CtrlK
BlogDocsLog inGet started
Tessl Logo
PluginPublic

testland/launchdarkly-testing

Use whenever code that reads LaunchDarkly feature flags needs tests: the TestData source for hermetic tests with no network, file-based fixtures, per-test flag overrides and assignment checks. Which flag combinations to cover is in openfeature-sdk-testing's flag test-matrix reference.

Quality

92%

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

88%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 highly actionable, well-structured skill whose executable examples, explicit initialization checkpoint, and anti-patterns checklist make the workflow hard to get wrong. Its only deductions are minor: a few trimmable commentary phrases and a version pin that will age.

DimensionReasoningScore

Conciseness

The body is code-forward with almost no padding — no explanations of general testing or feature-flag concepts — so it is clearly above anchor 3. It falls short of anchor 5 due to minor commentary ('the canonical hermetic-test pattern', 'Useful for cross-language test fixtures') and a time-sensitive version pin ('Node.js server SDK v8+') outside any deprecated section, which the guidelines penalize.

4 / 5

Actionability

Install commands, complete initialization with TestData, runnable test cases for evaluation/targeting/rollout, a file-based fixture alternative, teardown, and a CI YAML snippet make the guidance fully copy-paste ready and cover the common cases. This matches the anchor-5 example of executable code plus concise API notes.

5 / 5

Workflow Clarity

The authoring flow is clearly sequenced (install → init with waitForInitialization → td.update → assert → close), and the anti-patterns table serves as an explicit error-recovery checklist ('Race; variation returns default → Always wait', 'Always update first'). Not a destructive or batch workflow, so no cap applies; anchor 5 fits better than 4 because checkpoints and recovery guidance are explicit rather than merely present.

5 / 5

Progressive Disclosure

Sections are well organized (Overview, When to use, Authoring subsections, Running, CI, Anti-patterns, Limitations, References) with clearly labeled external references and no nested-reference chains. It does not reach anchor 5 because all content is inlined with no one-level-deep bundle references, and at ~180 lines it exceeds the under-50-line simple-skill case that would allow a 5 on sections alone.

4 / 5

Total

18

/

20

Passed

Description

92%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.

A strong description that pairs an explicit 'Use whenever' trigger with a concrete, comprehensive list of capabilities, all scoped tightly to LaunchDarkly. The only weakness is slightly thin synonym coverage for natural trigger phrases.

DimensionReasoningScore

Specificity

The description lists multiple concrete capabilities — 'the TestData source for hermetic tests with no network, file-based fixtures, per-test flag overrides and assignment checks' — which is comprehensive for the LaunchDarkly testing domain with no vague filler. Anchor 5 fits better than 4 because coverage is complete rather than leaving minor gaps.

5 / 5

Completeness

It explicitly answers both what ('TestData source... file-based fixtures, per-test flag overrides and assignment checks') and when ('Use whenever code that reads LaunchDarkly feature flags needs tests') with a concrete trigger clause. This matches the anchor-5 example structure exactly, and is clearly above anchor 4 since the 'when' is fully explicit.

5 / 5

Trigger Term Quality

Natural terms like 'LaunchDarkly', 'feature flags', and 'needs tests' match what a user would actually say, giving good keyword coverage. It falls short of anchor 5 because common synonyms and variations (e.g., 'feature toggle', 'unit tests') are absent.

4 / 5

Distinctiveness Conflict Risk

The vendor-specific 'LaunchDarkly' niche gives it distinct triggers, and it even disambiguates against a sibling skill by routing flag-combination coverage to 'openfeature-sdk-testing's flag test-matrix reference'. Conflict risk with other flag-testing skills is minimal.

5 / 5

Total

19

/

20

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Reviewed

On this page