ui-toolkit

Use when using Zoom UI Toolkit.

Quality

52%

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/ui-toolkit/SKILL.md

Quality

Content

65%

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 concise, well-structured overview with a sensible workflow and clear reference signaling, but it lacks executable code and validation checkpoints, and half of its reference links point to nonexistent files. It is efficient but not fully actionable or navigable.

Suggestions

Add a minimal executable snippet to the body (e.g. the npm install command and the UI Toolkit mount call) so the core integration is copy-paste ready before deferring to full-guide.md.

Insert an explicit validation checkpoint in the workflow, e.g. after step 3 'verify the session mounts and joins' before configuring chat/captions/recordings in step 4.

Fix or remove the broken references: troubleshooting/common-issues.md and ../video-sdk/web/SKILL.md do not exist in the bundle.

Dimension	Reasoning	Score
Conciseness	The body is lean: a one-sentence intro with a routing note and six compact workflow directives, with no padding or explanation of concepts Claude already knows, matching 'lean and efficient; every token earns its place'; it is not downgraded because the dense feature lists are efficient packing rather than verbosity.	3 / 3
Actionability	Steps enumerate concrete sub-tasks (chat, captions, recordings, theming, cross-origin isolation, token generation) and routing decisions, but provide no executable code, npm package, or mount/signature snippets, fitting 'some concrete guidance but incomplete'; not 1 because it is more specific than vague 'process as needed' phrasing, not 3 because nothing is copy-paste ready.	2 / 3
Workflow Clarity	The six steps form a clear, well-ordered sequence (above 1), but there are no explicit validation checkpoints such as 'verify the session joins before configuring chat', and step 6 is a debug pointer rather than a validate-fix-retry loop, fitting 'sequence present but checkpoints missing or implicit'.	2 / 3
Progressive Disclosure	The structure is a lean overview with well-labeled, one-level-deep references (better than 1), but two of the four referenced paths are broken: troubleshooting/common-issues.md and ../video-sdk/web/SKILL.md do not exist, so navigation is not actually easy and it cannot reach 3.	2 / 3
	Total	9 / 12 Passed

Description

40%

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 a terse, tautological trigger that names the product but fails to convey concrete capabilities or distinguish it from sibling Zoom skills. It meets the minimum 'Use when' trigger requirement but lacks the action specificity and trigger-term coverage of strong examples.

Suggestions

Add concrete actions to the description, e.g. 'Mount Zoom Video SDK UI Toolkit for prebuilt web session UIs: configure join/leave, chat, captions, recordings, and theming, with server-side signature generation.'

Expand trigger terms with natural variations a user would say, such as 'Zoom Video SDK UI Toolkit', 'prebuilt Zoom web UI', or 'embed a Zoom video session'.

Add a one-line disambiguator in the description, e.g. 'For full Meeting SDK joins, use build-zoom-meeting-sdk-app instead', to reduce conflict with sibling Zoom skills.

Dimension	Reasoning	Score
Specificity	The description 'Use when using Zoom UI Toolkit.' names the product but describes zero concrete actions (no mount/configure/join/signature-generation verbs), matching the 'vague or no actions' anchor; it cannot reach 2 because no specific capability is enumerated.	1 / 3
Completeness	It has an explicit 'Use when' trigger (so not capped below 2 for a missing trigger clause), but the 'what' is tautological ('using Zoom UI Toolkit') with no substantive capability statement; it falls short of 3 because the what is not clearly answered with concrete actions.	2 / 3
Trigger Term Quality	'Zoom UI Toolkit' is a real product term a user might say, but the phrasing is circular ('Use when using...') with no natural variations or task-oriented triggers, fitting 'some relevant keywords but missing common variations'; not 3 due to lack of coverage, not 1 because the product name is a legitimate keyword.	2 / 3
Distinctiveness Conflict Risk	The Zoom UI Toolkit product name carves a specific niche (so above 1), but the description does not disambiguate from sibling Zoom skills (Meeting SDK, Video SDK) that the body itself references, leaving overlap risk; not 3 because the distinct niche is not articulated.	2 / 3
	Total	7 / 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: 1 missing, 1 suspicious	Warning

	Total	15 / 16 Passed

Repository: openai/plugins
Path: plugins/zoom/skills/ui-toolkit/SKILL.md
Commit: 11c74d6

Reviewed: 1 day 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.