Name: onboarding
Rating: 89.60000000000001 (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

88%

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 1-3

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 well-structured, highly actionable orchestrator with excellent workflow sequencing and validation, but it is padded with redundant restatements of the same decision points and verbose communication-style directives. Its progressive disclosure is undermined by heavy reliance on nested skill files that are not included in the bundle.

Suggestions

Include the referenced nested skill files (mcp-configure/SKILL.md, sdk-install/{detect,plan,apply}/SKILL.md, first-flag/SKILL.md) in the bundle, or collapse their essentials inline so the skill is self-contained.

Consolidate the decision-point (D5/D7/D8) definitions into a single canonical table and reference it, instead of restating them in the Decision Points, Step Execution Rules, Step 5, and Edge Cases sections.

Trim the User-Facing Communication directives to a short checklist; the response-structure and forbidden-output rules add length that competes with token budget without changing the orchestration logic.

Dimension	Reasoning	Score
Conciseness	The body is purposeful orchestration rather than concept padding, but it restates decision-point IDs (D5/D7/D8) across the Decision Points, Step Execution Rules, Step 5, and Edge Cases sections, and spends substantial tokens prescribing response tone and forbidden-output rules that could be tightened.	2 / 3
Actionability	It provides concrete executable commands (the exact `npx skills add ...` invocation), specific agent-detection indicators, exact dashboard URL templates, and a precise onboarding-log schema — actionable guidance rather than pseudocode.	3 / 3
Workflow Clarity	Steps 0-6 are explicitly sequenced with blocking/non-blocking decision points in a table, validation checkpoints (MCP auto-verify probing, end-to-end SDK validation, compile check), and feedback loops (MCP fail -> log -> restart -> ldcli/API fallback), plus a resumption path.	3 / 3
Progressive Disclosure	The overview points cleanly to one-level-deep references that exist (1.8-summary, 1.9-editor-rules, sdk/recipes, sdk/snippets), but its primary detailed materials are delegated to nested skills (mcp-configure, sdk-install/detect\|plan\|apply, first-flag) whose SKILL.md files are not present in the bundle, leaving the main disclosure targets as dangling references.	2 / 3
	Total	10 / 12 Passed

Description

100%Weight 40%Scale 1-3

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 concise, third-person, and concrete, covering what the skill does and when to use it with natural trigger phrases including a direct "onboard me" invocation. It is among the strongest possible descriptions for this rubric.

Dimension	Reasoning	Score
Specificity	The description enumerates concrete actions — "kickoff roadmap, resumable log, explore repo, MCP, companion flag skills, nested SDK install (detect/plan/apply), first flag" — listing multiple specific capabilities rather than vague claims.	3 / 3
Completeness	It explicitly answers both what (the colon-separated action list) and when ("Use when adding LaunchDarkly... or 'onboard me'"), with an explicit trigger clause rather than implied timing.	3 / 3
Trigger Term Quality	Natural user phrasing is covered with "adding LaunchDarkly," "setting up or integrating feature flags," "SDK integration," and the direct trigger "onboard me," matching the anchor for good coverage of terms users would actually say.	3 / 3
Distinctiveness Conflict Risk	The LaunchDarkly-specific scope and distinct triggers make it clearly niche and unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 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: 3 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.