“data engineering”

Use when implementing or reviewing frontend architecture, component variants, data boundaries, localization, preferences or SSR hydration while preserving…

Practical guide for building production ML systems based on Chip Huyen's AI Engineering book.

ICM-based zero-to-verified engineering workflow.

A CPU performance engineering brain: a vetted reading list, benchmarks and cited source passages

Use when reviewing a vd-studio pull request as the automated AI PR reviewer (OpenHands pr-review plugin) — judging test coverage for a diff, structuring the…

Master context engineering for AI agent systems.

A/B testing infrastructure, feature flags (LaunchDarkly, Unleash), experimentation platforms, PLG patterns, and funnel optimization.

Use when designing, building, reviewing, or polishing user interfaces, motion, component behavior, interaction details, and product-feel across any frontend…

Develop and deploy Lakeflow Jobs on Databricks via DABs, Python SDK, or the CLI.

Craft rules for web UI polish (press states, origins, transforms, clip-path, gestures, performance, accessibility) and a Before/After review table.

Reference manual for Python project layout, uv dependencies, static checks, tests, packaging, and CI conventions.

Develop and deploy Lakeflow Jobs on Databricks via DABs, Python SDK, or the CLI.

Inject controlled failures to test system resilience, validate recovery paths, and build reliability confidence.

Collect immutable, timestamped ICAIRE LinkedIn and X post-level snapshots when refreshing Audience Growth Engine source data.

Orchestrates substantial frontend and UI work with audit-first context, product-aware design direction, shadcn-aware component engineering, Storybook state…

Chaos engineering: hypothesis-driven fault injection to surface weakness before users do.

Govern product and software work with V.I.B.E.

Use when the user says "close issue [ID]", "close [ID]", "finish closeout", or when a Linear issue already has a review-ready PR and this repository needs the…

Run the marketing-engineer operating system — one shared brain, ten agents, a review queue, and a weekly loop — on top of Cogny's MCPs.

Use for architecture, system design, code review, debugging, refactoring, technical debt, data models, testing strategy, performance, reliability, or…

Umbrella skill for distinctive frontend design, UI polish, Apple-style fluid interaction, animation vocabulary lookup, and strict motion review.

Expert API design and delivery: resource modeling, versioning, consistent error envelopes, pagination/filtering, idempotency, OpenAPI/contracts, and boundary…

Use when asked to implement, fix, build, or work on an existing Linear issue in this repository, and coding should stop before PR creation

Understanding how a compiled, obfuscated, packed or virtualized target works: binaries and firmware, Android APKs and iOS IPAs, .NET and JVM assemblies, WASM…