CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

zoom-contact-center-android

Zoom Contact Center SDK for Android. Use for native Android chat/video/ZVA/scheduled callback integrations, campaign mode, service lifecycle, and rejoin handling.

60

Quality

75%

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 ./plugins/zoom/skills/contact-center/android/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

61%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 admirably lean and correctly avoids teaching known concepts, and its API surface summary is genuinely non-inferable knowledge. However, it functions as an index to a bundle that mostly does not exist — four of five Quick Links plus the RUNBOOK are dead — and it offers no executable code or validation checkpoints for the SDK lifecycle it describes.

Suggestions

Create the advertised bundle files (concepts/sdk-lifecycle.md, examples/service-patterns.md, troubleshooting/common-issues.md, RUNBOOK.md) or remove the dead links so Quick Links matches the actual bundle.

Add a minimal executable Kotlin/Java snippet showing ZoomCCInterface init and ZoomCCItem construction with entryId/apiKey so the guardrails are actionable rather than declarative.

Add explicit validation checkpoints to the lifecycle, e.g. confirm service init success via ZoomCCServiceListener before engaging, and verify releaseZoomCCService(key) on teardown.

DimensionReasoningScore

Conciseness

The ~45-line body is lean: doc links, a terse SDK surface list ("getZoomCCChatService()", "getZoomCCZVAService()"...), guardrail bullets, and cross-links, with zero explanation of concepts Claude already knows. Not below 5 — every token adds API surface or lifecycle rules Claude cannot infer.

5 / 5

Actionability

Concrete guidance exists ("Initialize SDK in `Application.onCreate`", "Use `entryId` for chat/video/ZVA", "Release services on teardown") but there is no executable code anywhere — no Kotlin/Java snippet showing `ZoomCCItem` construction or `ZoomCCInterface.init(...)`, and key parameters are missing. This matches anchor 3 (some concrete guidance but incomplete, missing key details) rather than 4 (mostly executable code/commands).

3 / 5

Workflow Clarity

"Hard Guardrails" implies a rough lifecycle sequence (init in `Application.onCreate` → define `ZoomCCItem` with entryId/apiKey → release on teardown), but the steps are never enumerated as a sequence and validation checkpoints are entirely absent — nothing about confirming init success, listener callbacks, or failure recovery. Anchor 3 (sequence present but checkpoints missing/implicit); the RUNBOOK that presumably carried verification is a dead link, so it cannot be credited.

3 / 5

Progressive Disclosure

The structure is well signaled ("Quick Links" to concepts/sdk-lifecycle.md, examples/service-patterns.md, references/android-reference-map.md, troubleshooting/common-issues.md, plus RUNBOOK.md), but the actual bundle contains only references/android-reference-map.md — 4 of 5 advertised files (and RUNBOOK.md, plus the cross-skill links) do not exist. Dead references make the navigation promise undeliverable, matching anchor 2 (references effectively buried/broken) rather than 3; not anchor 1 because the one real reference is well-organized and one level deep.

2 / 5

Total

13

/

20

Passed

Description

78%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 strong description: explicit 'Use for' trigger clause naming concrete integration areas, distinctive platform/product scoping, and good natural keyword coverage. Its main weakness is that the 'what' half is a bare SDK label with unexpanded acronyms rather than a statement of actions.

Suggestions

Add one or two concrete action verbs to the what half, e.g. 'Integrate Zoom Contact Center chat, video, and virtual agent (ZVA) into native Android apps' so the description states what the skill does, not just what it is.

Expand the ZVA acronym and add a synonym such as 'virtual agent' so users who don't know the acronym still trigger the skill.

DimensionReasoningScore

Specificity

"Use for native Android chat/video/ZVA/scheduled callback integrations, campaign mode, service lifecycle, and rejoin handling" lists several specific capability areas (chat, video, ZVA, scheduled callback, campaign mode, lifecycle, rejoin) with only minor coverage gaps. Not a 5: these are feature/domain nouns rather than concrete actions Claude performs, and terms like ZVA are unexpanded.

4 / 5

Completeness

"Zoom Contact Center SDK for Android" states the what and "Use for native Android chat/video/ZVA/scheduled callback integrations..." is an explicit when-clause with concrete trigger areas. It is not a 5 because the 'what' is a bare identifier — it names the SDK but never states what it does (e.g. no verbs like 'initialize', 'build', 'configure'), leaving the what-side weaker than the when-side.

4 / 5

Trigger Term Quality

Natural terms users would say are present: "chat", "video", "scheduled callback", "campaign", "rejoin", "Android", "Zoom Contact Center". A few natural terms are missing — no synonyms for ZVA (e.g. "virtual agent"), and no phrasings like "in-app support" or "mobile engagement" — so it falls just short of comprehensive anchor 5 and clearly above anchor 3.

4 / 5

Distinctiveness Conflict Risk

"Zoom Contact Center SDK for Android" carves out a clear niche: platform (Android), product (Contact Center), and channel features are all explicit, so conflict risk with Zoom's other SDKs (Meeting, apps, iOS) or generic chat/video skills is minimal. Third-person voice is used throughout, so no specificity penalty applies.

5 / 5

Total

17

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

relative_links

Relative link issues: 4 missing, 2 suspicious

Warning

Total

15

/

16

Passed

Repository

openai/plugins

Path

plugins/zoom/skills/contact-center/android/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.