Is the Agent Graphs (LaunchDarkly) skill free?

Yes. The skill itself is free from launchdarkly/ai-tooling. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Agent Graphs (LaunchDarkly) SkillProof Score?

8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 5/5.

How do I install Agent Graphs (LaunchDarkly)?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Agent Graphs (LaunchDarkly) with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Agent Graphs (LaunchDarkly)

Guides Claude through designing and wiring LaunchDarkly AI-config agent graphs.

by launchdarkly · launchdarkly/ai-tooling

Works with setup

Install — copy the command Download source ↗

Test report

Verdict: Works with setup
Score: 8.8/10
Tested: Jul 15, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · b5fbcee

Cleanly-scoped skill that discloses its own hard dependency up front (`compatibility: Requires the remotely hosted LaunchDarkly MCP server`) rather than hiding it, and a deprecated sibling skill politely redirects here instead of duplicating stale instructions. Could not exercise create-agent-graph live — no LaunchDarkly MCP access in this environment — so the skill's tool-call schema was checked against the SKILL.md body only, not a real API round trip.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 7/10
Docs & honesty 5/5

What Agent Graphs (LaunchDarkly) does

Walks Claude through designing a directed graph of LaunchDarkly AI configs (nodes) connected by routing edges with handoff data, then creating and verifying it via the LaunchDarkly MCP server's create-agent-graph/get-agent-graph tools. Triggers on requests to build multi-agent routing, triage, or escalation workflows on LaunchDarkly. Needs the remotely-hosted LaunchDarkly MCP server and account, which the frontmatter honestly discloses up front.

How to install Agent Graphs (LaunchDarkly)

git clone https://github.com/launchdarkly/ai-tooling
cd ai-tooling
mkdir -p ~/.claude/skills
cp -r skills/agentcontrol/agent-graphs ~/.claude/skills/agent-graphs

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Agent Graphs (LaunchDarkly)

/agent-graphs Guides Claude through designing and wiring LaunchDarkly AI-config agent graphs.

It also activates on plain-language prompts like these:

Design a LaunchDarkly agent graph that routes support tickets to specialists
Help me wire up a billing vs technical triage flow in LaunchDarkly AI configs
Build a multi-agent escalation graph using LaunchDarkly's agent config tools

Frequently asked questions

Is the Agent Graphs (LaunchDarkly) skill free?: Yes. The skill itself is free from launchdarkly/ai-tooling. SkillProof publishes the install command and an independent test verdict at no cost.
Does Agent Graphs (LaunchDarkly) work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 15, 2026. Verdict: Works with setup. Cleanly-scoped skill that discloses its own hard dependency up front (`compatibility: Requires the remotely hosted LaunchDarkly MCP server`) rather than hiding it, and a deprecated sibling skill politely redirects here instead of duplicating stale instructions. Could not exercise create-agent-graph live — no LaunchDarkly MCP access in this environment — so the skill's tool-call schema was checked against the SKILL.md body only, not a real API round trip.
What is the Agent Graphs (LaunchDarkly) SkillProof Score?: 8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 5/5.
How do I install Agent Graphs (LaunchDarkly)?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Agent Graphs (LaunchDarkly) with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.