Total 50,676 skills
Showing 12 of 50676 skills
Linting and formatting for Megatron-LM. Covers running autoformat.sh, tools (ruff, black, isort, pylint, mypy), and code style rules.
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.
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 creating, redesigning, critiquing, reducing, polishing, hardening, or making design decisions for a user-facing interface, brand surface, product UI, component, dashboard, flow, app shell, onboarding, empty state, or visual system. Applies Mies van der Rohe-inspired restraint, the Interface Craft workflow, and anti-generic design discipline. Not for backend-only work.
Generate Chinese body illustrations in Ian's style. It is used for tasks such as creating "weird", "Xiaohei", "hand-drawn", "body illustration", "article illustration", "illustration suggestion", "shot list", "remove title/modify image" requested by users for Chinese articles, posts, blogs, Notion documents, workflow documents, methodologies, processes, structures, states, metaphors or viewpoints; the default visual style adopts Xiaohei IP, pure white hand-drawn style, a small amount of red, orange and blue annotations, and a concise, fresh yet whimsical visual style.
Find Earth2Studio models, data sources, and examples for a weather/climate use case. Do NOT use for writing inference code, downloading data, or installation.
Create and modify NeMo AutoModel training and evaluation recipes, including YAML structure, builders, and execution flow.
Stage 1 of Clinical ASR Flywheel. Use when bootstrapping a cycle: NVCF+MW disclosure, NVIDIA_API_KEY check, deps install, TTS+ASR smoke test.
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.
Semi-automated design quality review for Flows apps. Runs concrete repo probes (grep, lint, build) to propose a draft 1–5 score for each of the official 10 quality-guidelines questions from docs.cognite.com/cdf/flows/guides/quality-guidelines, then asks the user to confirm or override each score. Still requires the user to walk their tasks end-to-end in the running app (Step 2) since navigation and clickability feel cannot be measured statically. Writes reviews/design-review/feedback-round-<N>/design-review-report.md with an overall average and prioritized fix lists. Use when the user asks to run a Flows design review, run the design quality assessment, or run flows-design-review. Must be run AFTER flows-code-review reaches 0 Must Fix and BEFORE flows-external-app-submit.
Resume the most recent agent session for the current working directory. Use when the user says "where were we", "resume", "handoff", "pick up where I left off", or starts a session with no fresh context.
Inspects sandbox health, traces agent behavior, and diagnoses problems. Use when monitoring a running sandbox, debugging agent issues, or checking sandbox logs. Trigger keywords - monitor nemoclaw sandbox, debug nemoclaw agent issues.