CtrlK
BlogDocsLog inGet started
Tessl Logo

testland/growthbook-testing

Wraps GrowthBook Node SDK testing patterns: GrowthBookClient initialization with direct payload (initSync; no network), isOn / getFeatureValue / evalFeature, scoped instances (createScopedInstance) for per-request user context, inline experiment (runInlineExperiment) tests, and tracking-callback assertion patterns. Use when writing tests for code using GrowthBook for flags + experiments.

76

Quality

95%

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

Overview
Quality
Evals
Security
Files

Quality

Content

87%

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 tight, actionable catalog of executable GrowthBook testing patterns with strong code examples and a useful anti-patterns checklist. Its main gap is the absence of an explicit validate→fix→retry loop in the testing workflow.

Suggestions

Add an explicit verification/feedback loop after `npm test` (e.g., on failure: read the assertion error, adjust the payload or context, re-run) to lift workflow_clarity toward 3.

Collapse the repeated 'Per docs.growthbook.io/lib/node' citations into a single source note in the References section to tighten conciseness further.

Consider a short numbered 'Testing workflow' sequence (init payload → write per-test scoped instance → assert → run → check tracking fired) to make the implied process explicit.

DimensionReasoningScore

Conciseness

The body is lean: each section is a one-line intro plus executable code, with no padding about what GrowthBook or flags are. Minor repeated "Per docs.growthbook.io" citations serve a sourcing purpose rather than inflating tokens.

3 / 3

Actionability

Provides copy-paste-ready, executable TypeScript for install, initSync payload, isOn/getFeatureValue, scoped instances, inline experiments, tracking callbacks, feature-usage, and a typed feature contract—fully concrete guidance.

3 / 3

Workflow Clarity

Sections are logically ordered (install → init → patterns → run → CI → anti-patterns), but there is no explicit validation checkpoint or fix-and-retry feedback loop; only `npm test` is implied as verification. It exceeds the simple-skill (<50 line) exemption, so it cannot reach the 3 anchor.

2 / 3

Progressive Disclosure

A single well-organized file with clear sections and a clearly signaled one-level-deep References section pointing to external docs and sibling skills; no bundle files exist to verify, and the inline content fits the scope without needing a split.

3 / 3

Total

11

/

12

Passed

Description

100%

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 third-person, concise, and richly specific, naming concrete SDK methods and an explicit Use-when trigger. It cleanly answers both what the skill does and when to invoke it with low conflict risk.

DimensionReasoningScore

Specificity

Lists multiple concrete actions and APIs—"GrowthBookClient initialization with direct payload (initSync; no network), isOn / getFeatureValue / evalFeature, scoped instances (createScopedInstance)... inline experiment (runInlineExperiment) tests, and tracking-callback assertion patterns"—far exceeding the vague-language anchor.

3 / 3

Completeness

Explicitly states both what it does (wraps the listed testing patterns) and when to use it ("Use when writing tests for code using GrowthBook for flags + experiments"), matching the full what-and-when anchor.

3 / 3

Trigger Term Quality

Natural user-facing terms appear—"writing tests for code using GrowthBook for flags + experiments"—covering the keywords a user would actually say, alongside the more technical API names.

3 / 3

Distinctiveness Conflict Risk

Scoped narrowly to the GrowthBook Node SDK testing niche with distinct triggers, making conflict with other flag/experiment skills unlikely.

3 / 3

Total

12

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Reviewed

Table of Contents