{
  "markdown": "# LaunchDarkly Agent Skills\n\nLaunchDarkly's public collection of agent skills and playbooks. These skills encode repeatable workflows for working with LaunchDarkly, so coding agents can execute common tasks safely and consistently.\n\n## What Is This Repo?\n\nAgent Skills are modular, text-based playbooks that teach an agent how to perform a workflow. This repo is designed to be a public, open-source home for LaunchDarkly skills and to align with the emerging Agent Skills Open Standard.\n\n## Available Skills\n\n### Feature Flags\n\n| Skill | Description |\n|-------|-------------|\n| `feature-flags/launchdarkly-flag-command` | Resolve `/flag` style requests into fast flag lookup, detail, and disambiguation |\n| `feature-flags/should-flag-change` | Advisory, read-only call on whether a code change (diff/PR) should ship behind a feature flag |\n| `feature-flags/launchdarkly-flag-discovery` | Audit flags, find stale/launched flags, and assess removal readiness |\n| `feature-flags/launchdarkly-flag-create` | Create new feature flags in a way that fits existing codebase patterns |\n| `feature-flags/launchdarkly-flag-targeting` | Control targeting, rollouts, rules, and cross-environment config |\n| `feature-flags/launchdarkly-flag-cleanup` | Safely remove flags from code using LaunchDarkly as the source of truth |\n| `feature-flags/launchdarkly-flag-drift` | Detect and reconcile drift between an in-code SDK fallback default and the LaunchDarkly default rule |\n| `feature-flags/launchdarkly-guarded-rollout` | Configure guarded rollouts with progressive traffic, metric monitoring, and rollback |\n| `feature-flags/flag-release` | Record a flag's automated release for a PR, honoring release intent and per-environment release policies |\n| `feature-flags/flag-and-release-change` | End-to-end PR orchestrator: decide → create + wire the flag → record its release (composes the skills above) |\n| `feature-flags/launchdarkly-flag-qualitative-feedback-setup` | Add a qualitative user feedback widget tied to a flag, adapting to the project's framework and design system |\n\n### AgentControl\n\n| Skill | Description |\n|-------|-------------|\n| `agentcontrol/configs-create` | Create configs with variations for agent or completion mode |\n| `agentcontrol/migrate` | Migrate an app with hardcoded LLM prompts to AgentControl in five stages (extract, wrap, tools, tracking, evals) |\n| `agentcontrol/configs-update` | Update and delete configs, manage lifecycle |\n| `agentcontrol/configs-variations` | Manage config variations for A/B testing |\n| `agentcontrol/tools` | Create and attach tools for function calling |\n| `agentcontrol/projects` | Create and manage projects to organize configs |\n| `agentcontrol/online-evals` | Attach LLM-as-a-judge evaluators to configs |\n| `agentcontrol/configs-targeting` | Configure targeting rules for config rollouts |\n| `agentcontrol/snippets` | Create and manage reusable prompt snippets across configs |\n| `agentcontrol/agent-graphs` | Create and manage multi-agent graphs with routing and handoffs |\n\n### Experiments\n\n| Skill | Description |\n|-------|-------------|\n| `experiments/launchdarkly-experiment-setup` | Set up experiments with metrics, treatments, and data collection |\n\n### Metrics\n\n| Skill | Description |\n|-------|-------------|\n| `metrics/launchdarkly-metric-choose` | Select the right metric type for an experiment |\n| `metrics/launchdarkly-metric-create` | Create metrics and instrument tracking events |\n| `metrics/launchdarkly-metric-instrument` | Add tracking calls to code for existing metrics |\n\n## Install as a Claude Code Plugin\n\nThis repo is a [Claude Code plugin](https://code.claude.com/docs/en/create-plugins). Installing it gives you all the skills above plus the LaunchDarkly MCP server.\n\n1. Add this repo as a plugin marketplace in Claude Code:\n   ```\n   /plugin marketplace add launchdarkly/ai-tooling\n   ```\n2. Install the plugin:\n   ```\n   /plugin install launchdarkly@launchdarkly-ai-tooling\n   ```\n3. Authenticate the LaunchDarkly MCP server when prompted with your [API access token](https://docs.launchdarkly.com/home/account/api).\n\nOnce installed, skills are available as `/launchdarkly:<skill-name>` across all your projects, and the MCP server can read and modify your flags directly.\n\n### Onboarding\n\n| Skill | Description |\n|-------|-------------|\n| `onboarding` | End-to-end LaunchDarkly setup: quiet scripted flow, SDK install, first flag with a live reveal, MCP offered afterwards |\n| `onboarding/mcp-configure` | Configure the LaunchDarkly hosted MCP server (OAuth, no API keys needed) |\n| `onboarding/sdk-install` | Install and initialize the correct SDK via detect, plan, and apply sub-steps |\n\n## Install as a Cursor Plugin\n\nThis repo is a [Cursor plugin](https://cursor.com/docs/plugins/building). Installing it gives you all the skills above plus the LaunchDarkly MCP server, so the agent can read and modify your flags directly.\n\n1. Open Cursor and go to **Settings > Plugins**.\n2. Search for **LaunchDarkly** in the marketplace, or install from the repo URL:\n   ```\n   https://github.com/launchdarkly/ai-tooling\n   ```\nOnce installed, the skills and MCP server are available across all your projects.\n\n## Quick Start (Local)\n\n```bash\n# Clone the repo\ngit clone https://github.com/launchdarkly/ai-tooling.git\ncd ai-tooling\n\n# If your agent supports skills.sh installs:\nnpx skills add launchdarkly/ai-tooling\n\n# Or manually copy a skill into your agent's skills path:\ncp -r skills/feature-flags/launchdarkly-flag-cleanup <your-agent-skills-dir>/\n\n```\n\nThen ask your agent something like:\n\n```\nWhich feature flags are stale and should be cleaned up?\n```\n\n```\nCreate a feature flag for the new checkout flow\n```\n\n```\nRoll out dark-mode to 25% of users in production\n```\n\n```\nRemove the `new-checkout-flow` feature flag from this codebase\n```\n\n## Install via skills.sh CLI\n\n```bash\nnpx skills add <owner/repo>\n```\n\n## Contributing\n\nSee `CONTRIBUTING.md` for how to add new skills and the conventions we follow.\n\n## License\n\nApache-2.0\n",
  "bytes": 6014,
  "sha": "637649a1fe20ed254e9bdb959952056b6369bb13140f6b0801c37f541a7fe675",
  "repo_slug": "launchdarkly/ai-tooling",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/skl_launchdarkly_ai_tooling_online_evals_0d2df234/readme"
}