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

76%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/zoom/skills/virtual-agent/android/SKILL.md

Quality

Content

65%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.

A token-efficient, well-structured overview that names the right APIs and guardrails but lacks executable code and validation checkpoints. Its biggest defect is that three of the four referenced bundle files do not exist, breaking the progressive-disclosure navigation it relies on.

Suggestions

Add a minimal executable WebView/bridge snippet (e.g., addJavascriptInterface registration and window.zoomCampaignSdkConfig injection) so the Integration Model is copy-ready, not just named.

Create or remove the missing referenced files (concepts/webview-lifecycle.md, examples/js-bridge-patterns.md, troubleshooting/common-issues.md) so Quick Links resolve to real content.

Number the Integration Model steps and add an explicit validation checkpoint (e.g., verify bridge callbacks fire before applying URL policy) to convert the implied sequence into a clear workflow.

Dimension	Reasoning	Score
Conciseness	The body is a lean set of bullets with no padding and no re-explanation of concepts Claude already knows (WebView, Android, JS bridges). Every line carries integration-specific information and assumes Claude's competence. It is not below 5 because nothing is redundant or over-explained.	5 / 5
Actionability	Names concrete APIs (window.zoomCampaignSdkConfig, exitHandler, commonHandler, support_handoff, shouldOverrideUrlLoading) but provides no executable code or commands for registering the bridge, injecting config, or setting up the WebView. It is not a 4 because the guidance stops at named concepts rather than copy-ready steps, and not a 2 because the named handlers are concrete enough to act on.	3 / 5
Workflow Clarity	The Integration Model bullets imply a rough sequence (host URL → inject context → register bridge → apply URL policy) and Hard Guardrails add constraints, but there is no numbered sequence and no validation checkpoints. It is not a 4 because checkpoints are entirely implicit, and not a 2 because a coherent sequence is present.	3 / 5
Progressive Disclosure	The body is structured as a clear overview with a well-signaled Quick Links list pointing one level deep to concepts/, examples/, references/, and troubleshooting/ files. However, of the four referenced bundle paths only references/android-reference-map.md actually exists, so most navigation links are broken; this keeps it at 3 rather than 4-5 despite the good structural intent.	3 / 5
	Total	14 / 20 Passed

Description

87%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 precise, third-person description that pairs a clear capability statement with an explicit "Use for" trigger clause covering concrete integration concerns. It is specific, well-triggered, and highly distinct within its niche.

Dimension	Reasoning	Score
Specificity	Lists several concrete capability areas — "Java/Kotlin bridge callbacks, native URL handling, support_handoff relay, and lifecycle-safe embedding" — naming the domain plus multiple specific actions, with only minor abstraction gaps. It is not a 5 because the actions are categorized capabilities rather than fully concrete, distinct operations.	4 / 5
Completeness	Explicitly states both what ("Zoom Virtual Agent Android integration via WebView") and when via a concrete "Use for ..." trigger clause enumerating bridge callbacks, URL handling, support_handoff, and lifecycle embedding. It clearly matches the anchor that requires concrete trigger phrases for both what and when.	5 / 5
Trigger Term Quality	Strong natural keyword coverage ("Zoom Virtual Agent", "Android", "WebView", "Java/Kotlin bridge callbacks", "support_handoff", "lifecycle") that a developer would actually say. It is not a 5 because it lacks synonyms and file/extension variants, leaning slightly technical.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche (Zoom Virtual Agent on Android via WebView) with distinct, specific triggers and minimal overlap with other skills. The combination of vendor, platform, and mechanism makes conflict risk very low.	5 / 5
	Total	18 / 20 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: 1e28582

Reviewed: 7 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.