CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

debug-zoom-integration

Use when isolating failures.

42

Quality

53%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/zoom/skills/debug-zoom-integration/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

68%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 an admirably lean triage skeleton with clean structure, but it stays at the outline level: no concrete checks per triage layer and no in-process validation checkpoints. The cross-skill reference routing is a good idea though the linked sibling skills are not present in this bundle.

Suggestions

Add one concrete probe or check per triage layer (e.g. "Auth: verify token expiry and error code 124 in the response") so the triage order is executable rather than a list of topic labels.

Insert an explicit checkpoint between triage steps, e.g. "Confirm the failing layer with one piece of evidence before moving to the next layer", to convert the sequence into a validated workflow.

Verify the Reference Routing links resolve in the deployed bundle (../oauth/SKILL.md etc. are absent here), or inline a one-line pointer of what each referenced skill covers.

DimensionReasoningScore

Conciseness

The body is lean and efficient — a triage list, an evidence checklist, reference links, and output spec with zero concept padding. Every token earns its place and Claude's competence is fully assumed.

5 / 5

Actionability

The triage order ("Auth and app configuration", "Request construction or event verification"), evidence list, and output spec give real structure, but each layer lacks the specific checks, commands, or probes to run — matching anchor 3 (some concrete guidance but incomplete, missing key details).

3 / 5

Workflow Clarity

A clear ordered sequence exists (Triage Order 1-5), but there are no validation checkpoints between layers (e.g. how to confirm a hypothesis before moving on); "Verification steps" appears only as an output deliverable, not as an in-process checkpoint — anchor 3.

3 / 5

Progressive Disclosure

Sections are well organized and the Reference Routing links are clearly signaled and one level deep, but they point to sibling skills (../oauth/SKILL.md etc.) that do not exist alongside this bundle, and no per-area detail exists in-bundle — a minor organization gap consistent with anchor 4 rather than 5.

4 / 5

Total

15

/

20

Passed

Description

16%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 a bare trigger clause with no capability statement, no domain naming, and no natural trigger terms. It would both under-trigger (users saying "debug my Zoom app") and over-trigger (any failure isolation task).

Suggestions

State what the skill does in third person, e.g. "Isolates failures in Zoom integrations by triaging auth, request, SDK, and media layers, then proposes ranked fixes."

Include the domain and natural trigger terms: name Zoom, plus user phrasings like "debug", "error", "not working", "failing" (e.g. "Use when a Zoom integration the user already built is failing or erroring").

Make the 'when' clause concrete so it does not collide with generic debugging skills — tie it to Zoom OAuth, REST, webhooks, or SDK failures.

DimensionReasoningScore

Specificity

The description "Use when isolating failures" names no concrete actions and not even the domain (Zoom integration debugging); it is pure abstract language with no capability statement at all.

1 / 5

Completeness

Only a 'when' clause is present with no 'what' — the exact anchor-2 case ("Use when working with documents"). It does not reach 3 because there is no clear 'what' at all, and not 1 because a trigger clause does exist.

2 / 5

Trigger Term Quality

"isolating failures" is a single generic, clinical phrase; the natural terms users would actually say — debug, error, not working, Zoom — are all missing. It sits above anchor 1 only because one relevant keyword is present.

2 / 5

Distinctiveness Conflict Risk

With no mention of Zoom or integration, "Use when isolating failures" would claim virtually any debugging task, conflicting with any other debugging or error-triage skill.

1 / 5

Total

6

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

relative_links

Relative link issues: 6 suspicious

Warning

Total

15

/

16

Passed

Repository

openai/plugins

Path

plugins/zoom/skills/debug-zoom-integration/SKILL.md

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.