Name: mcp-configure
Rating: 71.2 (1 reviews)
Author: launchdarkly

mcp-configure

Configure the LaunchDarkly hosted MCP server during onboarding. Use when the parent LaunchDarkly onboarding skill reaches the MCP offer, after the first flag works. Supports Cursor, Claude Code, Windsurf, GitHub Copilot, and other MCP-compatible agents. OAuth authentication; no API keys for the hosted server.

Quality

89%

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.

A well-structured, highly actionable skill body: a sequenced workflow with explicit verification and error-recovery branching, backed by real one-level-deep reference files that carry the per-agent config templates. Only minor conciseness gains are available from de-duplicating the restart guidance.

Dimension	Reasoning	Score
Conciseness	The body is efficient and operational — install URL, config paths, error signatures, and recovery guidance with little padding. Minor over-explanation remains: restart advice is repeated across Step 5's 3b path, the resume step, and 'What NOT to Do', which could be trimmed. Not 3, since nearly every section carries non-obvious information Claude cannot infer.	4 / 5
Actionability	Fully executable guidance: the quick-install URL, per-agent config file paths, a named probe tool ('list-feature-flags' with the user's project key), exact auth-error signatures (401, 403, 'unauthorized', 'forbidden'), copy-ready user-facing messages, and a complete blocking-question JSON for legacy migration. Common cases are covered concretely, with full config JSON one reference away.	5 / 5
Workflow Clarity	A clear five-step sequence with an explicit validation probe and three-way branching (success / auth error / tool not found), re-probe feedback loops after re-authorization, a defined resume path after restart, and a non-blocking fallback. Matches the anchor for explicit validation steps and error-recovery loops.	5 / 5
Progressive Disclosure	The body holds the workflow and decision logic while per-agent JSON templates and UI links are appropriately split into two real, one-level-deep reference files, cited inline with working anchors (e.g. 'references/mcp-ui-links.md#clients') and indexed in a References section. Both referenced files exist and cover exactly what is claimed.	5 / 5
	Total	19 / 20 Passed

Description

82%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 description with an explicit, concrete trigger clause tied to the parent onboarding flow and a distinct niche. The 'what' is slightly terse — enumerating the concrete actions it performs (detect agent, install link, manual config, verify) would lift specificity and completeness margins.

Suggestions

Enumerate the concrete actions in the 'what' portion (e.g. 'Detect the agent, present the quick-install link or write the MCP config, and verify tools are live') to raise specificity beyond a single action.

Add one or two natural trigger synonyms such as 'set up MCP' or 'add the LaunchDarkly MCP server' to broaden the phrases a user would naturally say.

Dimension	Reasoning	Score
Specificity	Names the domain ('Configure the LaunchDarkly hosted MCP server') with one concrete action plus the auth model ('OAuth authentication; no API keys'), matching the 'domain plus 1-2 concrete actions, not comprehensive' anchor. It stops short of listing sub-actions (agent detection, quick install, manual config, verification) that would justify a 4.	3 / 5
Completeness	Both questions are explicitly answered: the 'what' is 'Configure the LaunchDarkly hosted MCP server during onboarding' with supported agents, and the 'when' is a concrete trigger phrase — 'Use when the parent LaunchDarkly onboarding skill reaches the MCP offer, after the first flag works'. Not below 5 because the trigger clause is present and specific, unlike anchor 4's 'when could be more explicit'.	5 / 5
Trigger Term Quality	Good natural keyword coverage: 'LaunchDarkly hosted MCP server', 'MCP', 'onboarding', and the concrete agent names (Cursor, Claude Code, Windsurf, GitHub Copilot). Missing a few natural phrasings users would say, such as 'set up MCP' or 'add MCP server', so it falls short of the comprehensive anchor 5.	4 / 5
Distinctiveness Conflict Risk	A clear niche (LaunchDarkly hosted MCP setup) gated to the parent LaunchDarkly onboarding flow, with product-specific terms and agent names; it is unlikely to trigger for any other skill. Fits the 'clear niche with distinct triggers; minimal conflict risk' anchor.	5 / 5
	Total	17 / 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: 2 suspicious	Warning

	Total	15 / 16 Passed

Repository: launchdarkly/ai-tooling
Path: skills/onboarding/mcp-configure/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.