zoom-cobrowse-sdk

Use when using Cobrowse.

Quality

43%

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/cobrowse-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 a lean, well-sequenced workflow overview that respects token budget, but it stays at a planning-checklist level with no executable code and no validation feedback loops. Progressive disclosure is undermined by four broken reference links to non-existent files.

Suggestions

Add concrete, executable snippets for the core lifecycle (initialize, start/join, subscribe, end) so the minimal workflow is copy-paste ready rather than purely descriptive.

Create the missing referenced files (concepts/session-lifecycle.md, examples/privacy-masking.md, examples/remote-assist.md, troubleshooting/common-issues.md) or remove the dead links from the References section.

Insert an explicit validation/verification step (e.g. confirm the session is stable via SDK events before advancing to advanced capabilities) to add a feedback loop to the workflow.

Dimension	Reasoning	Score
Conciseness	The body is ~25 lean, well-organized lines with no padding and no explanation of concepts Claude already knows; every step and reference earns its place. It is not a 2 because there is no unnecessary explanation to tighten.	3 / 3
Actionability	Steps name concrete domains (CORS/CSP, allowed origins, lifecycle events, third-party cookies) but provide no executable code, commands, or API specifics — instruction-only yet high-level. It is not a 1 because the topics are concrete, and not a 3 because nothing is copy-paste ready.	2 / 3
Workflow Clarity	A clear six-step sequence exists with a soft gate ("only after the base session is stable"), but there are no explicit validation checkpoints or validate-fix-retry feedback loops. It is not a 3 because checkpoints are implicit, and not a 1 because the ordering is explicit and sensible.	2 / 3
Progressive Disclosure	The overview is concise with well-signaled, labeled one-level references, but 4 of the 6 referenced paths (concepts/, examples/, troubleshooting/) do not exist as files, breaking navigation. It is not a 3 because dead links prevent easy navigation, and not a 1 because the structure itself is well organized rather than monolithic.	2 / 3
	Total	9 / 12 Passed

Description

22%

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 minimal and tautological ("Use when using Cobrowse."), providing a trigger keyword but no statement of capabilities or concrete actions. It is distinctive only by virtue of the product name and fails to answer what the skill does.

Suggestions

State concrete capabilities, e.g. "Initialize browser co-browse sessions, manage PIN/link handoff, apply masking and privacy controls, and handle SDK lifecycle events."

Add explicit natural triggers users would say, e.g. "Use when integrating Zoom Cobrowse for live browser co-browsing, screen masking, or remote assist."

Expand the "Use when" clause to distinguish Cobrowse from sibling Zoom products (Contact Center, Virtual Agent, Video SDK) so it does not fire for the wrong skill.

Dimension	Reasoning	Score
Specificity	The description "Use when using Cobrowse." names no concrete actions or capabilities, only echoing the product name, matching the vague/abstract anchor ("Helps with documents"). It is not a 2 because no domain actions are named at all.	1 / 3
Completeness	Although a "Use when..." trigger is present, the description never says what the skill does — "using Cobrowse" is not a capability. The "what" is missing, so it falls to the missing-what-or-when anchor rather than a 2.	1 / 3
Trigger Term Quality	"Cobrowse" is a natural product term a user would say, but the description offers only that single keyword with no common variations or context. It is not a 3 because coverage is far too thin, and not a 1 because the one term is genuinely natural rather than jargon.	2 / 3
Distinctiveness Conflict Risk	"Cobrowse" names a fairly distinct niche, but the bare phrasing could overlap with other Zoom skills and gives no discriminating detail. It is not a 3 because the trigger is too sparse to rule out conflicts.	2 / 3
	Total	6 / 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: 4 missing	Warning

	Total	15 / 16 Passed

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

Reviewed: about 1 hour 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.