zoom-virtual-agent-web

Zoom Virtual Agent SDK for web embeds. Use for campaign or entry ID chat launch, event-driven controls, user context updates, and CSP-safe deployment.

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

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

Quality

Content

57%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.

The body is admirably concise and well-organized with clear guardrails, but it lacks executable code and an explicit validated workflow, and most critically its progressive-disclosure links are broken — three of four referenced bundle files do not exist.

Suggestions

Create the three missing referenced files (concepts/lifecycle-and-events.md, examples/campaign-and-entry-patterns.md, troubleshooting/common-issues.md) or remove/fix the broken Quick Links so navigation resolves.

Add a minimal executable launch snippet (e.g., a ready-gated show call) to lift actionability from directive prose to copy-paste-ready code.

Render the guardrails as an explicit numbered workflow with a validation checkpoint (verify CSP/script host, then gate on ready, then show) to give a clear validate→proceed sequence.

Dimension	Reasoning	Score
Conciseness	The body is lean with no padding and no explanation of concepts Claude already knows; every line (guardrails, links, chaining) earns its place, matching the lean-and-efficient anchor.	3 / 3
Actionability	"Hard Guardrails" give concrete directives (gate behind "zoomCampaignSdk:ready or waitForReady()", do not call show/hide before init) but there is no executable code or copy-paste-ready example, leaving guidance directive rather than fully executable.	2 / 3
Workflow Clarity	A sequence is implied (init → ready → show/hide) and a validation hint appears ("Keep CSP and script host policy validated before debugging business logic"), but there is no explicit multi-step workflow with checkpoints or a validate→fix→retry feedback loop.	2 / 3
Progressive Disclosure	Scoring against the actual bundle: only references/web-reference-map.md exists, while concepts/lifecycle-and-events.md, examples/campaign-and-entry-patterns.md, and troubleshooting/common-issues.md are referenced but missing, so the signaled one-level-deep navigation is broken.	1 / 3
	Total	8 / 12 Passed

Description

85%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.

The description is strong: it states concrete capabilities and provides an explicit "Use for..." trigger covering both what and when, with a clearly distinctive Zoom-web niche. Its only weakness is trigger-term naturalness, leaning SDK-technical rather than echoing how a user would phrase the request.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "campaign or entry ID chat launch, event-driven controls, user context updates, and CSP-safe deployment" — matching the multi-action anchor rather than a single-named-action score of 2.	3 / 3
Completeness	Answers both "what" (Zoom Virtual Agent SDK for web embeds) and "when" via an explicit "Use for..." trigger clause, satisfying the both-present anchor for a 3.	3 / 3
Trigger Term Quality	Includes relevant domain terms ("campaign or entry ID chat launch", "CSP-safe deployment") but they skew technical/SDK-specific, missing the common natural phrasings a user would say; not the broad natural coverage of a 3.	2 / 3
Distinctiveness Conflict Risk	Clear niche — Zoom Virtual Agent SDK scoped to web embeds with distinct triggers (campaign/entry ID, CSP deployment) — making it unlikely to fire for the wrong skill.	3 / 3
	Total	11 / 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, 4 suspicious	Warning

	Total	15 / 16 Passed

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

Reviewed: 10 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.