zoom-virtual-agent-android

Zoom Virtual Agent Android integration via WebView. Use for Java/Kotlin bridge callbacks, native URL handling, support_handoff relay, and lifecycle-safe embedding.

Quality

86%

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

Quality

Content

72%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.

A concise, well-structured navigation-first skill body that points cleanly to one-level-deep references and avoids restating known concepts. Its main weakness is the absence of executable code examples and explicit validation checkpoints, which leave actionability and workflow clarity at the mid level.

Suggestions

Add a minimal executable bridge-registration snippet (Java/Kotlin) so the Integration Model becomes copy-paste-ready and actionability can reach 3.

Include a validation or sanity-check step in the workflow (e.g. verifying a JS callback fires after WebView load) so multi-step sequencing has explicit checkpoints.

Confirm the three Quick Links whose targets are not in the bundle (concepts/webview-lifecycle.md, examples/js-bridge-patterns.md, troubleshooting/common-issues.md) resolve to real files, or mark them as planned to avoid dead references.

Dimension	Reasoning	Score
Conciseness	The body is lean — e.g. 'Host campaign URL in Android WebView. Inject runtime context (`window.zoomCampaignSdkConfig`)' — with no explanation of concepts Claude already knows; every line earns its place. It does not pad with library or platform background that would drop it to score 2.	3 / 3
Actionability	It names concrete integration hooks (`exitHandler`, `commonHandler`, `support_handoff`, `window.zoomCampaignSdkConfig`, `shouldOverrideUrlLoading`) but provides no executable code showing how to wire them. It clears the 'some concrete guidance but incomplete' bar yet falls short of the copy-paste-ready anchor at score 3.	2 / 3
Workflow Clarity	The Integration Model lists a light sequence (host → inject context → register bridge → apply URL policy) and a guardrail ('Initialize handlers before expecting JS callbacks'), but there are no validation checkpoints or error-recovery loops. It is above score 1 because a sequence exists, but below score 3 because checkpoints are only implicit.	2 / 3
Progressive Disclosure	The SKILL.md is a clear overview with Quick Links pointing to one-level-deep references, and the referenced references/android-reference-map.md exists, keeping content appropriately split and easy to navigate. It is not score 2 because the overview stays concise and details are well-signaled rather than inlined.	3 / 3
	Total	10 / 12 Passed

Description

100%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.

A focused, third-person description that explicitly covers both what the skill does and when to use it, with concrete, distinctive trigger terms. Strong across all dimensions with no fluff or over-claims.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions — 'Java/Kotlin bridge callbacks', 'native URL handling', 'support_handoff relay', and 'lifecycle-safe embedding' — rather than vague language, matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	It states what the skill does ('Zoom Virtual Agent Android integration via WebView') and gives an explicit when clause ('Use for Java/Kotlin bridge callbacks, native URL handling, support_handoff relay...'), clearly answering both what and when. It is not the score-2 case because the trigger guidance is explicit rather than merely implied.	3 / 3
Trigger Term Quality	Terms like 'Zoom Virtual Agent Android', 'Java/Kotlin bridge callbacks', 'WebView', and 'support_handoff' are the natural phrases a developer integrating Zoom VA on Android would say, giving good coverage of natural trigger keywords. It is slightly technical-leaning but does not rely on jargon alone, so it sits above the 'some relevant keywords but missing variations' level.	3 / 3
Distinctiveness Conflict Risk	The niche is sharply defined — Zoom Virtual Agent on Android via WebView — with distinct triggers that make it unlikely to fire for unrelated skills. It is not score 2 because the scope is too specific to overlap meaningfully with generic Android or web skills.	3 / 3
	Total	12 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 3 missing, 2 suspicious	Warning

	Total	15 / 16 Passed

Repository: openai/plugins
Path: plugins/zoom/skills/virtual-agent/android/SKILL.md
Commit: 11c74d6

Reviewed: 17 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.