aka. Agent Skills
Discover skills for AI coding agents. Works with Claude Code, OpenAI Codex, Gemini CLI, Cursor, and more.
Enforces iterative web research for coding and DevOps questions to prevent assumptions about libraries, frameworks, APIs, versions, and configurations. Use this skill when the user asks about programming languages, frameworks, libraries, DevOps tools, cloud platforms, databases, container orchestration, CI/CD, infrastructure as code, or any technical topic where current documentation, version-specific behavior, or recent changes matter. This skill ensures Claude searches and fetches authoritative sources before answering, even for topics Claude may have knowledge about, to verify current state and avoid outdated information.
Use when you have a written implementation plan to execute in a separate session with review checkpoints
Next.js middleware patterns for request processing
Client Components patterns in Next.js App Router
NextAuth.js / Auth.js authentication patterns
Deep codebase analysis that extracts learnings from documentation. Creates context entries and learnings from docs/ with pattern matching.
Comprehensive product analytics skill for PostHog implementation and management. Auto-triggers on phrases like "add analytics", "track event", "feature flag", "A/B test", "experiment", "session recording", "product analytics", "user tracking", "posthog", "conversion funnel", "user behavior", "engagement metrics", "rollout", "percentage rollout". Provides slash commands /kodo ph-event (event tracking setup), /kodo ph-flag (feature flag management), /kodo ph-experiment (A/B testing), /kodo ph-sync (Notion documentation sync). Ensures full instrumentation from Day 1 with autocapture, custom events, feature flags, experiments, and maintains comprehensive documentation in Notion.
This skill should be used when the user asks to "create a presentation", "generate slides", "make a presentation", "turn into slides", "presentation from this document", "slides from PRD", "slides from transcript", or wants to convert any document into an HTML slide presentation.
Archive a memory by ID (with confirmation)
Manage Portainer deployments - create stacks from Git repos, check deployment status, redeploy, view logs. Use when user asks about deploying to Portainer, checking stack status, or managing Docker deployments.
Playwright fixtures and test setup patterns
Rules and patterns for implementing cache in a Lutece 8 plugin. AbstractCacheableService, CDI initialization, cache operations, invalidation via CDI events.
Complete guide for building beautiful apps with Expo Router. Covers fundamentals, styling, components, navigation, animations, patterns, and native tabs.
This skill should be used when the user asks about "prisma client", "findMany", "findUnique", "create", "update", "delete", "prisma query", "include", "select", "where", "prisma transactions", "nested writes", or mentions database queries and CRUD operations with Prisma.
This skill should be used when the user asks to "generate video", "create video with Veo", "text to video", "image to video", "animate image", or "video generation". Generates videos using Google Veo 3.1 API with text, image, or video inputs.
This skill should be used when the user asks to "analyze video", "summarize video", "extract video transcript", "understand video content", "video to text", "describe video", "ask questions about video", or "what happens in this video". Analyzes videos using Google Gemini API with local file upload or YouTube URL input.
Gather ticket metadata in one call.
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup
Gather git context and branch data in one call.
This skill should be used when the user asks to "plan a feature", "evaluate a feature", "review a feature proposal", "analyze a feature before implementation", "plan a feature", "review this feature", "assess this feature", or uses the /super-dev command for multi-agent feature planning with 5-perspective judgment system.