CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

zoom-meeting-sdk-macos

Zoom Meeting SDK for macOS native apps. Use when embedding Zoom meetings in macOS with default/custom UI, PKCE + SDK auth, host start/join flows, and desktop meeting feature controllers.

61

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/zoom/skills/meeting-sdk/macos/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%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 exemplary in token efficiency and its information architecture follows progressive-disclosure best practice, but it functions purely as a navigation index and most of what it navigates to is missing from the bundle. Restoring the referenced files would lift actionability and workflow clarity substantially without changing the lean body.

Suggestions

Ship the missing bundle files referenced by 'Start Here' and 'Operations' (macos.md, concepts/lifecycle-workflow.md, concepts/architecture.md, examples/join-start-pattern.md, scenarios/high-level-scenarios.md, troubleshooting/common-issues.md, RUNBOOK.md) or remove the dead links — currently 8 of 11 links are unresolvable.

Add a minimal inline quick-start (e.g. a short SDK-initialize/auth-then-join snippet or a 3-step outline) so SKILL.md provides some executable guidance even before the linked files are read.

Resolve the [../SKILL.md](../SKILL.md) cross-reference — it points outside the skill directory and does not exist in this bundle; either materialize it or drop it from 'Key Sources'.

DimensionReasoningScore

Conciseness

The ~25-line body is a lean index — a one-line purpose statement ("Use this skill when building macOS apps with embedded Zoom meeting capabilities"), a numbered reading list, and short link sections — with zero padding or explanation of concepts Claude already knows. Every token earns its place, matching the anchor-5 'lean and efficient' example.

5 / 5

Actionability

The body offers only high-level pointers — a numbered "Start Here" list and a "RUNBOOK.md - 5-minute preflight and debugging checklist" link — with no concrete commands, code, or steps, and critically 8 of the 11 referenced paths (macos.md, concepts/lifecycle-workflow.md, concepts/architecture.md, examples/join-start-pattern.md, scenarios/high-level-scenarios.md, troubleshooting/common-issues.md, RUNBOOK.md, ../SKILL.md) do not exist in the bundle, so even the pointers can't be followed. This matches anchor 2 ('minimal concrete guidance; high-level hints but missing the specific steps to execute') rather than 3, because the guidance that exists is unresolvable.

2 / 5

Workflow Clarity

The numbered "Start Here" list gives a rough reading sequence, but there is no operational workflow with validation checkpoints, and the claimed preflight/debugging runbook ("RUNBOOK.md - 5-minute preflight and debugging checklist") is missing from the bundle, leaving sequence-with-gaps — anchor 3 ('steps listed but validation gaps') rather than 4, since the main follow-through artifact doesn't exist.

3 / 5

Progressive Disclosure

The structure is well designed — a clear overview with one-level-deep, well-signaled references organized into Start Here / Key Sources / Operations — but scored against the actual bundle, only the three references/*.md files exist; the majority of linked navigation targets are absent, so the otherwise good organization degrades to anchor 3 ('some structure but could be better organized') rather than 4–5.

3 / 5

Total

13

/

20

Passed

Description

87%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.

A strong description: it pairs an explicit 'Use when' trigger with a concrete list of the SDK's capability surface, and the macOS platform qualifier keeps conflict risk minimal. The only slack is that capabilities are listed as topics rather than action verbs and a few natural synonyms are absent.

DimensionReasoningScore

Specificity

Quotes like "PKCE + SDK auth", "host start/join flows", "default/custom UI", and "desktop meeting feature controllers" name several concrete capabilities, but they read more as a topic list than action verbs, leaving minor gaps versus the comprehensive anchor 5.

4 / 5

Completeness

It explicitly answers both what ("Zoom Meeting SDK for macOS native apps... PKCE + SDK auth, host start/join flows, and desktop meeting feature controllers") and when ("Use when embedding Zoom meetings in macOS with...") with concrete trigger phrases, matching the anchor-5 good example structure. Not 4 because the 'when' clause is explicit and specific, not merely implied.

5 / 5

Trigger Term Quality

Natural terms are present ("Zoom Meeting SDK", "macOS", "native apps", "embedding Zoom meetings", "host start/join"), which a user would plausibly say, but common variations/synonyms (e.g. "Swift/Objective-C app", "video conferencing", "in-app meeting") are missing — matching anchor 4 rather than the exhaustive coverage of 5.

4 / 5

Distinctiveness Conflict Risk

"Zoom Meeting SDK for macOS" carves out a clear niche with distinct triggers; the platform qualifier (macOS) and SDK-specific terms (PKCE, host start/join) make confusion with adjacent skills (iOS/Windows SDKs, Zoom Video SDK, general video conferencing) unlikely.

5 / 5

Total

18

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

relative_links

Relative link issues: 7 missing, 1 suspicious

Warning

Total

15

/

16

Passed

Repository

openai/plugins

Path

plugins/zoom/skills/meeting-sdk/macos/SKILL.md

Reviewed

Table of Contents

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.