zoom-oauth

Use when implementing OAuth.

Quality

40%

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/oauth/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 token-efficient and well structured as an overview, with a clear sequenced workflow and a real validation checkpoint. It is held back by a lack of executable detail and by four broken reference links that undermine progressive disclosure.

Suggestions

Add at least one executable example per critical step (the authorization-code+PKCE request, a refresh-token exchange call) or specific Zoom endpoints/scope strings.

Fix the four missing references — create concepts/oauth-flows.md, concepts/token-lifecycle.md, concepts/scopes-architecture.md, and troubleshooting/redirect-uri-issues.md, or remove the dead links.

Add an explicit error-recovery loop after the step-5 validation (validate → fix flagged issue → re-validate before touching application code) to earn the workflow-clarity 3.

Dimension	Reasoning	Score
Conciseness	The body is lean and never explains OAuth concepts Claude already knows; each workflow step is concrete guidance and every line earns its place, though "single-use" refresh tokens is restated in steps 4 and 6.	3 / 3
Actionability	Steps name concrete concerns (PKCE, redirect URI, refresh-token reuse) but provide no executable code, commands, endpoints, or literal scope strings — guidance is specific yet incomplete.	2 / 3
Workflow Clarity	The 6 steps are clearly sequenced and step 5 is an explicit pre-code validation checkpoint, but there is no validate→fix→retry feedback loop for the risky credential operations, so it falls short of a 3.	2 / 3
Progressive Disclosure	The overview-plus-References structure is one level deep and well signaled, but 4 of the 7 referenced paths (concepts/* and troubleshooting/redirect-uri-issues.md) do not exist in the bundle, breaking navigation.	2 / 3
	Total	9 / 12 Passed

Description

15%

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 a bare trigger clause that omits what the skill does and never ties itself to Zoom, making it both incomplete and conflict-prone. It names only a single relevant keyword. The description needs explicit capabilities and Zoom-specific triggers.

Suggestions

Add concrete actions, e.g. "Implement Zoom OAuth flows, handle token refresh, and diagnose scope or redirect-URI errors."

Include Zoom-specific trigger terms (Zoom auth, Zoom login, Zoom access tokens, Zoom scopes) so it does not fire for other providers' OAuth.

Combine what and when in one line, e.g. "Use when implementing or troubleshooting Zoom OAuth: authorization-code flows, refresh-token rotation, scope selection, and OAuth error diagnosis."

Dimension	Reasoning	Score
Specificity	"Use when implementing OAuth." names no concrete actions — it states only a trigger, with no specific operations like token refresh or scope selection, matching the vague/abstract anchor.	1 / 3
Completeness	It gives a "when" trigger but entirely omits what the skill does; per the rubric, missing either what or when warrants a 1, and the what is absent here.	1 / 3
Trigger Term Quality	"OAuth" is a natural keyword a user would say, but the description offers no common variations (auth, login, token, authorization, Zoom), fitting "some relevant keywords but missing common variations."	2 / 3
Distinctiveness Conflict Risk	"Use when implementing OAuth." is generic across all OAuth providers and never mentions Zoom, so it would conflict with any OAuth-related skill and trigger for the wrong one.	1 / 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: 4 missing	Warning

	Total	15 / 16 Passed

Repository: openai/plugins
Path: plugins/zoom/skills/oauth/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.