CtrlK
BlogDocsLog inGet started
Tessl Logo

zoom-video-sdk-linux

Zoom Video SDK for Linux - C++ headless bots, raw audio/video capture/injection, Qt/GTK integration, Docker support

49

Quality

54%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./plugins/zoom/skills/video-sdk/linux/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

46%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 content is highly actionable with concrete code and commands, but it suffers from heavy redundancy (an entire second merged document duplicating navigation and critical points) and a progressive-disclosure structure whose referenced bundle files largely do not exist, while inline validation checkpoints for risky SDK operations are absent.

Suggestions

Remove the duplicated 'Merged from video-sdk/linux/SKILL.md' section (lines ~233-431) and consolidate the repeated critical points, sample-repo tables, use-case ladders, and quick-reference into a single canonical version to cut the body roughly in half.

Either create the referenced bundle files (concepts/, examples/, troubleshooting/, RUNBOOK.md) or drop the links to them, since the bundle currently contains only references/linux-reference.md and most navigation points at missing material.

Add inline validation checkpoints for the risky flows (e.g. after initialize, verify the SDK returned success before addListener/joinSession; after PulseAudio config, verify the daemon is running) rather than relying solely on the external RUNBOOK.

DimensionReasoningScore

Conciseness

The 435-line body is noticeably padded: it repeats the same critical points multiple times ('NO Canvas API' appears ~4 times, PulseAudio ~15 times, the architecture pattern is restated in Quick Links, By Use Case, Most Critical Documents, Key Learnings, and Quick Reference), and an entire second merged document ('Merged from video-sdk/linux/SKILL.md') duplicates the navigation, structure tree, use-case paths, critical documents, sample repos, and quick reference already present above.

2 / 5

Actionability

Guidance is mostly executable: concrete apt commands, a complete Quick Start C++ snippet with init params and session context, and copy-paste solutions for PulseAudio, Qt5 symlinks, heap mode, and virtual devices, with only minor gaps (the Sample Architecture code block is truncated and never closed).

4 / 5

Workflow Clarity

Sequences are present (Quick Start's numbered 1-4 create/initialize/listen/join flow, the onboarding path, and by-use-case ladders), but there are no explicit validation checkpoints for the risky operations involved (SDK init, session join, audio config); the only validation reference is the external RUNBOOK, so checkpoints are missing rather than inline.

3 / 5

Progressive Disclosure

Although the body is full of one-level-deep reference links, they are not well-organized: the file is a monolithic wall split across two merged documents with duplicate headings (Sample Repositories, Quick Start/Path, Most Critical Documents), and almost every referenced bundle file (concepts/, examples/, troubleshooting/, RUNBOOK.md) does not actually exist in the bundle—only references/linux-reference.md is present—so the structure is buried and largely points at missing material.

2 / 5

Total

11

/

20

Passed

Description

62%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 specific, third-person, and clearly differentiated, but it omits any explicit 'when to use' trigger guidance and only partially covers the SDK's feature surface, capping completeness and trigger-term quality.

Suggestions

Add an explicit trigger clause, e.g. 'Use when building Linux C++ bots or apps with the Zoom Video SDK, or when the user mentions raw audio/video capture, headless Zoom bots, or Qt/GTK Zoom integration.'

Broaden trigger keywords to include synonyms users actually say: 'raw media', 'PCM/YUV frames', 'virtual camera/mic', 'cloud recording', 'live streaming', and 'live transcription'.

Expand the capability list slightly to surface the full feature set (recording, live streaming, live transcription, command channel, chat) so coverage reads as comprehensive rather than partial.

DimensionReasoningScore

Specificity

The description lists several concrete capabilities ('C++ headless bots, raw audio/video capture/injection, Qt/GTK integration, Docker support') naming the platform and four specific action areas, but does not enumerate the full feature set (recording, live streaming, transcription, command channel), leaving minor coverage gaps.

4 / 5

Completeness

The 'what' is clearly stated (C++ SDK capabilities on Linux), but there is no 'Use when...' clause or equivalent trigger guidance telling Claude when to invoke the skill, which caps completeness at 3 per the rubric.

3 / 5

Trigger Term Quality

It surfaces the natural terms 'Zoom Video SDK', 'Linux', 'headless bots', 'Qt/GTK', and 'Docker', but lacks common synonyms and extension cues a user would naturally say (e.g. 'raw media', 'PCM/YUV', 'virtual camera/mic'), so keyword coverage is relevant but incomplete.

3 / 5

Distinctiveness Conflict Risk

The niche is sharply defined ('Zoom Video SDK for Linux', C++ headless bots with raw media capture/injection), which is unlikely to overlap with or mis-trigger for unrelated skills; minimal conflict risk.

5 / 5

Total

15

/

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 66 missing

Warning

Total

15

/

16

Passed

Repository
openai/plugins
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.