zoom-meeting-sdk-web

Zoom Meeting SDK for Web - Embed Zoom meeting capabilities into web applications. Two integration options: Client View (full-page, familiar Zoom UI) and Component View (embeddable, Promise-based API). Includes SharedArrayBuffer setup for HD video, gallery view, and virtual backgrounds.

Quality

64%

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/meeting-sdk/web/SKILL.md

Quality

Content

70%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable with abundant executable code and clearly sequenced, validated workflows, but it suffers from a duplicated merged navigation section and a severe progressive-disclosure failure: the file is a monolith whose reference links point to nonexistent files while the real bundle references sit orphaned.

Suggestions

Move the large inline Client View and Component View API references, event-listener catalogs, and React patterns into the existing references/ files (or the referenced client-view/component-view/SKILL.md files) so SKILL.md becomes a concise overview.

Fix the broken links: either create the referenced files (concepts/sharedarraybuffer.md, troubleshooting/error-codes.md, RUNBOOK.md, etc.) or repoint them to the real references/ files that already exist (e.g. sharedarraybuffer-gallery-view.md, web.md).

Delete the duplicated 'Merged from meeting-sdk/web/SKILL.md' navigation index and the self-referential [SKILL.md](SKILL.md) links to remove redundant padding.

Dimension	Reasoning	Score
Conciseness	The bulk is useful, executable API reference Claude does not already know, but a duplicated 'Merged from meeting-sdk/web/SKILL.md' index repeats the Client-vs-Component table, Key Gotchas, and External Resources, and several self-referential [SKILL.md](SKILL.md) links add noise. Not a 3 because of this redundant padding; not a 1 because the core content is accurate and non-trivial rather than explaining concepts Claude knows.	2 / 3
Actionability	Provides fully executable, copy-paste-ready code throughout: a minimal Component View TS implementation, both Quick Starts, the auth-endpoint clone commands, full API option listings, event listeners, and a production-ready React pattern. This matches the 'fully executable, specific examples, copy-paste ready' anchor.	3 / 3
Workflow Clarity	Sequences are explicit — numbered Quick Start steps (1-5), an ASCII Core Workflow diagram, and an Optional Preflight Gate that validates readiness (allow/warn/block) before proceeding only on allow/approved-warn. Error-recovery guidance appears via 'Common failure points' and 'Common Issues & Solutions'. Joining a meeting is not a destructive/batch operation, so the workflow_clarity cap does not apply.	3 / 3
Progressive Disclosure	The body is a ~1100-line monolith with full inline API references for both views that belong in separate files, while nearly every reference link (client-view/SKILL.md, concepts/sharedarraybuffer.md, troubleshooting/*, RUNBOOK.md, ../../probe-sdk/SKILL.md, etc.) points to a file that does not exist in the bundle, and the 7 actual references/ files (web.md, sharedarraybuffer-gallery-view.md, web-tracking-id.md, etc.) are never linked — orphaned. This is broken, misleading navigation rather than well-signaled one-level-deep references.	1 / 3
	Total	9 / 12 Passed

Description

60%

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 specific and clearly names the two integration views plus SharedArrayBuffer features, but it omits any explicit 'Use when...' trigger guidance and does not distinguish Meeting SDK from the sibling Video SDK. These gaps cap completeness and distinctiveness at 2.

Suggestions

Add an explicit 'Use when...' clause naming natural triggers, e.g. 'Use when embedding Zoom meetings in a web app, adding Zoom video calls to a website, or when the user mentions Zoom Client View / Component View.'

Include common natural phrasings users actually say ('Zoom Web SDK', 'add Zoom to website', 'Zoom video integration') to broaden trigger coverage.

Add a one-line disambiguator against Video SDK (e.g. 'For real Zoom meetings, not non-meeting video sessions') to reduce conflict risk.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities: 'Embed Zoom meeting capabilities', 'Client View (full-page, familiar Zoom UI)', 'Component View (embeddable, Promise-based API)', and 'SharedArrayBuffer setup for HD video, gallery view, and virtual backgrounds.' It is not a 2 because it names several specific options/features rather than just a domain and a couple of actions.	3 / 3
Completeness	It clearly answers 'what' (embed Zoom meetings, two views, SharedArrayBuffer features) but contains no 'Use when...' clause or equivalent explicit trigger guidance, so per the rubric completeness is capped at 2. It is not a 1 because the 'what' is strong and specific.	2 / 3
Trigger Term Quality	Relevant keywords appear ('Zoom meeting', 'web applications', 'Client View', 'Component View') but common natural variations a user might say ('Zoom Web SDK', 'add Zoom to my website', 'Zoom integration') are missing, and 'SharedArrayBuffer' and 'Promise-based API' lean technical. Not a 3 because natural-term coverage is incomplete and partly jargon.	2 / 3
Distinctiveness Conflict Risk	'Zoom Meeting SDK for Web' is a recognizable niche, but the body devotes an entire Hard Routing Rule to distinguishing Meeting SDK from Video SDK, indicating a real sibling-skill conflict the description itself does not address. Not a 3 because that overlap is unresolved; not a 1 because the product niche is clearly named.	2 / 3
	Total	9 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (1116 lines); consider splitting into references/ and linking	Warning
relative_links	Relative link issues: 35 missing, 6 suspicious	Warning

	Total	14 / 16 Passed

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

Reviewed: 5 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.