CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

start

Use when starting Zoom work.

56

Quality

70%

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/start/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

100%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 exemplar router skill: lean, concrete, and well-structured. It turns a vague description into an unambiguous decision procedure — a routing table covering the common intents, explicitly gated deeper references, and operating rules that prevent the catalog-dump failure mode.

DimensionReasoningScore

Conciseness

The ~40-line body is a lean routing table, a short gated reference list, and four terse operating rules — no explanations of concepts Claude already knows and no padding. Phrases like "Prevents common early mistakes, especially Meeting SDK vs Video SDK and REST API vs SDK confusion" add real, non-obvious value per token.

5 / 5

Actionability

For an instruction-only router skill the guidance is fully concrete: the routing table maps each user intent ("Set up OAuth, tokens, scopes, or app credentials") to an exact destination skill, and the operating rules are executable directives ("Prefer one clear recommendation over a product catalog dump", "Ask a short clarifier only when the route is genuinely ambiguous"). The common routing cases are covered with no gaps.

5 / 5

Workflow Clarity

This is a simple, single-purpose skill whose one action — classify by job-to-be-done and route — is unambiguous: the table enumerates the routes, the references are explicitly gated ("Use these only after selecting the workflow"), and rule 2 covers the ambiguous-case fallback. Per the simple-skill note this scores 5; no destructive or batch operations apply, so no validation cap.

5 / 5

Progressive Disclosure

Under 50 lines with well-organized sections (What This Skill Does, Routing Table, Supporting Zoom References, Operating Rules) and all references one level deep, clearly labeled, and gated behind the routing decision. No bundle files (references/, scripts/, assets/) exist and nothing in the body belongs in a separate file, so the simple-skill exception applies cleanly.

5 / 5

Total

20

/

20

Passed

Description

28%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: it says when to use the skill but gives no indication of what the skill does (classify requests and route them to the right Zoom implementation skill). As the plugin's default entry skill its broad trigger is partly by design, but as a standalone description it is vague and leaves Claude to infer the skill's purpose entirely from the body.

Suggestions

State the core capability alongside the trigger, e.g. 'Classifies Zoom requests by job-to-be-done and routes them to the right implementation skill (OAuth setup, Meeting SDK, Video SDK, bots, webhooks, debugging).'

Add natural trigger terms users would actually say — "Zoom integration", "Zoom SDK", "Zoom app", "Zoom API", "Zoom bot" — instead of only "starting Zoom work".

Mention the common disambiguations the skill exists to handle (Meeting SDK vs Video SDK, REST API vs SDK) so the description signals when routing help is needed.

DimensionReasoningScore

Specificity

"Use when starting Zoom work." names the Zoom domain but states no concrete actions or capabilities whatsoever — only a trigger clause. It matches 'Names the domain but actions are minimal or generic' and falls below anchor 3, which requires 1-2 concrete actions to be stated.

2 / 5

Completeness

Only a 'when' is present ("Use when starting Zoom work") with the 'what' entirely absent, exactly matching anchor 2's 'only when is present without what'. It is not 3 because the skill's purpose (routing requests to implementation skills) is not even weakly implied in the description.

2 / 5

Trigger Term Quality

The only trigger language is "starting Zoom work" — a single generic keyword pattern. Natural phrases users would actually say ("Zoom integration", "Zoom SDK", "Zoom app", "build a Zoom bot", "Zoom OAuth") are missing, matching anchor 2 rather than anchor 3's 'some relevant keywords'.

2 / 5

Distinctiveness Conflict Risk

"Zoom" carves out a clear niche versus non-Zoom skills, but "starting Zoom work" would trigger for virtually every Zoom request — setup, building, debugging, planning — overlapping with all the sibling Zoom skills it routes to. This matches 'Somewhat specific but could still overlap with similar skills'; it is not 4 because the within-domain overlap risk is high rather than minor.

3 / 5

Total

9

/

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: 12 suspicious

Warning

Total

15

/

16

Passed

Repository

openai/plugins

Path

plugins/zoom/skills/start/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.