zoom-contact-center-web

Zoom Contact Center SDK for Web. Use for web chat/video/campaign embeds, engagement event handling, app-context integrations, and Smart Embed postMessage workflows.

Quality

70%

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/contact-center/web/SKILL.md

Quality

Content

65%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 token-efficient and well-structured as an overview, but it lacks executable code and most of its referenced bundle files (3 of 4 Quick Links plus RUNBOOK.md) do not exist, undermining both actionability and navigation. Adding minimal working snippets and creating or removing the dead references would lift the weakest dimensions.

Suggestions

Add a small executable snippet per integration mode (e.g. the `zoomCampaignSdk:ready` gate and a `postMessage` Smart Embed handshake) so guidance is copy-paste ready rather than descriptive.

Create the referenced files (concepts/lifecycle-and-events.md, examples/app-context-and-state.md, troubleshooting/common-issues.md, RUNBOOK.md) or remove the dead links, since only references/web-reference-map.md currently exists.

Turn the guardrails into a short explicit preflight sequence with a validate→fix→retry loop (or restore the RUNBOOK checklist) so the workflow has concrete validation checkpoints.

Dimension	Reasoning	Score
Conciseness	The body is lean — short bullets for integration modes, guardrails, chaining, and operations, with no over-explanation of concepts Claude already knows (postMessage, iframe, CSP are named, not taught); every section earns its place; not a 2 because there is no padding to tighten.	3 / 3
Actionability	Concrete identifiers appear ("gate calls behind `zoomCampaignSdk:ready`", "Persist state by `engagementId`") and named patterns are given, but there is no executable code or copy-paste example — it describes rather than instructs; not a 1 because specific API/event tokens and concrete guardrails are present, not a 3 because nothing is executable.	2 / 3
Workflow Clarity	The three integration modes plus guardrails provide structure and an implicit checkpoint ("Validate CSP and allow-list settings before debugging logic"), but there is no explicit sequenced workflow with validation→fix→retry feedback loops, and the referenced RUNBOOK.md checklist does not exist; not a 1 because steps/checkpoints are at least implicit, not a 3 because validation is not explicitly sequenced.	2 / 3
Progressive Disclosure	The overview is well-organized into clear sections with one-level-deep signaled references (Quick Links, Operations), but 3 of the 4 Quick Links (concepts/lifecycle-and-events.md, examples/app-context-and-state.md, troubleshooting/common-issues.md) and RUNBOOK.md point to files that do not exist in the bundle — only references/web-reference-map.md is real; not a 1 because structure and signaling are sound, not a 3 because navigation is broken by dead references.	2 / 3
	Total	9 / 12 Passed

Description

75%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 well-scoped to a clear niche with an explicit "Use for..." trigger clause covering both what and when. It is slightly held back by jargon-heavy trigger terms and capability-area phrasing that is less concrete than crisp verb+object actions.

Dimension	Reasoning	Score
Specificity	Quotes "web chat/video/campaign embeds, engagement event handling, app-context integrations, and Smart Embed postMessage workflows" — names the domain and several capability areas, but these read as feature-area labels rather than the crisp verb+object actions (e.g. "extract text", "fill forms") that anchor a 3, and "app-context integrations" is somewhat abstract; not a 1 because multiple concrete areas are named.	2 / 3
Completeness	"Zoom Contact Center SDK for Web. Use for web chat/video/campaign embeds..." explicitly answers both what it does and when to use it via an explicit "Use for..." trigger clause (equivalent to "Use when..."); not a 2 because the trigger guidance is explicit rather than implied.	3 / 3
Trigger Term Quality	"web chat/video/campaign embeds" are natural user terms, but "engagement event handling", "app-context integrations", and "Smart Embed postMessage workflows" are jargon-heavy and miss common variations a user would actually say; not a 3 because coverage of natural phrasings is incomplete, not a 1 because some relevant keywords are present.	2 / 3
Distinctiveness Conflict Risk	"Zoom Contact Center SDK for Web" carves a clear niche with distinct triggers unlikely to fire for unrelated skills; not a 2 because the scoping is specific enough to avoid meaningful overlap despite neighboring Zoom SDKs.	3 / 3
	Total	10 / 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: 4 missing, 3 suspicious	Warning

	Total	15 / 16 Passed

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

Reviewed: 9 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.