CtrlK
BlogDocsLog inGet started
Tessl Logo

testland/launchdarkly-testing

Wraps LaunchDarkly server-side SDK testing patterns: TestData data source for hermetic tests (no network), file-based data source for fixture-driven tests, flag override patterns (TestData.update for per-test flag values), and assignment-integrity tests. Use when writing tests for code that uses LaunchDarkly flags.

77

Quality

97%

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

92%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A tight, highly actionable skill body with executable code, a clear sequenced workflow, and useful anti-pattern checkpoints. Its main weakness is progressive disclosure: all detail lives inline in SKILL.md with no bundle files for deferral.

Suggestions

Move the more optional material (e.g., the file-based data source alternative, CI integration, percentage-rollout details) into reference files under references/, leaving SKILL.md a leaner overview with one-level-deep links.

Add a short 'Advanced patterns' section that points to those reference files with clear signals, so the main body stays scannable while detail remains discoverable.

If keeping everything inline is intentional, trim or fold the CI-integration and file-based sections so the body better matches an overview-first structure.

DimensionReasoningScore

Conciseness

The body is code-forward and lean — sections like Authoring, Anti-patterns, and Limitations carry useful detail without explaining basic concepts Claude already knows; not score 2 because there is no padded exposition to tighten.

3 / 3

Actionability

Provides fully executable TypeScript (init, variation, targeting, rollout, file-based, teardown), install commands, CI YAML, and an anti-pattern table with concrete fixes — copy-paste ready, matching the score-3 anchor.

3 / 3

Workflow Clarity

The Authoring section sequences Install → Initialize → Variation → Targeting → Rollout → Teardown, and the anti-patterns table supplies precondition checks (await waitForInitialization, update first, close in afterAll); as a testing skill rather than a destructive/batch op, the simple-skills allowance applies, so 3 rather than capped at 2.

3 / 3

Progressive Disclosure

There are no bundle files and the ~180-line body holds all detailed code inline with nothing split out, fitting the score-2 anchor 'content that should be separate is inline'; not score 3 because nothing is appropriately deferred to reference files despite the length, though references that do exist are clearly signaled.

2 / 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.

A strong, specific description that names concrete testing patterns, includes a natural 'Use when' trigger, and is clearly scoped to LaunchDarkly's server-side SDK. It answers both what and when without padding.

DimensionReasoningScore

Specificity

Lists multiple specific concrete patterns — 'TestData data source for hermetic tests (no network)', 'file-based data source for fixture-driven tests', 'flag override patterns (TestData.update for per-test flag values)', 'assignment-integrity tests' — matching the score-3 anchor of several specific actions, not vague domain naming.

3 / 3

Completeness

Explicitly answers both what (the four testing patterns) and when ('Use when writing tests for code that uses LaunchDarkly flags'), matching the score-3 anchor with an explicit trigger; not score 2 because the 'when' is present and explicit rather than implied.

3 / 3

Trigger Term Quality

The trigger clause 'Use when writing tests for code that uses LaunchDarkly flags' uses natural terms a user would say (LaunchDarkly, tests, flags); not score 2 because coverage of common phrasings is good rather than partial.

3 / 3

Distinctiveness Conflict Risk

Vendor-named and scoped to server-side SDK testing, giving it a clear niche unlikely to trigger for unrelated skills; not score 2 because the LaunchDarkly qualifier disambiguates it from generic flag-testing skills.

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