CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

rivet-sdk

Use when using Rivet SDK.

48

Quality

61%

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%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.

A token-efficient, well-structured overview whose main deficits are missing executable detail and broken navigation. The workflow is a reasonable high-level heuristic but reads like a summary of the full guide rather than standalone guidance, and most of its reference links point to files that do not exist in the bundle.

Suggestions

Add one small executable snippet (e.g. client instantiation and a webEventConsumer.event registration) so the workflow steps have concrete anchors.

Fix or prune the reference list: only references/full-guide.md exists — either ship concepts/, examples/, and troubleshooting/ files or point all links at the files that actually exist.

Make validation checkpoints explicit (e.g. 'verify webhook signature verification passes before composing multi-module flows') and fold the debug checklist into a validate-and-retry loop.

DimensionReasoningScore

Conciseness

The body is 26 lean lines with no padding and no explanation of concepts Claude already knows; the intro sentence, five workflow steps, and reference list each earn their place. It assumes Claude's competence throughout.

5 / 5

Actionability

Steps name concrete domain artifacts ('OAuth, API clients, webhook handlers', 'webhook signature handling', 'Lambda-style receivers') but provide no code, commands, API names, or environment variable specifics to actually execute anything. This sits between anchor 2's high-level-only hints and anchor 4's mostly-executable guidance.

3 / 5

Workflow Clarity

A clear five-step numbered sequence exists with an incremental ordering (smallest authenticated call before multi-module flows) and a debug checklist, but validation checkpoints are only implicit — no step says how to verify a webhook receiver or token refresh works. Not 4 because explicit checkpoints ('validate', 'only proceed when') are absent; not 2 because the sequence is coherent and reasonably defined.

3 / 5

Progressive Disclosure

The overview-plus-references structure is well signaled, but scored against the actual bundle: of the six referenced paths, only references/full-guide.md exists; rivet-sdk.md, concepts/architecture-and-lifecycle.md, examples/getting-started-pattern.md, examples/multi-client-pattern.md, and troubleshooting/common-issues.md are all missing, so navigation to the details is broken for five of six links.

3 / 5

Total

14

/

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 a bare trigger clause with no capability statement and almost no keyword surface. A user who already knew the term 'Rivet SDK' would find it, but nothing communicates what the skill does, that it targets Zoom server-side integrations, or how it differs from adjacent skills.

Suggestions

Add a capability statement naming the concrete actions, e.g. 'Scaffold Zoom server-side integrations with Rivet: OAuth and token refresh, webhook receivers, typed REST API wrappers, and multi-module server composition. Use when...'

State the Zoom context and natural trigger phrases users would say: 'Zoom integration', 'Zoom webhooks', 'server-side Zoom app', 'Node.js Zoom backend'.

Include the full 'Use when...' trigger listing the situations that call for Rivet vs direct OAuth + REST, so the 'what' and 'when' are both explicit.

DimensionReasoningScore

Specificity

The entire description is 'Use when using Rivet SDK.' — it names a domain but contains zero action verbs or capability statements. This falls between anchor 1 (no concrete actions) and anchor 2 (names the domain, minimal actions), and is above 1 only because the domain is named specifically.

2 / 5

Completeness

Only the 'when' clause is present ('Use when using Rivet SDK') with no statement of what the skill does — exactly anchor 2's example ('Use when working with documents'). It cannot score 3 because the 'what' is entirely absent, not merely weakly implied, and cannot score 1 because an explicit trigger is present.

2 / 5

Trigger Term Quality

'Rivet SDK' is a relevant, specific trigger term, but the description omits every natural variation a user would say: no 'Zoom', 'server-side integration', 'webhooks', 'OAuth', or 'Node.js'. Matches anchor 3 (some relevant keywords, missing common variations) rather than 4, where most natural terms would be present.

3 / 5

Distinctiveness Conflict Risk

'Rivet SDK' carves out a fairly distinct niche, but the missing 'Zoom' qualifier leaves moderate confusion risk with other Rivet-named tools (game engine, hosting platform). Not 5 because the trigger lacks the disambiguating product context that would eliminate that overlap.

4 / 5

Total

11

/

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: 5 missing

Warning

Total

15

/

16

Passed

Repository

openai/plugins

Path

plugins/zoom/skills/rivet-sdk/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.