CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

68

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

85%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.

The body is a strong, actionable onboarding workflow with excellent validation/feedback loops and clean progressive disclosure into two real reference files. The main improvement opportunity is reducing redundancy in the authorization/enabling guidance spread across Steps 2, 4, and 5.

Suggestions

Consolidate the enabling/authorization guidance: Step 2's 'tell the user what to expect' block and Step 4's per-agent authorization overlap with Step 5's enable step — merge into one place and cross-reference.

Tighten Step 2's multi-bullet 'what to expect after clicking the link' into a single concise line plus the fallback pointer to Step 3.

The 'What NOT to Do' section partly restates edge-case migration guidance; consider folding the npx/FM/AgentControl prohibitions into their respective edge-case bullets to avoid repetition.

DimensionReasoningScore

Conciseness

Mostly efficient and free of generic concept explanations, but enabling/authorization guidance is repeated across Steps 2, 4, and 5 and the 'tell the user what to expect' block in Step 2 could be tightened, fitting the 'mostly efficient but could be tightened' anchor.

3 / 5

Actionability

Highly concrete and executable: exact config file paths per agent, install URLs, the specific probe tool ('list-feature-flags'), exact user-facing prompt text in quotes, and precise log strings, covering the common cases copy-paste ready.

5 / 5

Workflow Clarity

A clearly sequenced 5-step process with an explicit validation checkpoint (probe MCP tool), success/failure branching, log-update-first discipline, restart/resume feedback loop, and a structured blocking migration question — matching the top anchor for validation and error recovery.

5 / 5

Progressive Disclosure

Clear overview body with well-signaled, one-level-deep references to real bundle files (mcp-config-templates.md, mcp-ui-links.md) that hold the bulk JSON and link tables; content is appropriately split and easy to navigate.

5 / 5

Total

18

/

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.

The description is well-constructed: third-person, explicit what-and-when, and clearly niche-scoped to LaunchDarkly MCP onboarding. Its only soft spot is specificity, since it frames one action with supporting attributes rather than enumerating several distinct actions.

DimensionReasoningScore

Specificity

Names the domain ('LaunchDarkly hosted MCP server') and a concrete action ('Configure ... during onboarding') plus supported agents, but describes essentially one action with attributes rather than multiple distinct concrete actions, matching the 'names domain and 1-2 concrete actions' anchor.

3 / 5

Completeness

Explicitly answers both 'what' ('Configure the LaunchDarkly hosted MCP server during onboarding') and 'when' with a concrete trigger clause ('Use when the parent LaunchDarkly onboarding skill reaches Step 4 (MCP)'), matching the top anchor.

5 / 5

Trigger Term Quality

Good natural keyword coverage including 'LaunchDarkly', 'MCP server', 'onboarding', and concrete agent names (Cursor, Claude Code, Windsurf, GitHub Copilot); a few common synonyms or phrasings a user might naturally say are missing, so it sits above the midpoint but not fully comprehensive.

4 / 5

Distinctiveness Conflict Risk

A clear niche (LaunchDarkly hosted MCP configuration during onboarding Step 4) with distinct, vendor-specific triggers and minimal overlap risk with other skills.

5 / 5

Total

17

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 2 suspicious

Warning

Total

15

/

16

Passed

Repository
launchdarkly/ai-tooling
Reviewed

Table of Contents

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.