build-zoom-virtual-agent

Use when using Virtual Agent.

Quality

43%

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/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 routing overview with a clear workflow and references section. Its main weaknesses are directional rather than executable guidance and a references section whose links do not match the actual bundle.

Suggestions

Add at least one concrete, copy-paste-ready snippet (e.g. a WebView bridge injection snippet or a validation command) to lift actionability.

Insert an explicit validation checkpoint in the workflow, such as 'Confirm campaign, entry ID, and allowed origins before coding; only proceed when all are verified.'

Fix the References section to match the actual bundle: remove or create the missing web/android/ios/concepts/troubleshooting paths, and surface the existing references/environment-variables.md, references/samples-validation.md, and references/versioning-and-drift.md.

Dimension	Reasoning	Score
Conciseness	The body is lean and dense with specific terms (SDK readiness, bridge injection, CSP, WebView lifecycle, version drift) with no padding or explanation of concepts Claude already knows, so every token earns its place.	3 / 3
Actionability	It gives concrete checklists of what to confirm (entry ID, allowed origins, lifecycle events) but the guidance is directional rather than executable, and step 2 simply delegates ('Route to the platform skill').	2 / 3
Workflow Clarity	The five steps are clearly sequenced with a debug step (step 5), but there is no explicit validation gate or 'only proceed when confirmed' checkpoint, so checkpoints are only implicit.	2 / 3
Progressive Disclosure	The References section is well-signaled with one-level links, but several referenced paths do not exist (web/, android/, ios/, concepts/, troubleshooting/) and three of four actual reference files are not surfaced, making navigation unreliable.	2 / 3
	Total	9 / 12 Passed

Description

22%

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 little more than a circular trigger clause ('Use when using Virtual Agent.') that omits any statement of what the skill does. It is lean but underspecified on both capabilities and trigger coverage.

Suggestions

Add concrete capabilities, e.g. 'Embed or wrap Zoom Virtual Agent in web campaigns and mobile WebView integrations, configure campaigns and handoff, and debug SDK/bridge/CSP issues.'

Expand trigger terms to natural variations users would say, such as 'Zoom Virtual Agent', 'Virtual Agent chatbot', 'web campaign bot', or 'WebView bot integration'.

Combine the what and when into a single sentence so both capability and trigger are explicit, following the strong examples in the rubric.

Dimension	Reasoning	Score
Specificity	The description 'Use when using Virtual Agent.' names no concrete actions or capabilities at all, only a trigger clause, matching the 'vague or no actions' anchor.	1 / 3
Completeness	It answers only the 'when' (Use when using Virtual Agent) and entirely omits the 'what does this do', matching the 'missing what OR when' anchor.	1 / 3
Trigger Term Quality	It includes one relevant keyword ('Virtual Agent') a user might say, but coverage is thin and missing common variations, so it falls short of the broad natural-term anchor.	2 / 3
Distinctiveness Conflict Risk	Tying the trigger to a specific named product gives it a niche, but it does not differentiate what kind of Virtual Agent work, so it could overlap with related skills.	2 / 3
	Total	6 / 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: 5 missing	Warning

	Total	15 / 16 Passed

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

Reviewed: about 9 hours 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.