build-zoom-meeting-app

Use when embedding meetings.

Quality

48%

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/build-zoom-meeting-app/SKILL.md

Quality

Content

67%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 routing skill: a clear conditional workflow with decision guards, a scoped coverage list, clearly signaled one-level-deep references, and a useful common-mistakes section. Its main weakness is actionability — several steps defer to references without saying which reference or what to do for each branch, and the linked sibling skills are not present to resolve.

Suggestions

Make step 3 concrete: state which reference covers which platform (e.g. "web → meeting-sdk/web.md, native → meeting-sdk/native.md") instead of "Pull in the relevant platform references".

Give the custom-video-session branch from step 1 an explicit action (e.g. "Route to Video SDK / video-sdk skill for custom video sessions") so every decision in the workflow resolves.

Verify the five sibling-skill paths (../meeting-sdk/SKILL.md, ../rest-api/SKILL.md, etc.) exist at the referenced location, or inline minimal fallback guidance if they might not.

Dimension	Reasoning	Score
Conciseness	The body is lean (~35 lines), assumes Claude's competence, and contains no explanations of known concepts; only the opening line and the "Covers" list partially duplicate the workflow items, which is trimmable but not verbose — efficient with minor instances to tighten.	4 / 5
Actionability	The conditional routing rules are concrete ("Route to Meeting SDK if the user needs actual Zoom meetings", "Add REST API only for meeting creation, resource management, or reporting") but key execution details are missing: step 3 "Pull in the relevant platform references" never says which references map to web vs native, and the custom-video-session branch has no stated action — matching "some concrete guidance but incomplete; missing key details".	3 / 5
Workflow Clarity	The five-step workflow is clearly sequenced with explicit "only if"/"only when" guards that function as decision checkpoints; it is not a destructive or batch operation so no validation loop is required, and the gap is that the video-session branch (step 1) never resolves to a stated action — clear sequence with a minor gap.	4 / 5
Progressive Disclosure	Sections are well organized and the five references are clearly signaled, one level deep, under "Primary References" with per-reference scope implied by their names; however, all five linked paths (../meeting-sdk/SKILL.md etc.) are unresolvable in this environment, so navigation cannot be fully trusted — good structure with a minor organization gap.	4 / 5
	Total	15 / 20 Passed

Description

28%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 a bare trigger clause with neither a capability statement nor natural trigger terms. It names the meeting-embedding domain but omits "Zoom", the SDKs involved, and every what-does-this-do detail, leaving it both incomplete and prone to overlapping sibling skills.

Suggestions

Add a what-clause stating capabilities, e.g. "Routes and implements Zoom meeting embedding: join/auth flows, meeting creation, and platform-specific SDK setup."

Include natural trigger terms users would actually say: "Zoom meeting", "embed Zoom", "join a meeting in-app", "Meeting SDK".

Mention "Zoom" explicitly and contrast with custom video sessions to reduce conflict risk with a sibling video-sdk skill.

Dimension	Reasoning	Score
Specificity	The description names the domain ("embedding meetings") but lists no concrete actions whatsoever — matching "names the domain but actions are minimal or generic" rather than anchor 1, since the domain itself is genuinely named rather than pure abstraction.	2 / 5
Completeness	The description provides only a 'when' clause ("Use when embedding meetings") with no statement of what the skill does — an exact match for anchor 2 ('only when is present without what'); it cannot reach 3 because the 'what' is entirely absent, not merely weakly implied.	2 / 5
Trigger Term Quality	Only the keyword pair "embedding meetings" appears; users would naturally say "Zoom meeting", "embed Zoom", "join flow", or "video call", none of which are present, matching "one or two generic keywords; missing the natural phrases users say".	2 / 5
Distinctiveness Conflict Risk	"Embedding meetings" is somewhat specific but, without "Zoom" or "SDK", could still overlap with generic video-conferencing, calendar, and video-sdk skills — more specific than anchor 2's "very broad" but not as clean as anchor 4's "mostly distinct".	3 / 5
	Total	9 / 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: 5 suspicious	Warning

	Total	15 / 16 Passed

Repository: openai/plugins
Path: plugins/zoom/skills/build-zoom-meeting-app/SKILL.md
Commit: 5fd93af

Reviewed: 2 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.