Skill catalog

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

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.

Execute approved PlanetScale changes end-to-end without per-step approval when the operator has explicitly acknowledged the risk. Defines the risk-acknowledgment contract, scoped autonomy levels, sensible execution orde…

Use when adding or fixing Roblox translation: localization tables, auto-translation, locale-specific content, or region detection.

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…

Configure config targeting rules to control which variations serve to different users. Enable percentage rollouts, attribute-based rules, segment targeting, and guarded rollouts.

Diagnose and fix browser, preview, or Electron export/download failures, especially image export issues involving Save As, Blob/Data URLs, the File System Access API, createWritable failures, and 0 KB files.

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.

Render Mermaid diagrams as SVG and PNG using the Beautiful Mermaid library. Use when the user asks to render a Mermaid diagram.

When the user wants to plan, create, or market a podcast. Also use when the user mentions "podcast," "podcast strategy," "podcast SEO," "show notes," "podcast distribution," "Spotify podcast," "Apple Podcasts," "podcast…

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 vi…

Experiment with configs by creating and managing variations. Helps you test different models, prompts, and parameters to find what works best through systematic experimentation.

Query the user's LLM Wiki knowledge base (the LLM Wiki desktop app at 127.0.0.1:19828 — NOT Obsidian, Notion, Apple Notes, Logseq, or any other PKM tool). Trigger ONLY when the user explicitly names LLM Wiki, says 'my w…

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.

Help users create technical roadmaps. Use when someone is planning engineering work, prioritizing tech debt, building architecture roadmaps, or aligning technical and product strategy.

Diagnoses and safely reclaims macOS disk space: caches, logs, app remnants, large/duplicate files, Docker/OrbStack, Chromium code-sign clones, developer caches. Use when a Mac is low on storage, shows “Caching needs mor…

Expert guidance for browser automation using Puppeteer with best practices for web scraping, testing, screenshot capture, and JavaScript execution in headless Chrome.

Design search — query input, zero results, refinement, and result presentation. Use when users retrieve rather than browse. For browse structure, use `navigation-patterns`.

Generate idiomatic Typst (.typ) code, edit and troubleshoot Typst documents and projects, and answer Typst syntax/reference questions. Use when working with .typ files or when the user explicitly asks for Typst document…

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

Design the first-run experience — activation path, progressive disclosure, and time to first value. Use for a user's very first session. For the mechanics of the signup form itself, use `form-design`.

Guide for setting up LaunchDarkly projects in your codebase. Helps you assess your stack, choose the right approach, and integrate project management that makes sense for your architecture.

Create a comprehensive brand standards document — covering logo usage, color, typography, voice, messaging, and application rules. Use when the user says "brand guidelines", "brand standards", "brand book", "style guide…

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

Turn any horizontal or square motion video into a 1080 x 1920 Instagram Reel or TikTok that uploads cleanly. Headline and logos inside the safe zone, H.264, yuv420p, limited colour range, bt709, a silent audio track whe…

Semantic Design System Skill for Google Stitch. Generates agent-friendly DESIGN.md files that enforce premium, anti-generic UI standards — strict typography, calibrated color, asymmetric layouts, perpetual micro-motion,…

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

Turn the approved plan into ordered working build steps, then build the app step by step — verifying and committing each one — in learn mode or fast mode. Use after the planning skills, and again whenever a build sessio…

Update, archive, and delete LaunchDarkly configs and their variations. Use when you need to modify config properties, change model parameters, update instructions or messages, archive unused configs, or permanently remo…

Use this skill when the user requests to generate, create, write, or draft a newsletter, email digest, weekly roundup, industry briefing, or curated content summary. Supports topic-based research, content curation from…

Attach judges to config variations for automatic LLM-as-a-judge evaluation. Create custom judges, configure sampling rates, and monitor quality scores.

Run a validated Admin GraphQL operation against a specific store using Shopify CLI. Use this when the user wants an executable store workflow, not just the query or mutation text. If the answer should include `shopify s…

Prepares tax materials as a two-link chain — month-end-prep confirms the books are closed and reconciled first, then tax-season-organizer calculates the quarterly estimated payment or builds the year-end 1099-NEC list a…

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.

Find or sharpen the project idea and write the scope doc. The first and most important planning conversation — a focused flipped-interaction interview that pulls the idea out of the learner's head, then cuts it down to…

Turn the approved scope into a complete product definition — the core journey, every behavior, states and edge cases, and a firm proof-of-concept boundary. No code talk. Run after 2-scope.

Turn the approved PRD into a technical blueprint the build can follow — stack, where it runs, components, data, file structure — calibrated to the learner and sized to a proof of concept. The last planning step before c…

Finish the Build With AI Basics hackathon—verify the proof of concept, prepare the required short demo video and public GitHub repository, and write your own Devpost submission. Run after 5-build, its final review, and…

Create banners using AI image generation. Discuss format/style, generate variations, iterate with user feedback, crop to target ratio. Use when user wants to create a banner, header, hero image, cover image, GitHub bann…

Generate a concise 4-5 page equity research earnings preview for a single company. Analyzes the most recent earnings transcript, competitor landscape, valuation, and recent news to produce a professional HTML report.

Apply the Law of Proximity — spatial closeness groups elements more strongly than any other cue. Use when spacing alone must carry grouping. For grouping via containers use `law-of-common-region`; via shared appearance…

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.

Apply a refined Scandinavian visual system with a neutral black-and-white foundation, restrained sans-serif typography, purposeful product imagery, generous spacing, clear page chapters, and minimal decoration. Use when…

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

Begin Build With AI: Basics, the Devpost learning hackathon. Checks you're in a fresh project folder, introduces flipped interaction, learns about your idea and background, and writes the learner profile that every late…

Analyzes sales data from PayPal and QuickBooks to find top performers and slow movers, layers in seasonality, and produces a prioritized 30-day content brief: what to push, what offers to run, what to hold. Strategic ou…

Datadog docs lookup using docs.datadoghq.com/llms.txt and linked Markdown pages.

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

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

Search and ask questions about coding agent session history across Claude Code, Codex, and Cursor. Use when asking what was worked on, what was tried before, how a problem was investigated across sessions, what happened…