If you're managing AI configs in LaunchDarkly and find yourself copying the same persona instructions or safety guardrails across multiple prompts, this handles the dedupe work. It walks you through creating reusable text blocks (snippets) for things like output formats, compliance disclaimers, or domain knowledge, then wiring them into your config variations. The workflow is straightforward: identify repeated text, create snippets with descriptive keys, verify they're saved, and update them when requirements change. One thing to note is that snippet updates create new versions that propagate to all referencing configs, so you need to think through the blast radius before changing widely used guardrails.
npx -y skills add launchdarkly/agent-skills --skill snippets --agent claude-codeInstalls into .claude/skills of the current project.
Select a file.
sickn33/antigravity-awesome-skills
moizibnyousaf/ai-agent-skills
github/awesome-copilot