Name: mcp-configure
Rating: 69.6 (1 reviews)
Author: launchdarkly

mcp-configure

Configure the LaunchDarkly hosted MCP server during onboarding. Use when the parent LaunchDarkly onboarding skill reaches Step 4 (MCP). Supports Cursor, Claude Code, Windsurf, GitHub Copilot, and other MCP-compatible agents. OAuth authentication; no API keys for the hosted server.

Quality

85%

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

85%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 body is highly actionable and well-structured, with a clear sequenced workflow, explicit validation checkpoints, and clean one-level-deep references. The only soft spot is conciseness — some user-facing coaching and duplicated enable/verify prose could be trimmed without losing clarity.

Suggestions

Collapse the repeated install-link coaching in Step 2 into a single compact bullet list; the multi-paragraph 'what to expect' guidance inflates the token budget.

Consolidate the enable/authorize guidance that appears in both Step 4 and Step 5 to avoid restating the same toggle+OAuth instructions twice.

Move the verbatim user-facing resume quote into the references or shorten it; long scripted strings in the main body cost tokens on every load.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and avoids explaining concepts Claude already knows, but Step 2's repeated install-link coaching ('tell the user what to expect after clicking the link') and the duplicate enable/verify guidance across Steps 4–5 could be tightened; some prose earns its place but a fair amount is user-facing scripting that pads the skill.	2 / 3
Actionability	Concrete config-file paths per agent, exact server URLs, copy-paste JSON via the references, a specific probe command (`list-feature-flags` with a known project key), and an explicit user-facing resume quote — fully executable guidance rather than vague direction.	3 / 3
Workflow Clarity	A clear 5-step sequence with explicit validation at Step 5 (probe MCP immediately, branch on success/failure, update the onboarding log first, retry-with-restart feedback loop, and a non-blocking fallback), plus a blocking confirmation gate (D-MIGRATE) before mutating config — the feedback-loop and checkpoint anchors are met.	3 / 3
Progressive Disclosure	SKILL.md is an overview that points one level deep to real, well-signaled references (`references/mcp-config-templates.md`, `references/mcp-ui-links.md`) for the bulky per-agent JSON and link tables; the references files exist and do not chain further, so navigation is easy and appropriately split.	3 / 3
	Total	11 / 12 Passed

Description

85%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 specific, complete (explicit what + when), and tightly scoped to a distinct niche. Trigger-term quality is the weakest dimension: it relies on product/agent names and niche jargon rather than the natural phrasings a user would say.

Suggestions

Add natural-language trigger phrases a user might say (e.g. 'set up LaunchDarkly MCP', 'connect LaunchDarkly to my editor', 'add the LaunchDarkly MCP server') alongside the current Step 4 reference.

Reduce reliance on internal vocabulary like 'hosted MCP server' as the sole trigger; pair it with plain terms like 'MCP tools for feature flags'.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — 'Configure the LaunchDarkly hosted MCP server during onboarding', 'OAuth authentication; no API keys' — and specifies the supported agents (Cursor, Claude Code, Windsurf, GitHub Copilot), matching the 'multiple specific concrete actions' anchor.	3 / 3
Completeness	Explicitly answers both what ('Configure the LaunchDarkly hosted MCP server') and when ('Use when the parent LaunchDarkly onboarding skill reaches Step 4 (MCP)'), satisfying the 'what AND when with explicit triggers' anchor.	3 / 3
Trigger Term Quality	It includes relevant terms ('MCP', 'LaunchDarkly', 'Cursor', 'Claude Code', 'onboarding') but leans on product/agent names and the niche jargon 'hosted MCP server' rather than the natural phrasings a user would say; missing common variations a user might actually utter.	2 / 3
Distinctiveness Conflict Risk	Scoped to a narrow niche — LaunchDarkly MCP at a specific onboarding step — with distinct triggers tied to the parent skill's Step 4, making it unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 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: 2 suspicious	Warning

	Total	15 / 16 Passed

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

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.