dense with genuinely non-obvious, project-specific knowledge (pnpm build-script policy blocking keytar, the SingleTenant/MultiTenant 401 pairing rule, global-vs-workspace CLI install rationale) and assumes Claude's competence on general concepts. Minor over-explanation and some repetition (the tenant-pairing rule and single-tenant rationale each appear three times) keep it at anchor 4 rather than 5.

4 / 5

Actionability

Every step is copy-paste executable: pinned dependencies ("@microsoft/teams.cli@3.0.2", "@chat-adapter/teams@4.41.1"), exact curl calls with jq extraction, exact .env keys, absolute CLI paths, and validation regexes on every captured value. This matches the anchor for fully executable, copy-paste-ready commands covering the common cases.

5 / 5

Workflow Clarity

The flow is explicitly sequenced (Apply → Credentials → Restart → Finish wiring) with real validation checkpoints: a credential probe that short-circuits re-runs, sign-in persistence verified from a fresh process, a build-plus-registration test whose failure modes are enumerated, idempotent directives, and a thorough symptom→fix Troubleshooting section with feedback loops. This matches the anchor for clear sequence with explicit validation and error recovery.

5 / 5

Progressive Disclosure

Section headers and internal anchor links give the ~590-line document reasonable navigation, but roughly 200 lines (the manual Azure portal path, optional RSC configuration, and much of Troubleshooting) clearly belong in separate reference files — no bundle files exist and everything is inlined. This matches anchor 3 (some structure, content that should be separate is inline), not 2 because the inlined content is well-sectioned rather than a structureless wall.

3 / 5

Total

17

/

20

Passed

Description

53%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 concise and names a distinct, well-scoped capability, but it is bare-bones: it states only what the skill does at the highest level and omits any usage triggers, synonyms, or an enumeration of the concrete operations the skill performs. Adding an explicit when-to-use clause and natural trigger variations would lift the two heaviest dimensions.

Suggestions

Add a 'Use when...' clause with concrete triggers, e.g. "Use when the user wants to connect, add, or set up Microsoft Teams, MS Teams, or a Teams bot/channel for NanoClaw."

Enumerate the concrete capabilities so specificity reflects the skill's actual scope, e.g. "Registers the Entra app and Teams bot, stores credentials, and wires the owner's DM" rather than the generic "integration".

Include natural synonyms and variations users would say — "MS Teams", "Teams bot", "Microsoft 365 Teams" — to improve trigger-term coverage.

DimensionReasoningScore

Specificity

"Add Microsoft Teams channel integration via Chat SDK" names the domain and one concrete action plus mechanism, matching the anchor for 1-2 concrete actions without comprehensive coverage. It is not a 4 because it lists none of the skill's specific operations (bot registration, credential storage, owner wiring, app install).

3 / 5

Completeness

The description gives a clear "what" (add Teams channel integration via the Chat SDK) but contains no "Use when..." clause or any trigger guidance, which caps completeness at 3 per the judging guidelines. It is an exact match for the anchor-3 example (clear what, when missing entirely), not 4 which requires an explicit when.

3 / 5

Trigger Term Quality

"Microsoft Teams" and "channel" are natural terms a user would say, but common variations and synonyms ("MS Teams", "Teams bot", "MSTeams") are absent. This sits between anchor 3 (some relevant keywords, missing variations) and anchor 4, closer to 3 given the sparse keyword set.

3 / 5

Distinctiveness Conflict Risk

"Microsoft Teams" pins a clear niche distinct from other channel skills with minimal conflict risk, matching anchor 4 (mostly distinct, minor overlap with closely related skills such as sibling add-channel skills). Not 5 because there are no explicit distinct triggers separating it from generic channel-integration requests.

4 / 5

Total

13

/

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.

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (589 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

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.