CtrlK
BlogDocsLog inGet started
Tessl Logo

zoom-meeting-sdk-windows

Zoom Meeting SDK for Windows - Native C++ SDK for embedding Zoom meetings into Windows desktop applications. Supports custom UI architecture with raw video/audio data, headless bots, and deep integration with meeting features. Includes SDK architecture patterns and Windows message loop handling.

52

Quality

60%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

High

Do not use without reviewing

Fix and improve this skill with Tessl

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

Quality

Content

62%

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

The body is highly actionable with clear, validated workflows and copy-paste-ready code, but it is significantly over-budget due to heavy navigation redundancy and a merged duplicate second half, and it advertises a multi-file structure whose referenced files largely do not exist. Collapsing the duplicate indexes and creating (or removing) the missing referenced files would substantially improve it.

Suggestions

Remove the duplicate navigation/index sections (the merged second-half SKILL.md, "Complete Documentation Library", "By Document Type", "How to Find What You Need") and keep a single consolidated reference list to cut the body roughly in half.

Create the referenced bundle files (concepts/sdk-architecture-pattern.md, examples/authentication-pattern.md, troubleshooting/windows-message-loop.md, etc.) or remove the dead links, since only 3 of ~25 referenced files currently exist.

Move the large code-example blocks that are duplicated across navigation prose into their referenced example files and link to them once, keeping only minimal inline snippets in SKILL.md.

DimensionReasoningScore

Conciseness

The ~1180-line body is padded: the same reference link list is repeated across at least four navigation indexes ("Detailed References", "Complete Documentation Library", "By Document Type", "How to Find What You Need"), and lines 826-1182 are a merged duplicate of another SKILL.md that re-indexes everything already covered — matching anchor 1 "Verbose; padded with unnecessary context" rather than the efficient anchor 2/3.

1 / 3

Actionability

It provides copy-paste-ready executable C++ (full listener classes with all virtual methods), concrete cmd/powershell (vcpkg, xcopy), ffmpeg/ffplay commands, a config.json, and .vcxproj/.filters XML, matching anchor 3 "Fully executable code/commands; specific examples; copy-paste ready".

3 / 3

Workflow Clarity

The Quick Start is a numbered 6-step sequence, the Core Workflow is shown as an ASCII state diagram with explicit callbacks, and each code example validates return codes (SDKError checks, CanStartRawRecording gating) with error-recovery branches and "CRITICAL" checkpoints, matching anchor 3.

3 / 3

Progressive Disclosure

Navigation is well-signaled and one-level-deep, but the body is monolithic with inline link indexes that should be split out, and the actual bundle contains only 3 of the ~25 referenced files (concepts/*, examples/*, troubleshooting/*, ../references/*, RUNBOOK.md are mostly absent), fitting anchor 2 "could be better organized; content that should be separate is inline" rather than a clean, real file split.

2 / 3

Total

9

/

12

Passed

Description

57%

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 distinct, clearly identifying a well-bounded niche, but it lacks an explicit "Use when..." trigger clause and its action/trigger phrasing is only moderately varied. Adding explicit when-to-use guidance and a few more natural trigger variations would lift the weaker dimensions.

Suggestions

Append an explicit trigger clause, e.g. "Use when embedding Zoom meetings into Windows C++ desktop apps, building headless Zoom bots, or capturing raw Zoom video/audio streams."

Replace vague phrasing like "deep integration with meeting features" with concrete actions (e.g. "mute/unmute, send chat, start local recording, manage breakout rooms").

Broaden natural trigger terms to include variations users actually say, such as "Zoom bot", "Zoom integration", "virtual camera", and "Zoom Windows SDK".

DimensionReasoningScore

Specificity

Names the domain ("Native C++ SDK", "Windows desktop applications") and several concrete capabilities ("custom UI architecture with raw video/audio data, headless bots", "Windows message loop handling"), but the action verbs are weak ("Supports"/"Includes") and "deep integration with meeting features" is vague, matching anchor 2 rather than the crisp multi-action list of anchor 3.

2 / 3

Completeness

It clearly answers what the skill does (embedding meetings, custom UI, raw media, headless bots) but provides no "Use when..." clause or equivalent explicit trigger guidance, so per the judging guideline completeness is capped at 2 ("Has what, but when is missing or only implied").

2 / 3

Trigger Term Quality

Contains natural terms a user would say ("Zoom meetings", "Windows desktop applications", "headless bots", "raw video/audio"), but coverage of common variations is limited (no "meeting bot", "Zoom integration", "virtual camera"), fitting anchor 2 "some relevant keywords but missing common variations" rather than the broad variation coverage of anchor 3.

2 / 3

Distinctiveness Conflict Risk

"Zoom Meeting SDK for Windows - Native C++ SDK" is a highly specific niche with distinct triggers (Zoom + Windows + C++ + bots) that is unlikely to conflict with other skills, matching anchor 3.

3 / 3

Total

9

/

12

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (1187 lines); consider splitting into references/ and linking

Warning

relative_links

Relative link issues: 121 missing, 13 suspicious

Warning

Total

14

/

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.