NeVibeCode · 2,385 items
Skills for AI and ML
Skills for AI and ML: what each one does, an install command and example prompts.
nemo-mbridge-multi-node-slurm skill Converts single-node launches into multi-node Slurm jobs and helps investigate NCCL, launch, and memory failures.
CX Codex +1
1,800installs
nemo-mbridge-perf-sequence-packing skill A skill for configuring packed sequences and long-context training in Megatron-Bridge: offline LLM packing, collate-time VLM packing, Energon online packing.
CX Codex +1
1,800installs
nemo-mbridge-perf-moe-vlm-training skill Practical guidance for training MoE VLMs in Megatron Bridge. It helps configure FSDP or 3D parallelism and debug OOM failures during multimodal training runs.
CX Codex +1
1,800installs
nemo-mbridge-mlm-bridge-training skill This skill runs Megatron-LM and Megatron Bridge training, compares loss curves, and helps investigate divergence after code changes.
CX Codex +1
1,800installs
nemo-mbridge-perf-parallelism-strategies skill Picks TP, PP, CP, EP and DP degrees for Megatron Bridge training runs, and traces an OOM or slowdown back to a parallelism config change.
CX Codex +1
1,800installs
nemo-mbridge-perf-activation-recompute skill Guides activation recomputation setup in Megatron Bridge to resolve GPU memory OOMs during LLM training. Balances memory savings against extra recomputed operations.
CX Codex +1
1,800installs
nv-generate-vae-finetune skill Stages and runs NV-Generate-CTMR MAISI VAE finetuning from CT or MRI NIfTI datalists. Use it to validate a dataset before starting GPU training.
CX Codex +1
1,800installs
nv-segment-ct-finetune skill Finetunes NV-Segment-CT VISTA3D on CT NIfTI image and label datasets, with a fixed-channel softmax path and optional MLflow tracking.
CX Codex +1
1,800installs
nv-reason-cxr skill Runs NV-Reason-CXR-3B smoke tests on chest X-ray images. Useful for verifying pipeline command shapes and parsing JSON reasoning outputs.
CX Codex +1
1,800installs
nv-segment-ctmr skill Runs NV-Segment-CTMR on CT or MRI NIfTI volumes and writes a label map plus a JSON report. Not meant for clinical interpretation.
CX Codex +1
1,800installs
nv-generate-mr skill Generates synthetic body MRI volumes using NV-Generate-CTMR rflow-mr. Useful for staging T1 MRI volume synthesis without paired segmentations.
CX Codex +1
1,800installs
nv-segment-ct skill Runs VISTA3D on CT NIfTI volumes and writes a label map plus a JSON report. Built for research runs, not clinical use.
CX Codex +1
1,800installs
nv-generate-mr-brain-finetune skill Finetunes the NV-Generate-CTMR MR-Brain v1 diffusion model on your T1, T2, FLAIR, SWI or MRA NIfTI volumes. A preflight pass runs first, without a GPU.
CX Codex +1
1,800installs
nv-generate-mr-brain skill Generates synthetic T1, T2, FLAIR, SWI, or MRA brain MRI volumes with NV-Generate-CTMR MR-Brain v1. It provides test NIfTI volumes without clinical scans.
CX Codex +1
1,800installs
mongodb-search-and-ai skill Guides search implementation in MongoDB Atlas, from full-text matching to vector search. Configures indexes and queries tailored to your schemas.
CX Codex +1
5,800installs
acreadiness-policy
official skill Guides the creation, configuration, and execution of AgentRC readiness policies. Useful for setting custom scoring weights, strict thresholds, and CI gating.
133installs
add-dictation skill This skill wires Claude speech recognition into your own app: a mic button, live captions, or transcripts of audio you already have.
CX Codex +1
324installs
geo-content-optimizer skill Audits and rewrites a page so ChatGPT, Perplexity, Gemini and AI Overviews are more likely to quote it. Handy when search clicks are sliding.
CX Codex +1
1,700installs
eval-audit skill Audits LLM evaluation pipelines to uncover unvalidated judges, vanity metrics, and flawed error analysis. Best used when reviewing existing evals.
CX Codex +1
1,000installs
error-discovery skill A skill for interactive error analysis on a dataset of LLM outputs: it builds a review UI, picks diverse samples and helps organize failure modes.
CX Codex +1
1,000installs
add-read-aloud skill Builds Grok text-to-speech into an existing app, for read-aloud controls, automatic playback, or spoken page content.
CX Codex +1
320installs
add-voice skill Adds two-way Grok voice conversations to an app. Use it when replacing an STT-LLM-TTS chain or an OpenAI Realtime integration.
CX Codex +1
319installs
aeo skill Audits and restructures content so LLMs cite it as an authoritative source. Useful for teams building content for AI-first search audiences.
459installs
generate-synthetic-data skill A skill that builds varied synthetic test queries for LLM pipeline evaluation when real data is sparse.
CX Codex +1
984installs
results-analysis skill Turns ML experiment artifacts into a strict analysis bundle: statistics, real figures, report. Built for checking significance, not for writing prose.
CX Codex +1
542installs
tao-finetune-huggingface-model skill Fine-tunes HuggingFace CV, VLM, and LLM models on local NVIDIA GPUs inside an NGC PyTorch container when no dedicated TAO model skill matches.
CX Codex +1
1,700installs
hsb-setup skill Sets up a Holoscan Sensor Bridge environment by connecting to a devkit, building a container, and checking board connectivity. Use it for first HSB demo bring-up.
CX Codex +1
1,700installs
dockkit skill A skill for the DockKit framework: write Swift code that drives motorized docks and gimbals so the iPhone physically follows a subject.
CX Codex +1
3,000installs
build-review-interface skill Builds a custom browser-based annotation interface to review LLM traces and record human feedback. Useful when evaluating models and collecting labeled datasets.
CX Codex +1
970installs
evaluate-rag skill Guides separate evaluation of RAG retrieval and generation, metric selection, and document chunking tests.
CX Codex +1
970installs
agent-skill-stack
official skill Finds a small compatible set of AI Agent Skills for a multi-step goal. Use it to audit installed Skills or work out what a project still needs.
128installs
marimo-notebook skill Instructs coding assistants to format marimo reactive notebooks in pure Python files with PEP 723 dependencies and CLI support.
CX Codex +1
5,900installs
bencium-aeo skill This skill prepares content for AI search citations, FAQ schemas, and evidence panels. Use it to assess whether pages are ready for LLM extraction.
CX Codex +1
3,300installs
langgraph-decision-models skill A skill that swaps LLM calls made only to extract a routing decision for typed questions that return probabilities.
CX Codex +1
1,600installs
chat-with-anyone skill The skill finds a person's speech in public video, pulls a clean reference clip and voices replies in that voice. A second mode builds a voice from a photo.
CX Codex +1
2,100installs
axiom-vision skill A skill for Vision framework work: subject segmentation, pose detection, OCR, barcodes. Useful when you build a recognition feature on Apple platforms.
CX Codex +1
1,800installs
tao-run-on-slurm skill Submit TAO jobs to a remote SLURM GPU cluster over SSH, with Pyxis/Enroot containers. Use it when training or inference needs cluster storage on Lustre.
CX Codex +1
1,600installs
tao-run-on-kubernetes skill Turns a TAO spec-bundle into a Kubernetes Job and submits it with plain kubectl. For training runs and inference on EKS, GKE, AKS or an on-prem GPU cluster.
CX Codex +1
1,600installs
tilegym-improve-cutile-kernel-perf skill Systematically profiles, tunes, and benchmarks cuTile GPU kernels in TileGym. Runs iterations on real hardware to lower latency while preserving accuracy.
CX Codex +1
1,600installs
tilegym-monkey-patch-kernels-to-transformers skill This skill wires TileGym kernels into Hugging Face Transformers models by swapping components before model creation. Use it to integrate existing kernels or build new cuTile ones.
CX Codex +1
1,600installs
1,001–1,040 of 2,385
