setup-zoom-webhooks

Use when building Zoom webhooks.

Quality

57%

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/webhooks/SKILL.md

Quality

Content

75%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 body is a lean, well-structured overview with a clear sequenced workflow and good progressive disclosure into reference files. Its main weakness is actionability: the steps describe what to do but defer all executable specifics (verification code, subscription API calls) to the bundled references.

Suggestions

Add a minimal copy-pasteable code or command snippet for the highest-value step (e.g. the endpoint validation-token response or signature verification) so the skill is actionable without opening a reference.

Fix the broken "Common issues" reference: either create `troubleshooting/common-issues.md` or relink it to an existing file such as `references/verification.md`.

Surface the existing `environment-variables.md` and `verification.md` bundle files in the References list so they are discoverable.

Dimension	Reasoning	Score
Conciseness	The body is lean throughout: a one-line scope statement, six terse numbered steps, and a short reference list, with no explanation of what webhooks are or other concepts Claude already knows. Every token earns its place, matching the score-5 anchor (lean, assumes competence).	5 / 5
Actionability	Steps are concrete in intent ("Implement endpoint verification and signature verification", debug by checking listed items) but contain no executable code or commands, deferring specifics to the references. This fits score 3 (some concrete guidance but incomplete, missing key execution details) and is not minimal enough to drop to 2 given the concrete debug checklist in step 6.	3 / 5
Workflow Clarity	The six steps are clearly sequenced with implicit checkpoints ("before creating subscriptions", "before processing business logic") and idempotency/retry guidance. It matches score 4 (clear sequence, most checkpoints present, minor validation gaps); it lacks an explicit validate->fix->retry loop, which keeps it below 5.	4 / 5
Progressive Disclosure	The SKILL.md is a clean overview pointing to one-level-deep, clearly labeled references (full-guide, signature-verification, subscriptions, events). This fits score 4 (good structure, references mostly clear, minor gaps); it does not reach 5 because the "Common issues" link points to a non-existent `troubleshooting/common-issues.md` and two bundle files (environment-variables.md, verification.md) are unreferenced.	4 / 5
	Total	16 / 20 Passed

Description

40%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 concise and includes a usable "Use when" trigger with a distinct domain keyword, but it omits any concrete statement of what the skill does. Expanding to name specific actions would lift completeness and specificity.

Suggestions

Add a brief "what" clause naming concrete actions, e.g. "Register Zoom webhook subscriptions, verify endpoint and signature authenticity, and handle event delivery."

Include natural trigger variations like "Zoom webhook subscriptions" or "Zoom event endpoints" to broaden keyword coverage.

Keep the third-person imperative voice but avoid the generic verb "building" in favor of specific verbs (register, verify, process).

Dimension	Reasoning	Score
Specificity	"building Zoom webhooks" names the domain but the action ("building") is generic and minimal, with no concrete capabilities enumerated. It fits the score-2 anchor (names domain, actions minimal/generic) and falls short of score 3's requirement of 1-2 concrete actions.	2 / 5
Completeness	Only a "when" clause is present ("Use when building Zoom webhooks") with no clear statement of what the skill does; "building" is too vague as a "what". This matches the score-2 anchor (only "when" present, "what" vague), and although a "Use when" trigger exists, the missing "what" prevents reaching 3.	2 / 5
Trigger Term Quality	"Zoom webhooks" is a relevant, natural keyword a user would say, but there are no synonyms or variations (e.g. "webhook subscriptions", "event endpoints"). It matches score 3 (some relevant keywords, missing common variations) and is not bare enough for score 2.	3 / 5
Distinctiveness Conflict Risk	"Zoom webhooks" carves a clear niche with minimal conflict risk, though the sibling `setup-zoom-websockets` skill (noted in the body) creates minor overlap risk. It fits score 4 (mostly distinct, minor overlap with closely related skills) and is not comprehensive enough for 5 given the terse, unspecific trigger.	4 / 5
	Total	11 / 20 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: 1 missing	Warning

	Total	15 / 16 Passed

Repository: openai/plugins
Path: plugins/zoom/skills/webhooks/SKILL.md
Commit: 1e28582

Reviewed: 7 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.