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

76%

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

72%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 a lean, well-structured index with concrete API-level guardrails, but it functions as an overview only: it lacks an explicit sequenced workflow with validation checkpoints, and most of its Quick Link references point to files that are absent from the bundle.

Suggestions

Add the missing referenced files (concepts/lifecycle-and-events.md, examples/campaign-and-entry-patterns.md, troubleshooting/common-issues.md) or remove their links, so Quick Links resolves to real bundle content.

Include a short ordered launch workflow (e.g., preflight CSP/host check → wait for ready → launch → verify) with an explicit validation checkpoint to raise workflow clarity.

Make the CSP guardrail actionable by naming the concrete check or command to run rather than only stating the constraint.

Dimension	Reasoning	Score
Conciseness	The body is extremely lean — official doc links, four quick links, four guardrail bullets, and chaining pointers with no padding and no explanation of concepts Claude already knows — matching the anchor for lean, efficient content where every token earns its place.	5 / 5
Actionability	Guardrails give concrete, API-specific directives ('Gate calls behind readiness (`zoomCampaignSdk:ready` or `waitForReady()`)', 'Do not call `show/hide/open/close` before SDK initialization'), providing mostly executable guidance; not a 5 because 'Keep CSP and script host policy validated' stays abstract without a concrete check to run.	4 / 5
Workflow Clarity	Only implicit sequencing is present via guardrail ordering ('before SDK initialization', 'before debugging business logic'); there is no explicit multi-step workflow or validation checkpoint, matching the anchor for sequence present but checkpoints missing or implicit.	3 / 5
Progressive Disclosure	Structure is well organized with a clearly signaled Quick Links section pointing one level deep, but only 1 of the 4 referenced bundle paths (references/web-reference-map.md) actually exists — the other three (concepts/, examples/, troubleshooting/) are missing — so navigation is undermined beyond a minor gap.	3 / 5
	Total	15 / 20 Passed

Description

80%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.

The description is concise, third-person, and clearly answers both what the skill does and when to use it with concrete trigger phrases. It is strong on completeness and specificity, with only minor gaps in natural trigger-term breadth and a slight overlap risk with related web-embed skills.

Dimension	Reasoning	Score
Specificity	Names the domain ('Zoom Virtual Agent SDK for web embeds') and lists several concrete action areas ('campaign or entry ID chat launch', 'event-driven controls', 'user context updates', 'CSP-safe deployment'), matching the anchor for several specific actions with minor coverage gaps; not a 5 because the actions are stated as categories rather than fully enumerated concrete operations.	4 / 5
Completeness	It explicitly states what the skill is ('Zoom Virtual Agent SDK for web embeds') and when to use it via a concrete 'Use for ...' clause enumerating trigger phrases, matching the anchor that clearly and explicitly answers both what and when.	5 / 5
Trigger Term Quality	Relevant domain keywords are present ('campaign or entry ID chat launch', 'event-driven controls', 'CSP-safe deployment') but they lean technical and miss common user-side synonyms or variations, fitting the anchor for some relevant keywords missing common variations; not a 4 because natural lay phrasing is sparse.	3 / 5
Distinctiveness Conflict Risk	'Zoom Virtual Agent SDK for web embeds' carves a clear niche with distinct triggers, but 'web embeds' could marginally overlap with the adjacent contact-center web context referenced in chaining, so it is mostly distinct with minor overlap risk rather than a clean 5.	4 / 5
	Total	16 / 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, 4 suspicious	Warning

	Total	15 / 16 Passed

Repository: openai/plugins
Path: plugins/zoom/skills/virtual-agent/web/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.