Guidelines for the Tour Card UI, the primary item in the tour grid. Use when building the tour browsing interface.

Build persistent memory systems for AI agents using Mem0, claude-mem, or custom implementations. Use when adding conversation memory, user preferences, or contextual recall to agents. Covers memory architecture patterns, retrieval strategies, and privacy controls. NOT for RAG systems (use building-rag-systems).

Build production traffic engineering for Kubernetes with Envoy Gateway, Gateway API, KEDA autoscaling, and Envoy AI Gateway. Use when implementing ingress, rate limiting, traffic routing, TLS, autoscaling, or LLM traffic management.

Use when building AI agents with Google's Agent Development Kit (ADK). Triggers include creating ADK agents, Gemini-powered agents, multi-agent workflows, MCP integration with ADK, agent evaluation, workflow agents (Sequential/Parallel/Loop), Vertex AI deployment, or comparing OpenAI SDK with ADK. NOT when using other frameworks (OpenAI SDK, LangChain, CrewAI) or general LLM API calls.

Help users build effective AI applications. Use when someone is building with LLMs, writing prompts, designing AI features, implementing RAG, creating agents, running evals, or trying to improve AI output quality.

Produce an LLM Build Pack (prompt+tool contract, data/eval plan, architecture+safety, launch checklist). Use for building with LLMs, GPT/Claude apps, prompt engineering, RAG, and tool-using agents.

Use when building web UIs with Next.js 15+ and React 19 - covers Server Components, App Router, testing with Vitest and Playwright, and accessibility standards

Build Kubernetes observability stacks with Prometheus, Grafana, OpenTelemetry, Jaeger, and Loki. Use when implementing metrics, tracing, logging, SRE practices, or cost engineering for cloud-native applications.

Use when building async database layers with SQLModel and PostgreSQL. Triggers include async session management, create_async_engine, SQLModel relationships, CRUD operations with async/await, N+1 prevention with selectinload, JSONB columns, self-referential models, or Alembic async migrations. NOT when using sync SQLAlchemy (use sync patterns) or raw SQL (use SQLModel ORM).

Execute whiteboard plans through gated phases with subagent dispatch. Require feature branch. Each phase goes through DISCOVERY -> PRE-GATE (pseudocode) -> IMPLEMENT -> POST-GATE (reviewer) -> CHECKPOINT. Produce per-phase commits, execution log, and working code with tests. Use after /code-foundations:whiteboarding to implement saved plans. Triggers on: build it, execute plan, implement the whiteboard, run the plan.

Will utilise buildkite read only mcp server to solve specific buildkite issues encountered

Use this skill when working with Buildkite CI/CD pipelines, agents, builds, test analytics, or package registries. Covers pipeline configuration, YAML syntax, agent setup, build steps, plugins, and API usage.

Guides development of AILANG builtin functions. Use when user wants to add a builtin function, register new builtins, or understand the builtin system. Reduces development time from 7.5h to 2.5h (-67%).

Use omicverse's pyComBat wrapper to remove batch effects from merged bulk RNA-seq or microarray cohorts, export corrected matrices, and benchmark pre/post correction visualisations.

Guide Claude through omicverse's bulk RNA-seq DEG pipeline, from gene ID mapping and DESeq2 normalization to statistical testing, visualization, and pathway enrichment. Use when a user has bulk count matrices and needs differential expression analysis in omicverse.

Walk Claude through PyDESeq2-based differential expression, including ID mapping, DE testing, fold-change thresholding, and enrichment visualisation.

Use when generating multiple curriculum-aligned concept files in parallel (5+ concepts) - researches curriculum, creates concept list, spawns parallel generation agents, orchestrates review loop until all pass

**Direct bash for loops are approximately 10x faster than sub-agents for bulk operations.**

Turn bulk RNA-seq cohorts into synthetic single-cell datasets using omicverse's Bulk2Single workflow for cell fraction estimation, beta-VAE generation, and quality control comparisons against reference scRNA-seq.

Transcribe ALL videos from a TikTok profile. Use when you want to process an entire profile's content.

Automate bumping the `lun` version in GitHub Actions and keeping `install-lun` references in sync.

Execute automated release workflow for Rust projects using Conventional Emoji Commits. Analyze commits since last release, determine semantic version bump (MAJOR/MINOR/PATCH), update Cargo.toml, generate changelog with git-cliff, create git tags, and publish GitHub releases. Use when the user requests to cut a release, bump version, create a release, or publish a new version. Also use when the user asks about the release process or wants to preview what the next release would be.

Bump tantivy to the latest commit on main branch, fix compilation issues, and open a PR

Bump version numbers for a new release. Use when releasing, updating version, or preparing a new version.

Create optimized production bundles with Bun's native bundler. Use when building applications for production, optimizing bundle sizes, setting up multi-environment builds, or replacing webpack/esbuild/rollup.

Use when bundling JavaScript/TypeScript code with Bun's fast bundler. Covers building for different targets, tree-shaking, code splitting, and optimization strategies.

Bun's bundler is a fast JavaScript/TypeScript bundler built on the same engine as Bun's runtime. It's an esbuild-compatible alternative with native performance.

Build production-grade CLI tools with Bun. Reference implementation covering argument parsing patterns (--flag value, --flag=value, --flag), dual markdown/JSON output, error handling, subcommands, and testing. Use when building CLIs, designing argument parsing, implementing command structures, reviewing CLI quality, or learning Bun CLI best practices.

Generate optimized Docker images for Bun applications. Use when deploying to containers, minimizing image sizes, setting up CI/CD pipelines, or deploying to Kubernetes.

Set up high-performance development servers with Hot Module Replacement. Use when creating dev servers for web apps, setting up React Fast Refresh, or configuring API servers with live reload.

Use for Docker with Bun, Dockerfiles, oven/bun image, containerization, and deployments.

Use when integrating Drizzle ORM with Bun's SQLite driver for type-safe schema definitions and migrations.

bun-expert

Use for Bun file I/O: Bun.file, Bun.write, streams, directories, glob patterns, metadata.

Use when building APIs with Hono framework on Bun, including routing, middleware, REST APIs, context handling, or web framework features.

Use when implementing hot reloading with Bun (--hot, --watch), HMR, or automatic code reloading during development. Covers watch mode, hot mode, and HTTP server reload.

Use when building HTTP servers with Bun.serve, handling requests/responses, implementing routing, creating REST APIs, or configuring fetch handlers.

Use when migrating from Jest to Bun's test runner, import compatibility, mocks, and config.

Evaluate JavaScript at bundle time and inline results. Use when optimizing compile-time code generation, embedding files, inlining environment variables, or executing code during the bundling process.

Run Next.js applications with Bun for faster development and builds.

Use when running Nuxt 3 with Bun runtime, building Vue/Nuxt apps with Bun, or configuring Nuxt projects to use Bun for development and production.

Bun package manager commands (install, add, remove, update), workspaces, lockfiles, npm/yarn/pnpm migration. Use for dependency management with Bun.

Use when getting started with Bun, installing Bun, initializing projects, or configuring bunfig.toml. Invoke for Bun setup, installation issues, or project scaffolding questions.

Bun runtime patterns and best practices. Package management, bundling, testing, scripts. Use when working with Bun as the JavaScript runtime.

Bun shell scripting with Bun.$, Bun.spawn, subprocess management. Use for shell commands, template literals, or command execution.

Use for bun:sqlite, SQLite operations, prepared statements, transactions, and queries.

Use when building or running SvelteKit apps on Bun, including SSR, adapters, and Bun-specific APIs

TanStack Start full-stack React framework with Bun runtime. Use for TanStack Router, server functions, vinxi, or encountering SSR, build, preset errors.

Use for bun:test syntax, assertions, describe/it, test.skip/only/each, and basic patterns.

Use for test coverage with Bun, --coverage flag, lcov reports, thresholds, and CI integration.