Name: apply
Rating: 64.8 (1 reviews)
Author: launchdarkly

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

Securityby

Passed

No findings from the security scan

Quality

Content

92%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.

The content is a strong operational document: every step carries concrete commands, scripts, URL patterns, or decision-point gates, and validation checkpoints with error-recovery paths are built in. SDK-specific material is appropriately externalized to recipes and snippets rather than inlined. The only notable weakness is repetition of the dual-SDK caveats across multiple sections.

Dimension	Reasoning	Score
Conciseness	The body is dense and operational with no explanation of concepts Claude already knows, but the dual-SDK emphasis ("two packages... two install commands... two inits") is repeated nearly verbatim in the intro and in Steps 1, 2, and 3, which could be trimmed to a single stated rule.	4 / 5
Actionability	Fully executable guidance throughout: copy-ready structured-question scripts with exact question text and options, exact dashboard URL patterns with {projectKey}/{envKey} placeholders, a per-bundler env-var table, the get-environments MCP call signature, and concrete .gitignore/.env.example steps. The absence of init code is explicitly justified ("using the wrong snippet... will mislead you") with a clear deferral path to recipes and snippet files.	5 / 5
Workflow Clarity	Steps 1-4 are clearly sequenced (install → secrets → init → verify) with explicit validation checkpoints (lockfile/manifest verification, waiting for user confirmation, "Do not proceed to the next step if the code doesn't compile") and error-recovery loops (D8 peer-conflict options with a decline path using placeholders).	5 / 5
Progressive Disclosure	The body keeps only flow-level process content and defers SDK-specific bulk one level deep to references/sdk/recipes.md and the snippets/ directory, with a numbered source-of-truth ordering and clear sibling-skill navigation links; no SDK detail that belongs in a separate file is inlined.	5 / 5
	Total	19 / 20 Passed

Description

63%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 communicates concrete, well-sequenced capabilities in third person, but entirely lacks an explicit use-when clause and omits the most natural trigger synonyms (notably "feature flags"). It is specific and largely distinct, yet functions more as flow navigation metadata than as a trigger surface.

Suggestions

Add an explicit trigger clause, e.g. "Use when executing an approved LaunchDarkly SDK integration plan or setting up LaunchDarkly feature flags in a project."

Include natural user phrasings and synonyms such as "feature flags", "set up LaunchDarkly", and "integrate the SDK" so the skill surfaces when users describe the goal in their own words.

Trim the navigation metadata ("Nested under sdk-install; next is run") or fold it into the when-clause to free description budget for trigger terms.

Dimension	Reasoning	Score
Specificity	Lists four concrete actions — "install dependency (or dual-SDK pair)", "configure env and secrets with consent", "add init at entrypoint(s)", "verify compile" — comprehensively covering the apply step, matching the multiple-specific-actions anchor.	5 / 5
Completeness	The "what" is clear and concrete, but there is no "Use when..." clause or equivalent explicit trigger guidance — "Nested under sdk-install; next is run" is navigation metadata, and the rubric explicitly caps completeness at 3 for a missing when-clause.	3 / 5
Trigger Term Quality	Contains relevant keywords ("LaunchDarkly SDK onboarding", "install", "init") but misses the most natural user phrasings such as "feature flags", "set up LaunchDarkly", or "integrate LaunchDarkly", matching the some-relevant-keywords-but-missing-synonyms anchor.	3 / 5
Distinctiveness Conflict Risk	Clear niche (LaunchDarkly apply step of an onboarding flow) with mostly distinct triggers, but "install dependency" and "install... SDK" overlap with the parent sdk-install skill, matching the mostly-distinct anchor.	4 / 5
	Total	15 / 20 Passed

Validation

93%

Warnings & errors only

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

Criteria	Description	Result
relative_links	Relative link issues: 14 suspicious	Warning

	Total	15 / 16 Passed

Repository: launchdarkly/ai-tooling
Path: skills/onboarding/sdk-install/apply/SKILL.md
Commit: ef54971

Reviewed: 6 days ago

Table of Contents

Discovery Implementation Validation

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.