CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

apply

Apply LaunchDarkly SDK onboarding: install dependency (or dual-SDK pair), configure env and secrets with consent, add init at entrypoint(s), verify compile. Nested under sdk-install; next is run.

Quality

81%

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

SKILL.md
Quality
Evals
Security

Quality

Content

81%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 well-structured procedural skill with excellent workflow sequencing, explicit consent/validation checkpoints, and concrete executable guidance throughout. Its only notable weakness is moderate repetition of guardrail instructions (dual-SDK rules, STOP reminders) and inline detail that could be pushed to reference files.

DimensionReasoningScore

Conciseness

The body is densely operational — exact MCP tool calls, dashboard URL templates, per-stack env-var tables — with almost no explanation of concepts Claude already knows. It falls between anchors 3 and 4 (noticeably above the midpoint) because the dual-SDK rules are repeated three times and "STOP. Do not write the question as text" appears twice within each decision point, which is more than minor trimming opportunity but less than pervasive padding.

4 / 5

Actionability

Mostly executable guidance: copy-paste-ready structured-question text with options, exact MCP calls ("get-sdk-key({ projectKey: ... })"), concrete URL templates, and exact bundler-prefixed env var names per stack. Not anchor 5 because the actual install commands and init code are deliberately deferred to referenced recipe/snippet files rather than included, leaving minor gaps in the file itself.

4 / 5

Workflow Clarity

Steps 1-4 are clearly sequenced with explicit validation checkpoints: lockfile/manifest verification after install, mandatory user-consent gates (D7/D8) with STOP conditions, build + lint verification, "Do not proceed to the next step if the code doesn't compile", and fix-and-retry error recovery for peer conflicts. This matches the anchor-5 pattern of explicit validation with feedback loops.

5 / 5

Progressive Disclosure

Good structure with well-signaled, clearly purposed references one level deep (SDK recipes, snippets/, observability-plugin.md, sibling plan/run/detect skills) and appropriate refusal to inline per-SDK snippets. Not anchor 5 because some inlined detail (e.g. the three-row bundler env-var table) arguably belongs in a reference, and no bundle files were provided alongside the skill to verify the referenced paths resolve.

4 / 5

Total

17

/

20

Passed

Description

75%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 highly specific, distinctive description that clearly communicates what the skill does across the whole apply phase. Its main weakness is the absence of an explicit "Use when..." trigger clause, which caps completeness, and slightly thin coverage of natural trigger synonyms.

Suggestions

Add an explicit trigger clause, e.g. "Use when executing an approved LaunchDarkly integration plan: installing the SDK, wiring SDK keys/client-side IDs, or adding LaunchDarkly initialization code."

Include natural trigger synonyms such as "feature flags setup", "initialize LaunchDarkly", or "add LaunchDarkly to my app" so the description matches how users actually phrase the request.

DimensionReasoningScore

Specificity

The description lists multiple concrete, domain-specific actions — "install dependency (or dual-SDK pair), configure env and secrets with consent, add init at entrypoint(s), verify compile" — covering the full workflow comprehensively. It exceeds anchor 4 because the action list spans the entire apply phase rather than having coverage gaps.

5 / 5

Completeness

The "what" is clearly and concretely answered, but there is no "Use when..." clause or equivalent explicit trigger guidance; "Nested under sdk-install; next is run" conveys workflow position, not when to invoke the skill. Per the judging guidelines a missing trigger clause caps completeness at 3, and it is not 4 because "when" is only weakly implied by the word "onboarding".

3 / 5

Trigger Term Quality

Natural keywords like "LaunchDarkly SDK", "install dependency", and "onboarding" are present and would match user phrasing, but common variations such as "feature flags", "set up LaunchDarkly", or "initialize the SDK" are missing. Good coverage with a few natural terms absent, matching anchor 4 rather than the comprehensive synonym coverage of anchor 5.

4 / 5

Distinctiveness Conflict Risk

"LaunchDarkly SDK onboarding" plus dual-SDK/SDK-key vocabulary establishes a clear niche with distinct triggers and minimal conflict risk against unrelated skills. Sibling-skill overlap is by design (explicit "Nested under sdk-install; next is run" positioning disambiguates it), so the anchor-5 fit is better than anchor 4.

5 / 5

Total

17

/

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: 16 suspicious

Warning

Total

15

/

16

Passed

Repository

launchdarkly/ai-tooling

Path

skills/onboarding/sdk-install/apply/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.