probe-sdk

Use when using Probe SDK.

Quality

36%

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/probe-sdk/SKILL.md

Quality

Content

65%

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

The body is concise and well-structured as a lean overview pointing to detail files, but it stays at a high level: it lacks executable guidance and validation checkpoints in its workflow, and most of its reference links point to files absent from the bundle, undermining the progressive-disclosure navigation it relies on.

Suggestions

Add a short inline Quick Start with one concrete executable snippet (e.g. initializing Prober/Reporter and calling diagnoseAudio/diagnoseVideo) so the body is actionable without forcing a reference hop.

Insert an explicit validation/feedback checkpoint in the workflow, e.g. 'Re-run failed diagnostics after permission or device changes; only gate join when checks pass or are intentionally bypassed.'

Fix or remove the broken reference links — only references/full-guide.md exists; either add the referenced files (probe-sdk.md, concepts/, examples/, troubleshooting/) to the bundle or point the References list at the files that actually exist under references/ (e.g. probe-reference-map.md, samples-validation.md, versioning-and-compatibility.md).

Dimension	Reasoning	Score
Conciseness	The body is lean — a one-line intro, five tightly written workflow steps, and a references list — with no padding or explanation of concepts Claude already knows, matching the 'lean and efficient; every token earns its place' anchor rather than the score-2 anchor which still carries unnecessary explanation.	3 / 3
Actionability	Steps name concrete gate types (browser support, camera, microphone, speaker, network, CPU) and concrete debug areas, but the body offers no executable code or commands and defers all implementation to references; this fits the 'some concrete guidance but incomplete; missing key details' anchor rather than the score-3 'fully executable, copy-paste ready' anchor.	2 / 3
Workflow Clarity	The five steps are clearly sequenced, but there are no explicit validation checkpoints or feedback loops (e.g. re-run diagnostics on failure, verify readiness before gating join); per the rubric, missing validation/checkpoints caps this at the 'steps listed but validation gaps' anchor rather than the score-3 'explicit validation steps; feedback loops' anchor.	2 / 3
Progressive Disclosure	The overview-plus-references structure is clean and one level deep, but checked against the actual bundle only 1 of 6 referenced links resolves (references/full-guide.md); probe-sdk.md, concepts/, examples/, and troubleshooting/ paths do not exist, so navigation is broken and this fits the 'some structure but could be better organized' anchor rather than the score-3 'easy navigation' anchor.	2 / 3
	Total	9 / 12 Passed

Description

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 too terse to be useful: it provides only a circular trigger and omits both the skill's concrete capabilities and natural user-language triggers. It is moderately distinctive only because it names a specific SDK, but lacks the distinguishing criteria needed to avoid overlap with sibling Zoom SDK skills.

Suggestions

State what the skill does in third person, e.g. 'Runs client-side preflight diagnostics (camera, microphone, speaker, network, browser) and produces readiness checks before a meeting or video session join.'

Replace the circular 'Use when using Probe SDK' trigger with natural user phrasing such as 'Use when the user needs to verify device/network readiness before joining a Zoom meeting or video session, or when they mention preflight, readiness, or device capability checks.'

Add a one-line distinguishing cue so it is not confused with sibling skills, e.g. 'For embedded meeting/session join flows, use the Meeting SDK or Video SDK instead.'

Dimension	Reasoning	Score
Specificity	The description 'Use when using Probe SDK.' names no concrete actions at all — it states a trigger but never says what the skill does (preflight diagnostics, readiness checks), matching the 'vague or no actions; abstract language' anchor and falling short of the score-2 anchor which at least names a domain and some actions.	1 / 3
Completeness	It has a weak, circular 'when' ('Use when using Probe SDK') but completely omits the 'what'; the score-1 anchor explicitly covers 'missing what OR when', and although a 'Use when' clause is present, it does not answer what the skill does, so it cannot reach the score-2 'has what' anchor.	1 / 3
Trigger Term Quality	The only trigger term is 'Probe SDK', a technical product name a user would not naturally say; users would phrase the need as 'check my camera/mic before joining' or 'readiness check', so this matches the 'no natural keywords; technical jargon' anchor rather than the score-2 'some relevant keywords' anchor.	1 / 3
Distinctiveness Conflict Risk	Naming 'Probe SDK' specifically carves a niche unlikely to conflict with non-Zoom skills, matching the 'somewhat specific but could still overlap' anchor; however sibling Zoom SDK skills exist and the description gives no criteria to distinguish Probe from Meeting/Video SDK, so it does not reach the score-3 'clear niche with distinct triggers' anchor.	2 / 3
	Total	5 / 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: 5 missing	Warning

	Total	15 / 16 Passed

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

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.