zoom-meeting-sdk-linux

Zoom Meeting SDK for Linux - C++ headless meeting bots with raw audio/video access, transcription, recording, and AI integration for server-side automation

Quality

66%

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/linux/SKILL.md

Quality

Content

65%Weight 40%Scale 1-3

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

The skill is highly actionable with executable code throughout, but it is verbose with duplicated sections and breaks progressive disclosure by inlining detail that belongs in reference files while pointing to several non-existent files.

Suggestions

Move the detailed Quick Start code blocks and SDK/API reference material into reference files, leaving SKILL.md as a lean overview with well-signaled one-level-deep links.

Remove the duplicated content between the 'SDK Overview', 'Key Features', and 'Quick Start' sections, and consolidate the repeated link/troubleshooting lists.

Add an inline validate→fix→retry checkpoint (e.g. confirm CanStartRawRecording and GLib loop running before subscribing) rather than deferring all checks to the RUNBOOK.

Create or remove the dangling references (linux.md, concepts/high-level-scenarios.md, meeting-sdk-bot.md, ../references/*.md, RUNBOOK.md) so navigation links resolve to real files.

Dimension	Reasoning	Score
Conciseness	The body is concrete and mostly efficient, but content is duplicated across sections (the SDK Overview and Key Features table overlap, the Quick Start repeats the intro's raw-recording flow, and link lists recur several times), so it could be tightened.	2 / 3
Actionability	Provides copy-paste-ready, executable C++ snippets and bash commands for SDK download, init, auth, join, raw recording, and PulseAudio setup.	3 / 3
Workflow Clarity	Join→record→subscribe sequences are clear with error throws, but there is no explicit validate/fix/retry feedback loop inline; preflight is deferred to a referenced RUNBOOK rather than an inline checkpoint.	2 / 3
Progressive Disclosure	References are well-signaled, but the SKILL.md is itself monolithic (~420 lines of detailed API/code that could live in reference files), and most referenced paths (linux.md, concepts/high-level-scenarios.md, meeting-sdk-bot.md, ../references/*.md, RUNBOOK.md) do not exist in the bundle.	2 / 3
	Total	9 / 12 Passed

Description

67%Weight 40%Scale 1-3

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 distinctive, clearly targeting Zoom Meeting SDK Linux development. Its main weakness is the absence of an explicit 'Use when...' trigger clause, leaving the activation context implied rather than stated.

Suggestions

Append an explicit trigger clause such as 'Use when building Zoom meeting bots on Linux or when the user mentions Zoom Meeting SDK, raw audio/video capture, or headless meeting automation.'

Add natural user-facing terms (e.g. 'Zoom bot', 'meeting recording bot') alongside the technical phrasing to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'raw audio/video access, transcription, recording, and AI integration' — rather than vague language.	3 / 3
Completeness	The 'what' is clearly stated, but there is no explicit 'when should Claude use it' trigger clause, which caps completeness at 2 per the guidelines.	2 / 3
Trigger Term Quality	Natural terms like 'Zoom meeting', 'recording', and 'transcription' appear, but there is no explicit 'Use when...' phrasing and the wording leans technical ('headless meeting bots', 'server-side automation').	2 / 3
Distinctiveness Conflict Risk	The 'Zoom Meeting SDK for Linux' niche is highly specific and unlikely to trigger for unrelated skills.	3 / 3
	Total	10 / 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: 19 missing, 5 suspicious	Warning

	Total	15 / 16 Passed

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

Reviewed: 7 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.