Name: apply
Rating: 54.400000000000006 (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

61%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/onboarding/sdk-install/apply/SKILL.md

Quality

Content

55%

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

The workflow is excellently sequenced with strong validation checkpoints and blocking consent gates, but the skill is materially weakened by missing bundle files (all recipe/snippet/sibling references resolve to nothing) and by init code being deferred rather than included.

Suggestions

Ship the referenced bundle (references/sdk/recipes.md, references/sdk/snippets/) or inline minimal executable init snippets per major SDK so the skill is self-contained and the references are not dead links.

Tighten the dual-SDK and consent sections by collapsing repeated bolded emphasis and restating the rationale once; preserve the decision-point templates but trim redundant reinforcement.

Verify each relative path (../SKILL.md, ../plan/SKILL.md, ../run/SKILL.md, ../../references/...) actually resolves in the distributed skill; broken navigation should be fixed or the references removed.

Dimension	Reasoning	Score
Conciseness	Mostly actionable, but it is fairly verbose with heavy bolded-emphasis repetition ("two", "both", "do not") and restates consent rationale at length; it could be tightened without losing clarity.	2 / 3
Actionability	Provides concrete structured-question templates, MCP calls, and env-var tables, but the core init code is explicitly deferred to external recipes rather than given as executable snippets, so it is not fully copy-paste ready.	2 / 3
Workflow Clarity	Clear four-step sequence with explicit BLOCKING decision points (D7, D8), validation checkpoints ("verify the dependency appears in the lock file", Step 4 compile/lint), and feedback loops ("Do not proceed to the next step if the code doesn't compile").	3 / 3
Progressive Disclosure	The body heavily references one-level-deep files (recipes.md, snippets/, plan/run/detect sibling SKILLs, parent sections), but none of these bundle files ship with the skill -- the supplied target contains only SKILL.md, so the references are dead and navigation is broken.	1 / 3
	Total	8 / 12 Passed

Description

67%

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 specific, third-person, and well-scoped to a distinct niche, but it lacks an explicit "Use when..." trigger clause and natural user-facing trigger terms, instead relying on structural navigation cues.

Suggestions

Add an explicit "Use when..." clause naming natural triggers (e.g. "Use when installing or onboarding a LaunchDarkly SDK during the SDK install workflow").

Include more natural user-facing terms such as "feature flags", "LaunchDarkly", or "SDK setup" so the description matches how users actually phrase the request.

Move the structural navigation hint ("Nested under sdk-install; next is run") out of the user-facing description, or reframe it as a trigger rather than a map of the workflow.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ("install dependency", "configure env and secrets with consent", "add init at entrypoint(s)", "verify compile") rather than vague language.	3 / 3
Completeness	It clearly answers "what does this do" with concrete actions, but the "when" is only implied via nesting ("Nested under sdk-install; next is run") rather than an explicit "Use when..." clause, which caps completeness at 2 per the judging guidelines.	2 / 3
Trigger Term Quality	Contains relevant technical terms (SDK, onboarding, secrets, entrypoint) but lacks the natural phrasings a user would say (e.g. "LaunchDarkly flags", "feature flags", "set up LaunchDarkly"); the trigger guidance "Nested under sdk-install; next is run" is structural rather than user-facing.	2 / 3
Distinctiveness Conflict Risk	Tightly scoped to LaunchDarkly SDK onboarding with distinct nested-step positioning, making it unlikely to trigger for unrelated skills.	3 / 3
	Total	10 / 12 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: a2fb6e9

Reviewed: 2 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.