zoom-virtual-agent-ios

Zoom Virtual Agent iOS integration via WKWebView. Use for Swift/Objective-C script injection, message handlers, support_handoff relay, and URL routing policies.

Quality

81%

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

71%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 well-organized, token-efficient overview that sequences the integration clearly and points to deeper references. Its weaknesses are missing executable detail (deferred to bundle files that are largely absent) and broken reference links that undermine navigation.

Suggestions

Create the missing referenced bundle files (concepts/webview-lifecycle.md, examples/js-bridge-patterns.md, troubleshooting/common-issues.md) or remove the dead links so navigation resolves.

Add at least one concrete, executable snippet in SKILL.md (e.g., a minimal WKUserScript injection or message-handler registration) so the core action is actionable without the bundle.

Add a brief validation/verification step to the Integration Model (e.g., confirm handlers are registered before load, or how to verify the bridge works) to strengthen workflow checkpoints.

Dimension	Reasoning	Score
Conciseness	The body is a lean overview with no padding or re-explanation of concepts Claude already knows; every section (Integration Model, Hard Guardrails, Chaining) earns its tokens.	5 / 5
Actionability	It names concrete APIs and constants (window.zoomCampaignSdkConfig, WKUserScript, SFSafariViewController, support_handoff) but gives no executable code or steps, and the bundle files meant to hold the actionable detail are missing, leaving key details incomplete.	3 / 5
Workflow Clarity	The Integration Model gives a clear sequence (load URL → inject config → register handlers → handle navigation) with an explicit ordering checkpoint ('Register scripts and handlers before web interaction'), though verification steps are absent.	4 / 5
Progressive Disclosure	Structure and signaling are good (numbered Quick Links, organized sections, one-level-deep references), but 3 of the 4 referenced files (concepts/webview-lifecycle.md, examples/js-bridge-patterns.md, troubleshooting/common-issues.md) do not exist, breaking navigation.	3 / 5
	Total	15 / 20 Passed

Description

92%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 crisp, third-person description that states both purpose and use cases with concrete, domain-specific actions and an explicit trigger clause. Its only gap is a slight lack of natural-language synonyms a non-expert user might voice.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'script injection, message handlers, support_handoff relay, and URL routing policies' — giving comprehensive coverage of the integration's tasks rather than vague abstraction.	5 / 5
Completeness	Explicitly states what ('Zoom Virtual Agent iOS integration via WKWebView' plus concrete actions) and when ('Use for ...') with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Strong domain keywords ('Zoom Virtual Agent', 'iOS', 'WKWebView', 'Swift/Objective-C') but missing common synonyms users might say (e.g., 'chatbot', 'mobile SDK', 'WebView bridge'), so a few natural terms are absent.	4 / 5
Distinctiveness Conflict Risk	A tight, specific niche (Zoom Virtual Agent on iOS via WKWebView) with distinct triggers and minimal realistic overlap with other skills.	5 / 5
	Total	19 / 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/ios/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.