Skills directory

Expert in web animations, transitions, and motion design using Framer Motion and CSS

Monitor management - list, search, file-based create, and alerting best practices.

Control SideFX Houdini from the shell via Flue - a Python bridge to hou without an MCP server.

Run Megatron-LM (MLM) and Megatron Bridge training with mock or real data. Covers correlation testing, available recipes, and multi-GPU examples.

Practical guidance for training MoE VLMs in Megatron Bridge. Compares FSDP and 3D-parallel approaches, using rounded lessons from Qwen3-VL, Qwen3-Next, and other multimodal experiments.

Builds UI from a Figma file or a design image so it matches the design, using your project's existing tokens and components.

Operational guide for choosing and combining parallelism strategies in Megatron Bridge, including sizing rules, hardware topology mapping, and combined parallelism configuration.

Add a new cuTile GPU kernel operator to TileGym. Covers dispatch registration in ops.py, cuTile backend implementation, __init__.py exports, test creation, and benchmark in tests/benchmark. Use when adding, creating, or implementing a new c

Turbo pipeline operations reference — lifecycle commands (pause, resume, restart, delete), pipeline states, checkpoint behavior, streaming vs job-mode differences, CLI syntax for `inspect`/`logs`, TUI shortcuts, and error pattern lookup. Tr

Find businesses, leads, emails, reviews, ratings, and contact details from Google Maps. Use for requests such as "find dentists in Berlin", "scrape Google Maps", "get local business leads", or "collect Google Maps reviews". Runs the open-so

Convert single-node scripts to multi-node Slurm sbatch jobs and debug common multi-node failures. Covers srun-native vs uv run torch.distributed approaches, container setup, NCCL timeouts, OOM sizing for MoE models, and interactive allocati

Validate and use packed sequences and long-context training in Megatron-Bridge, including offline LLM packing, collate-time VLM packing, Energon online packing, and CP constraints.

Publish presentations and web content to GitHub Pages. Converts PPTX, PDF, HTML, or Google Slides to a live GitHub Pages URL. Handles repo creation, file conversion, Pages enablement, and returns the live URL. Use when the user wants to pub

Use this skill when the user wants to deploy, run, debug, tear down, or call the REST API of the RTVI-CV 2D detection / tracking microservice. Trigger when the user says things like 'deploy rtvi-cv', 'start warehouse 2d', 'add a stream', 'c

Translates an image (or a set of image references — screenshots, mockups, Figma URLs, live websites) into two mirrored design-system artifacts: `docs/design.md` (YAML tokens + prose, following Google's open [design.md](https://github.com/go

Evidence-gated workflow for MoE performance optimization in Megatron Bridge. Covers measurement contracts, the Three Walls framework, parallel folding, profiling, matched A/B tuning, and final validation.

Use this skill when deploying standalone RT-VLM dense captioning or calling its REST API (uploads, captions, streams, chat-completions, Kafka). Not for VSS profile deploy or video-search ingestion.

Next.js 16 Cache Components - PPR, use cache directive, cacheLife, cacheTag, updateTag

Use this skill when deploying, operating, or integrating the VSS 3.2 GA RT-Embed Video Embedding microservice. Covers Docker Compose bring-up, GPU and storage prerequisites, the `/v1` REST API (file uploads, text and video embeddings, live

Uses the Adaptyv Bio Foundry API and Python SDK to design protein characterization experiments, estimate costs, submit sequences, monitor laboratory progress, and retrieve results. Applies to Adaptyv Foundry, its target catalog, binding scr

Plans, configures, inspects, restarts, and analyzes bounded FluidSim computational-fluid-dynamics simulations with explicit numerical-validity and HPC safety checks. Use for FluidSim solver selection, parameter review, FFT/MPI setup, output

Runs and analyzes molecular dynamics simulations with OpenMM and MDAnalysis. Sets up protein/small molecule systems, defines force fields, runs energy minimization and production MD, and analyzes trajectories (RMSD, RMSF, contact maps, free

Validate and use CPU offloading in Megatron Bridge, including layer-level activation offloading and fractional optimizer state offloading with HybridDeviceOptimizer.

Design UIs in Pencil (.pen files) and generate production code from them. Use when working with .pen files, designing screens or components in Pencil, or generating code from Pencil designs. Triggers on tasks involving Pencil, .pen files, d

Performs bulk RNA-seq differential expression analysis with PyDESeq2, including count validation, formula designs, explicit contrasts, Wald tests, FDR correction, coefficient-matched LFC shrinkage, and result visualization. Use for PyDESeq2

Validate and use MoE expert-parallel communication overlap in Megatron-Bridge, including overlap_moe_expert_parallel_comm, delay_wgrad_compute, and flex dispatcher backends such as DeepEP and HybridEP.

Adopt a typed .spec.ts for an existing hand-written CLAUDE.md — start from the file you already have, non-destructively

Long-context MoE training guidance for Megatron Bridge. Covers CP sizing, selective recompute, dispatcher choices, and practical patterns from DSV3, Qwen3, and Qwen3-Next long-context experiments.

Scaffolds an xUnit integration test project targeting Oracle in .NET solutions. Creates the test project, transaction-rollback base class, and seed data manager. Use only during Phase 3, before writing Oracle baseline integration tests. Do

Use to call the VIOS REST API (sensor list, timelines, clip extraction, snapshots, add/delete sensors and streams). Not for VLM inference or search.

Create or update standardized object-oriented component documentation using a shared template plus mode-specific guidance for new and existing docs.

Use to run AutoMagicCalib on local MP4s, RTSP, or the bundled sample dataset, and to deploy vss-auto-calibration when needed. Do not use for non-AMC calibration or runtime analytics.

Use to deploy the vss-video-analytics-api REST service standalone (config-source, data-log bind, Elasticsearch, optional Kafka). Not for full warehouse deploy.

Use this skill when the user asks about Goldsky Mirror pipelines — creating, deploying, operating, or troubleshooting Mirror. Triggers on: 'Mirror pipeline', 'goldsky pipeline apply', 'sync subgraph to database', 'mirror vs turbo', 'direct

MoE expert-parallel communication overlap in Megatron Bridge. Covers dispatch/combine overlap, flex dispatcher backends, and expert wgrad scheduling.

Use for VSS alert workflows — real-time monitoring, Alert-Bridge subscriptions, Slack notifications, incident queries, camera onboarding. Not for non-alert analytics.

Use this skill when reading video-analytics metrics, incidents, alerts, and sensor data via the VA-MCP server (port 9901). Not for live VLM or incident-range narrative reports.

Diagnoses, predicts, and mitigates node disruptions during Compute Engine host maintenance and hardware or software maintenance events for GPU and TPU workloads on GKE. Use when diagnosing node disruptions, predicting host maintenance event

Control Adobe Premiere Pro from the shell via Flue - ExtendScript bridges without an MCP server.

Search and read official Coralogix platform documentation using **`cx docs search`** and **`cx docs fetch`**. Use when the user asks how Coralogix features work, how to configure or use the UI, set up integrations (OpenTelemetry, agents, co

Representative, point-in-time MoE training playbooks by hardware and model family. Use them as candidate seeds, then revalidate the exact runtime, semantics, topology, and steady-state throughput.

Infrastructure-as-Code patterns for data engineering using Terraform to provision AWS resources (S3, EC2, IAM)

Work with any Upstash product, SDK, or tool, including serverless Redis (caching, sessions, leaderboards, key-value storage), Ratelimit (rate limiting and throttling), QStash (message queue, cron schedules, background jobs), Workflow (durab

Diagnose and fix broken Goldsky Mirror pipelines. Use this skill whenever a user has a Mirror pipeline that is failing, stuck, terminated, won't start, is in a restart loop, or is blocked by an in-flight request. Also use when the user ment

Operational guide for enabling hierarchical context parallelism in Megatron-Bridge, including config knobs, code anchors, pitfalls, and verification.

Build and sharpen a project's domain model. Use when the user wants to pin down domain terminology or a ubiquitous language, record an architectural decision, or when another skill needs to maintain the domain model.

Resiliency features in Megatron Bridge including fault tolerance, straggler detection, in-process restart, preemption, and re-run state machine.

Always load this skill whenever the conversation is about Goldsky Compose (the offchain-to-onchain TypeScript framework for oracles, keepers, circuit breakers, and cross-chain automation) — no matter what the user wants to do with it. That

Give your agents capabilities through tools (function calling). Helps you identify what your agent needs to do, create tool definitions, and attach them to config variations.

Control Autodesk desktop apps - 3ds Max and friends - from the shell via Flue, without an MCP server.