Name: onboarding
Rating: 87.2 (1 reviews)
Author: launchdarkly

onboarding

Onboard a project to LaunchDarkly: kickoff roadmap, resumable log, explore repo, MCP, companion flag skills, nested SDK install (detect/plan/apply), first flag. Use when adding LaunchDarkly, setting up or integrating feature flags in a project, SDK integration, or 'onboard me'.

1.48x

Quality

85%

Does it follow best practices?

Impact

92%

1.48x

Average score across 3 eval scenarios

Securityby

Low

Low-risk findings worth noting

Quality

Content

77%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-sequenced, validation-rich onboarding workflow with concrete inline commands and clear decision points. Its progressive disclosure is undermined by numerous nested-skill references that are absent from the bundle, and some guidance is repeated across sections.

Suggestions

Include the referenced nested skill files (mcp-configure/SKILL.md, sdk-install/{SKILL.md,detect/plan/apply/SKILL.md}, first-flag/SKILL.md, mcp-configure/references/*) in the bundle, or remove/clearly mark as external the links that cannot resolve here.

Consolidate the repeated deferred-credential and user-facing-communication rules into a single authoritative section instead of restating them in Prerequisites, Core Principles, and Agent Behavior Directives.

Add inline minimal executable snippets for the SDK install and first-flag steps so the skill is actionable even when the nested files are unavailable.

Dimension	Reasoning	Score
Conciseness	Mostly efficient operational guidance, but themes like deferred-credential handling, decision-point markers, and user-facing-output rules are restated across Prerequisites, Core Principles, and Agent Behavior Directives and could be tightened.	4 / 5
Actionability	Provides a concrete `npx skills add` command, deep-link URL table, and MCP auto-verify steps, but the executable detail for SDK install and first-flag creation is delegated to nested skill files that are not present in the bundle.	4 / 5
Workflow Clarity	Clear Steps 0-6 sequence with an explicit blocking-decision-points table (D5/D7/D8/D9), resume logic, edge-cases table, and validation checkpoints (compile check, auth-error stop, MCP probe) with feedback loops.	5 / 5
Progressive Disclosure	The body is structured as a well-signaled overview pointing to one-level-deep nested skills, but most referenced paths (mcp-configure/SKILL.md, sdk-install/, first-flag/SKILL.md, mcp-configure/references/) do not exist in the actual bundle; only references/* files are present and well-organized.	3 / 5
	Total	16 / 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, third-person description that pairs a comprehensive list of concrete onboarding actions with explicit 'Use when...' triggers. Trigger-term coverage is good but could add a few more natural synonyms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete onboarding actions — 'kickoff roadmap, resumable log, explore repo, MCP, companion flag skills, nested SDK install (detect/plan/apply), first flag' — giving comprehensive coverage of the domain.	5 / 5
Completeness	Explicitly answers both 'what' (the onboarding sequence) and 'when' via a concrete 'Use when...' clause enumerating trigger scenarios.	5 / 5
Trigger Term Quality	Includes natural user phrases like 'adding LaunchDarkly', 'setting up or integrating feature flags', and "'onboard me'", but omits common synonyms/variations such as 'LaunchDarkly setup' or 'feature flag integration'.	4 / 5
Distinctiveness Conflict Risk	The LaunchDarkly / feature-flag niche with specific trigger phrases has minimal overlap with other skills and is clearly distinguishable.	5 / 5
	Total	19 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 43 missing, 28 deeper-than-1-level	Warning
referenced_paths_exist	Referenced path issues: 7 deeper-than-1-level	Warning

	Total	14 / 16 Passed

Repository: launchdarkly/ai-tooling
Path: skills/onboarding/SKILL.md
Commit: 83f5166

Reviewed: 9 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.