CtrlK
BlogDocsLog inGet started
Tessl Logo

rivet-sdk

Use when using Rivet SDK.

43

Quality

43%

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/rivet-sdk/SKILL.md
SKILL.md
Quality
Evals
Security

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 appropriately lean and well-structured as an overview pointing to references, with a sensibly sequenced workflow. Its main weaknesses are abstract, non-executable steps and a References section where most linked files do not exist in the bundle.

Suggestions

Fix or remove the dangling reference links — only references/full-guide.md exists; either create the missing files (rivet-sdk.md, concepts/..., examples/..., troubleshooting/...) or relink to the actual bundle files (rivet-reference-map.md, environment-variables.md, samples-validation.md, versioning-and-compatibility.md).

Add at least one minimal executable snippet (e.g., a Rivet client/webhook receiver initialization) so the smallest authenticated call step is actionable rather than directional.

Insert an explicit validation checkpoint in the workflow, e.g. 'Verify the authed API call and webhook signature succeed before composing multi-module flows.'

DimensionReasoningScore

Conciseness

The body is a lean overview that assumes Claude's competence — it never explains what Zoom, webhooks, or OAuth are, and every line earns its place, matching the score-3 lean/efficient anchor.

3 / 3

Actionability

Steps name concrete areas (OAuth, API clients, webhook handlers, Lambda-style receivers, webhook signature handling) but give no executable code or commands, and directives like "Confirm Rivet is the right abstraction" are directional rather than instructive — fitting the score-2 anchor of some concrete guidance but incomplete; not score 1 because real guidance is present, not score 3 because nothing is copy-paste ready.

2 / 3

Workflow Clarity

The five steps are clearly sequenced, but there are no explicit validation checkpoints (e.g., verify auth before composing flows) — only an implicit debug step at the end, matching the score-2 anchor of sequence present but checkpoints missing; not score 1 because ordering is explicit, not score 3 because no validate-then-proceed feedback loops are stated.

2 / 3

Progressive Disclosure

The form is good — a concise overview with a clearly signaled one-level-deep References list — but 5 of the 6 referenced paths (rivet-sdk.md, concepts/architecture-and-lifecycle.md, examples/getting-started-pattern.md, examples/multi-client-pattern.md, troubleshooting/common-issues.md) do not exist in the bundle, so navigation is broken despite clean organization; not score 3 because dead links break navigation, not score 1 because the overview/reference split is well-structured and one level deep.

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 too sparse: it provides a thin when-trigger but no statement of what the skill does or which concrete capabilities it covers. It is distinct enough to avoid broad conflicts yet fails to inform Claude what actions the skill performs.

Suggestions

Add a concrete capabilities clause before the trigger, e.g. 'Build server-side Zoom integrations with Rivet: OAuth, API clients, webhook handlers, and deployment. Use when ...'.

Expand trigger terms with natural variations such as 'Zoom integration', 'Zoom webhooks', 'Rivet SDK', and 'server-side Zoom app'.

Avoid the awkward 'Use when using' repetition; lead with third-person actions ('Builds ...', 'Handles ...').

DimensionReasoningScore

Specificity

The description is "Use when using Rivet SDK." — it names the domain (Rivet SDK) but describes zero concrete actions, matching the score-1 anchor of vague/abstract language with no listed capabilities.

1 / 3

Completeness

It states when to use the skill ("Use when using Rivet SDK") but entirely omits what the skill does, so it is missing the "what" half — matching the score-1 anchor of missing what OR when.

1 / 3

Trigger Term Quality

"Rivet SDK" is a relevant keyword a user would say, comparable to the score-2 example "Works with PDF files", but only one term is present with no common variations or surrounding context.

2 / 3

Distinctiveness Conflict Risk

"Rivet SDK" names a specific niche so it is unlikely to broadly conflict, but the trigger is minimal and only loosely distinct, fitting the score-2 anchor of somewhat specific but could overlap.

2 / 3

Total

6

/

12

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 5 missing

Warning

Total

15

/

16

Passed

Repository
openai/plugins
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.