Overview CLI FAQ

Agent Skills 排行榜 · 关键词 + 语义搜索

按 / 聚焦搜索框
正在使用 AI 进行语义搜索...
29,283
总 Skills
230.2M
总安装量
2,818
贡献者
# Skill 仓库 描述 安装量
9851 tao-run-on-local-docker nvidia/skills
Local Docker Single-node execution platform that runs TAO jobs as named Docker containers on a Docker daemon. The daemon can be local to the agent host or remote through DOCKER_HOST=ssh://user@host / a Docker context. It is useful for development, debugging, small runs, and workflows where a local coding agent submits jobs to a remote GPU box. Use local Docker when the data is local to the Docker host or accessible through mounted volumes/cloud credentials. Do not use it for remote cluster sched...
 1.6K
9852 convex-security-audit waynesutton/convexskills
Convex Security Audit Comprehensive security review patterns for Convex applications including authorization logic, data access boundaries, action isolation, rate limiting, and protecting sensitive operations. Documentation Sources Before implementing, do not assume; fetch the latest documentation: Primary: https://docs.convex.dev/auth/functions-auth Production Security: https://docs.convex.dev/production For broader context: https://docs.convex.dev/llms.txt Instructions Security Audit Areas...
 1.6K
9853 dingtalk-message breath57/dingtalk-skills
钉钉消息技能 负责钉钉消息发送的所有操作。本文件为 策略指南 ，仅包含决策逻辑和工作流程。完整 API 请求格式见文末的 references/api.md 查阅索引。 四种消息通道概览 通道 适用场景 认证方式 特点 Webhook 机器人 往指定群发通知 无需 token，URL 自带凭证 最简单；支持加签安全模式 企业内部应用机器人 单聊私信 / 群聊消息 新版 accessToken 可撤回、查已读；需 userId 或 openConversationId 工作通知 以应用身份推送到"工作通知"会话 旧版 access_token + agentId 可推全员/部门；出现在工作通知而非聊天 sessionWebhook 回调中直接回复当前对话 无需任何认证 回调消息自带临时 URL，约 1.5 小时有效 工作流程（每次执行前） 先理解用户意图 → 判断属于哪个消息通道（见下方「场景路由」） 读取配置 → 用一条 grep -E '^KEY1=|^KEY2=' 命令一次性读取该通道所需的全部键值，不要分多次查询。（跨会话保留，所有 dingtalk-skills 共用同一文件）...
 1.6K
9854 tao-generate-video-reasoning-annotations nvidia/skills
Video Reasoning Annotation Pipeline Generate Chain-of-Thought training datasets from videos by producing multi-level captions, structured descriptions, and QA pairs (MCQ, binary, open-ended) with step-by-step reasoning traces. Domain-agnostic by default — customize prompts for any video domain. Purpose Transform raw videos into CoT Q&A training data for video understanding models. VLMs (e.g., Gemini, Qwen) act as "teacher" annotators: Steps 0–1 require the model to see the video (VLM calls); Ste...
 1.6K
9855 tao-run-automl nvidia/skills
TAO AutoML Run automated hyperparameter optimization for a TAO model by combining: The selected model skill under skills/models/<network>/ . The selected platform skill under skills/platform/<platform>/ . AutoMLRunner , which generates recommendations, launches train jobs, extracts metrics, and feeds results back to the optimizer. Do not launch until model metadata, platform preflight, data visibility, credentials, image choice, and compute shape are all proven. Reference Map Show more Installs ...
 1.6K
9856 frontend-design customware-ai/skills
This skill guides creation of distinctive, production-grade frontend interfaces that avoid generic "AI slop" aesthetics. Implement real working code with exceptional attention to aesthetic details and creative choices. The user provides frontend requirements: a component, page, application, or interface to build. They may include context about the purpose, audience, or technical constraints. Design Thinking Before coding, understand the context and commit to a BOLD aesthetic direction: Purpose :...
 1.6K
9857 tao-finetune-clip nvidia/skills
CLIP Contrastive Language-Image Pre-training model for zero-shot and fine-tuned image classification, image-text retrieval, and embedding extraction. Fine-tuning adapts CLIP's shared image-text embedding space to domain-specific image-caption data. No default NGC pretrained checkpoint is required for spec construction, but unset checkpoint behavior is action-specific. In the validation-fixes PyTorch image, export.checkpoint: null exports the selected CLIP architecture and may initialize weights ...
 1.6K
9858 tao-list-capabilities nvidia/skills
TAO Skill Bank Capabilities Use this skill when the user asks what tao-skill-bank can do, asks for plugin capabilities, asks which application or data workflows are available, asks which models are supported, or asks what models are capable with AutoML. Quick Start Run scripts/list_tao_capabilities.py for general capability questions, or scripts/list_tao_models.py for model/action and AutoML support questions. Capability Answers For a general capabilities answer, run the packaged helper: ${TAO_S...
 1.6K
9859 tao-port-huggingface-model nvidia/skills
TAO-HF Integration Skill Integrate a HuggingFace (HF) Computer Vision model into the NVIDIA TAO Toolkit ecosystem. Work the phases iteratively — not purely linearly — via a build → test → debug → fix → retest loop at every step: when something fails, diagnose and fix before moving on; when it passes, move to the next step. Show more Installs 577 Repository nvidia/skills GitHub Stars 1.9K First Seen Jun 8, 2026 Security Audits Gen Agent Trust Hub Pass Socket Pass Snyk Fail
 1.6K
9860 tao-convert-dataset-format nvidia/skills
Convert a TAO DAFT Dataset Quick start tao-daft convert < source-format > < target-format > --path < input > --output < output > Source and target are positional subcommands; --path and --output are flags. Discover the supported formats and per-pair flags from the leaf --help (see "CLI conventions" below). Show more Installs 579 Repository nvidia/skills GitHub Stars 1.9K First Seen Jun 8, 2026 Security Audits Gen Agent Trust Hub Pass Socket Pass Snyk Pass
 1.6K
9861 tao-train-image-classification nvidia/skills
Classification PyT PyTorch image classification. Supports a wide range of backbones (FAN, EfficientNet, ResNet, etc.) with distillation and quantization for deployment. Set model.backbone.pretrained_backbone_path for backbone weights or train.pretrained_model_path for full model. For TAO Deploy TensorRT actions ( gen_trt_engine , TensorRT evaluate , and TensorRT inference ), read references/tao-deploy-image-classification.md first. Deploy spec templates live in this skill's references/ folder wi...
 1.6K
9862 tao-train-ocrnet nvidia/skills
OCRNet OCRNet for scene text recognition. Recognizes text content from cropped text region images. Supports CTC and attention-based decoders. Set train.pretrained_model_path for pretrained OCR weights. For TAO Deploy TensorRT actions ( gen_trt_engine , TensorRT evaluate , and TensorRT inference ), read references/tao-deploy-ocrnet.md first. Deploy spec templates live in this skill's references/ folder with the spec_template_deploy_*.yaml prefix. Dataclass Schemas Generated TAO Core schemas are p...
 1.6K
9863 powerpoint-ppt practicalswan/agent-skills
PowerPoint Presentation Workflows Tech Stack Target / Version: PowerPoint current desktop or web releases and python-pptx automation. Use this skill when a .pptx deck is the output and slide composition matters. Leverage native parallel subagent dispatch and 200k+ context windows where available. Current MCP Reality Presentation MCP tooling is host-dependent. Some clients expose Office presentation tools directly, while others do not. Do not assume stable public tool names. If the current client...
 1.6K
9864 day1-onboarding ai-native-camp/camp-2
Day 1: Onboarding 이 스킬이 호출되면 아래 STOP PROTOCOL 을 반드시 따른다. STOP PROTOCOL — 절대 위반 금지 이 프로토콜은 이 스킬의 최우선 규칙이다. 아래 규칙을 위반하면 수업이 망가진다. 각 블록은 반드시 2턴에 걸쳐 진행한다 ┌─ Phase A (첫 번째 턴) ──────────────────────────────┐ │ 1. references/에서 해당 블록 파일의 EXPLAIN 섹션을 읽는다 │ │ 2. 기능을 설명한다 │ │ 3. references/에서 해당 블록 파일의 EXECUTE 섹션을 읽는다 │ │ 4. "지금 직접 실행해보세요"라고 안내한다 │ │ 5. ⛔ 여기서 반드시 STOP. 턴을 종료한다. │ │ ...
 1.6K
9865 adk-frontend botpress/skills
No SKILL.md available for this skill. View on GitHub
 1.6K
9866 tao-run-on-kubernetes nvidia/skills
Kubernetes Submits TAO container jobs as Kubernetes Jobs. Works on any cluster reachable via kubeconfig (EKS / GKE / AKS / on-prem) or in-cluster service account (when the SDK runs inside a pod). Single-pod by default; opt into multi-node distributed training via num_nodes > 1 (uses Indexed Job + headless Service, see Multi-node training below). Preflight Four checks: GPU host runtime ready, SDK installed, cluster reachable, GPU Operator/device plugin present. 0. GPU node host runtime. Run thi...
 1.6K
9867 tao-train-optical-inspection nvidia/skills
Optical Inspection Optical inspection for defect detection using Siamese networks. Compares image pairs to detect manufacturing defects, anomalies, or quality issues. Set train.pretrained_model_path for pretrained Siamese weights. For TAO Deploy TensorRT actions ( gen_trt_engine , TensorRT evaluate , and TensorRT inference ), read references/tao-deploy-optical-inspection.md first. The parent PyT container does not expose optical_inspection gen_trt_engine ; TensorRT engine generation is deploy-on...
 1.6K
9868 tao-generate-image-grounding nvidia/skills
Image Grounding Pipeline Turn (image, caption) pairs into per-image grounded annotations: cleaned captions, referring expressions with character spans, and pixel-space bounding boxes for each expression. A single VLM (Gemini or any OpenAI-compatible endpoint) handles both steps. Purpose Generate phrase-grounded training data for referring-expression and grounding models. The VLM acts as a "teacher" annotator: Step 0 extracts referring expressions from the caption while looking at the image; Step...
 1.6K
9869 tao-analyze-changenet-rca nvidia/skills
TAO ChangeNet Classification RCA Skill You are an expert investigator for NVIDIA TAO Visual ChangeNet classification experiments. Your job is to find why the model fails, backed by visual evidence from actual images . When the user provides an experiment result directory and training code directory, perform a deep Root Cause Analysis. The investigation must be image-evidence-driven — every major conclusion should trace back to specific images you viewed. Inputs Experiment result directory — cont...
 1.6K
9870 tao-train-action-recognition nvidia/skills
Action Recognition Action recognition from video sequences. Supports RGB, optical flow, and joint (multi-stream) input types for classifying temporal actions in video clips. Set model.pretrained_model_path for pretrained backbone weights. Dataclass Schemas Generated TAO Core schemas are packaged in schemas/<action>.schema.json , with schemas/manifest.json listing available actions. Each generated schema also emits references/spec_template_<action>.yaml from the schema top-level default field. Au...
 1.6K
9871 tao-run-inference-service nvidia/skills
TAO Inference Microservice Instructions To start an inference service: Collect required inputs (Section 1) and resolve the container image (Section 2). Build the job payload and inner command (Sections 3–4.1); use references/code-templates.yaml → job_payload_builder . Read skills/platform/<platform>/SKILL.md and start the container (Section 4.2). Write the service registry and poll readiness (Section 4.3); use references/code-templates.yaml → registry_write.<platform> and readiness_check . To se...
 1.6K
9872 tao-train-grounding-dino nvidia/skills
Grounding DINO Grounding DINO for open-set object detection. Combines DINO-style detection with BERT text encoder for language-guided detection. Detects objects described by text prompts without fixed class vocabulary. Set train.pretrained_model_path for full Grounding DINO weights or model.pretrained_backbone_path for backbone-only. For TAO Deploy TensorRT actions ( gen_trt_engine , TensorRT evaluate , and TensorRT inference ), read references/tao-deploy-grounding-dino.md first. Deploy spec tem...
 1.6K
9873 framer-motion dylantarre/animation-principles
Framer Motion / Motion Animation Guidelines You are an expert in Framer Motion (now Motion), React, and TypeScript. Follow these guidelines when creating animations. Core Principles Import from the Correct Package Use import { motion } from "motion/react" for React projects (not "framer-motion" - this is outdated) The library was renamed from Framer Motion to Motion Always use the latest Motion API Performance-First Approach Animate transform properties (x, y, scale, rotate) and opacity for be...
 1.6K
9874 funding-digest anthropics/financial-services
AI DISCLAIMER (MANDATORY): You MUST include the following disclaimer text in the powerpoint footer. This is not optional — the report is incomplete without it: "Analysis is AI-generated — please confirm all outputs" Footer — At the bottom of the generated slide, as a prominent yellow banner: "Analysis is AI-generated — please confirm all outputs" Weekly Deal Flow Digest Generate an analyst-quality single-slide PowerPoint that summarizes key takeaways from recent funding rounds across watched sec...
 1.6K
9875 tao-train-nvpanoptix3d nvidia/skills
NVPanoptix3D NVPanoptix3D for panoptic 3D scene reconstruction from posed RGB images. Produces 3D panoptic segmentation (semantic, instance, and panoptic masks) with occupancy completion. Built on VGGT backbone with Mask2Former-style head and 3D frustum reconstruction. Uses 2D and 3D stage checkpoints. Set train.checkpoint_2d and train.checkpoint_3d for staged initialization. Dataclass Schemas Generated TAO Core schemas are packaged in schemas/<action>.schema.json , with schemas/manifest.json li...
 1.6K
9876 fsi-strip-profile anthropics/financial-services
Workflow 1. Clarify Requirements Ask the user : Single-slide or multi-slide (3-4 slides)? Ask the user : Any specific focus areas or topics to emphasize? Only after user confirms , proceed to research 2. Research & Planning Data Sources: Primary : Company filings (BamSEC, SEC EDGAR - "Item 1. Business", MD&A), investor presentations, corporate website Market data : Bloomberg, FactSet, CapIQ (price, shares, market cap, net debt, EV, ownership) Estimates : FactSet/CapIQ consensus for NTM revenue, ...
 1.6K
9877 qdrant-performance-optimization qdrant/skills
Qdrant Performance Optimization There are different aspects of Qdrant performance, this document serves as a navigation hub for different aspects of performance optimization in Qdrant. Search Speed Optimization There are two different criteria for search speed: latency and throughput. Latency is the time it takes to get a response for a single query, while throughput is the number of queries that can be processed in a given time frame. Depending on your use case, you may want to optimize for one...
 1.6K
9878 tao-analyze-gaps-visual-changenet nvidia/skills
TAO VCN Classify Gap Analysis Skill You are an analyst for NVIDIA TAO VCN Classify (Visual Component Net) inference results. Your job is to identify the weakest samples per ground-truth label by measuring signed distance from the decision threshold in the wrong direction , then surface them for downstream augmentation or relabeling. This skill is intentionally lightweight. VCN's classify head is a single-score binary boundary (PASS vs NO_PASS by siamese_score ), so the analysis is computational,...
 1.6K
9879 tao-train-pose-classification nvidia/skills
Pose Classification Pose classification using ST-GCN (Spatial Temporal Graph Convolutional Network). Classifies skeleton sequences into action categories from pose keypoint data. Typically trained from scratch on skeleton data. The packaged PyTorch Pose Classification CLI supports dataset_convert , train , evaluate , export , and inference . dataset_convert is conditional: run it only when the input is raw DeepStream BodyPose JSON. If the dataset is already converted to TAO-ready .npy / .pkl fil...
 1.6K
9880 telegram-reader himself65/finance-skills
Telegram News Skill (Read-Only) Reads Telegram channels and groups for financial news and market research using tdl , a Telegram CLI tool. This skill is read-only. It is designed for financial research: reading channel messages, monitoring financial news channels, and exporting message history. It does NOT support sending messages, joining/leaving channels, or any write operations. Step 1: Ensure tdl Is Installed Current environment status: !`(command -v tdl && tdl version 2>&1 | head -3 || echo...
 1.6K
9881 build-loop-claude-code buildgreatproducts/builder-os
Claude Code Build Loop Quality-gated feature work: nothing ships on "it compiles" — every increment is built, reviewed, tested end to end, and fixed before the user hears "done." Source of work A plan file exists (roadmap, refactor plan, or task list with - [ ] checkboxes — search the repo): work the first unchecked task. Tasks are ordered intentionally — never skip ahead. If the plan references spec docs, read only the sections relevant to the current task. No plan (or the request is outside it...
 1.6K
9882 tao-train-reid nvidia/skills
Re-Identification Person re-identification. Learns discriminative embeddings to match the same person across different camera views. Metric learning based. Set model.pretrained_model_path for pretrained weights. Dataclass Schemas Generated TAO Core schemas are packaged in schemas/<action>.schema.json , with schemas/manifest.json listing available actions. Each generated schema also emits references/spec_template_<action>.yaml from the schema top-level default field. AutoML enablement is declared...
 1.6K
9883 tao-analyze-gaps-vlm-bcq nvidia/skills
VLM Binary Classification Gap Analysis Reads a VLM predictions JSON, compares each model response against ground truth, and writes FP/FN failure cases to a JSONL file with a summary report. Purpose After running a VLM on a binary yes/no evaluation task, the predictions need to be compared against ground truth to identify failure cases. This skill produces a structured list of FP (false positive) and FN (false negative) samples that downstream RCCA stages (e.g., cosmos generation, root cause anal...
 1.6K
9884 tao-train-visual-changenet nvidia/skills
Visual ChangeNet Visual ChangeNet is a TAO Toolkit model for visual inspection and defect detection. It supports two tasks: Classify — Binary image classification using a siamese-style architecture with a shared backbone (C-RADIO ViT) and a learnable difference module. Compares image pairs to classify defects as PASS/NO_PASS. Segment — Pixel-level change segmentation using a ViT-Large NVDINOv2 backbone. Compares before/after image pairs to produce a binary change mask. The backbone weight ( c_ra...
 1.6K
9885 tao-train-metric-learning-recognition nvidia/skills
ML Recog Metric learning recognition for fine-grained visual recognition. Learns embeddings for retrieval-based matching (e.g., retail product recognition). Uses triplet/contrastive losses. Set model.pretrained_model_path for pretrained backbone. For TAO Deploy TensorRT actions ( gen_trt_engine , TensorRT evaluate , and TensorRT inference ), read references/tao-deploy-metric-learning-recognition.md first. Deploy spec templates live in this skill's references/ folder with the spec_template_deploy...
 1.6K
9886 tao-train-dino nvidia/skills
DINO DINO (DETR with Improved DeNoising Anchor Boxes) for 2D object detection. Transformer-based detector with denoising training, multi-scale features, and optional distillation support. Uses pretrained backbone weights (e.g. ResNet-50 ImageNet). Set model.pretrained_backbone_path for backbone-only or train.pretrained_model_path for full model. When To Use Train, evaluate, export, distill, quantize, or run inference for a TAO DINO 2D object detector. For TAO Deploy TensorRT actions ( gen_trt_en...
 1.6K
9887 tao-train-depth-anything-v2 nvidia/skills
Depth Net Mono Monocular depth estimation using Metric Depth Anything v2 or Relative Depth Anything architectures. Predicts per-pixel depth from single RGB images. Pretrained checkpoint loading varies by model variant and use case — see the Pretrained checkpoint loading — use case matrix in references/parameters.md . The mono and stereo skills both invoke the unified TAO depth_net CLI inside the container; the mono/stereo family is selected via model.model_type (see references/parameters.md ). F...
 1.6K
9888 tao-train-mask2former nvidia/skills
Mask2Former Mask2Former for universal image segmentation (panoptic, instance, and semantic). Transformer-based with masked attention for high-quality segmentation results. Set model.backbone.pretrained_weights for Swin backbone weights. For TAO Deploy TensorRT actions ( gen_trt_engine , TensorRT evaluate , and TensorRT inference ), read references/tao-deploy-mask2former.md first. Deploy spec templates live in this skill's references/ folder with the spec_template_deploy_*.yaml prefix. Dataclass ...
 1.6K
9889 tao-train-nvdinov2 nvidia/skills
NVDINOv2 NVDINOv2 for self-supervised visual representation learning. Trains vision transformers via self-distillation (teacher-student) without labels. Produces general-purpose visual features. Set train.pretrained_model_path for pretrained ViT weights. For TAO Deploy TensorRT actions ( gen_trt_engine ), read references/tao-deploy-nvdinov2.md first. Deploy spec templates live in this skill's references/ folder with the spec_template_deploy_*.yaml prefix. Dataclass Schemas Generated TAO Core sch...
 1.6K
9890 tao-train-mask-auto-encoder nvidia/skills
MAE MAE (Masked Autoencoder) for self-supervised pretraining and fine-tuning. Masks random patches and reconstructs them to learn visual representations. Supports pretrain and finetune stages. Set train.pretrained_model_path for pretrained MAE weights when fine-tuning. For TAO Deploy TensorRT actions ( gen_trt_engine ), read references/tao-deploy-mask-auto-encoder.md first. Deploy spec templates live in this skill's references/ folder with the spec_template_deploy_*.yaml prefix. The parent PyTor...
 1.6K
9891 tao-train-rtdetr nvidia/skills
RT-DETR RT-DETR (Real-Time DEtection TRansformer) for 2D object detection. Designed for real-time inference with competitive accuracy. Supports distillation and quantization for deployment optimization. Set model.pretrained_backbone_path for backbone weights or train.pretrained_model_path for full model. For TAO Deploy TensorRT actions ( gen_trt_engine , TensorRT evaluate , and TensorRT inference ), read references/tao-deploy-rtdetr.md first. Deploy spec templates live in this skill's references...
 1.6K
9892 gstack-workflow-assistant reason-machines/trending-skills
gstack Workflow Assistant Skill by ara.so — Daily 2026 Skills collection Transform Claude Code from a generic assistant into a team of specialists you can summon on demand. Eight opinionated workflow skills that act as CEO, Engineering Manager, Release Manager, and QA Engineer with slash commands for planning, review, shipping, and testing. What It Does gstack provides specialized AI personas and workflows: CEO Review : Rethink problems and find the 10-star product hiding in requests Engineering...
 1.6K
9893 deepseek-ocr reason-machines/trending-skills
DeepSeek-OCR Skill by ara.so — Daily 2026 Skills collection. DeepSeek-OCR is a vision-language model for Optical Character Recognition with "Contexts Optical Compression." It supports native and dynamic resolutions, multiple prompt modes (document-to-markdown, free OCR, figure parsing, grounding), and can be run via vLLM (high-throughput) or HuggingFace Transformers. It processes images and PDFs, outputting structured text or markdown. Installation Prerequisites CUDA 11.8+, PyTorch 2.6.0 Python ...
 1.6K
9894 autoresearchclaw-autonomous-research reason-machines/trending-skills
AutoResearchClaw — Autonomous Research Pipeline Skill by ara.so — Daily 2026 Skills collection. AutoResearchClaw is a fully autonomous 23-stage research pipeline that takes a natural language topic and produces a complete academic paper: real arXiv/Semantic Scholar citations, sandboxed experiments, statistical analysis, multi-agent peer review, and conference-ready LaTeX (NeurIPS/ICML/ICLR). No hallucinated references. No human babysitting. Installation Clone and install git clone https://githu...
 1.6K
9895 wordpress-content jezweb/claude-skills
WordPress Content Create, update, and manage WordPress content — posts, pages, media, categories, tags, and menus. Produces live content on the site via WP-CLI or the REST API. Prerequisites Working WP-CLI SSH connection or REST API credentials (use wordpress-setup skill) Site config from wordpress.config.json or wp-cli.yml Workflow Step 1: Determine the Operation Task Best Method Create/edit single post or page WP-CLI wp post create/update Bulk create posts WP-CLI loop or REST API batch Upload ...
 1.6K
9896 tao-run-automl-deft-pipeline nvidia/skills
AutoML + DEFT Pipeline A workflow-bridge skill that runs three phases in sequence by delegating to two existing skills — tao-run-automl for HPO and a DEFT application skill (default tao-run-deft-aoi for AOI; other skills/applications/deft-* skills for non-AOI cases) for the iterative data-improvement loop. This skill does not re-implement AutoML or DEFT. It owns only the connective tissue: HPO spec inputs, the spec-handoff between AutoML and DEFT, and the post-DEFT AutoML re-run on the augmented...
 1.6K
9897 tao-run-deft-aoi nvidia/skills
Skill: tao-run-deft-aoi When to Use This Skill Use this skill when the user wants an agent to run the full DEFT AOI improvement loop for an NVIDIA TAO VisualChangeNet / ChangeNet PCB inspection model: baseline evaluation, RCA, synthetic defect generation, data mining, retraining, and deployment gating until a KPI target is met. "Run the DEFT loop" "Fine-tune until FAR below 0.1% at recall=100%" "Improve my AOI ChangeNet model using RCA and synthetic defects" "Iterate training until false accept ...
 1.6K
9898 tao-run-platform nvidia/skills
TAO Execution SDK The SDK is the optional Python layer for users who need job handles, S3 I/O wrapping, or platform-specific features (SLURM/Lustre queues, Kubernetes Jobs, local Docker debugging, Brev instance reuse). Most TAO skills run with just docker run and don't need it. Reach for the SDK when: You want a Job handle to poll status and stream logs over time. You need S3-aware input download / output upload baked into the entrypoint. You're chaining multiple jobs and want persisted state. P...
 1.6K
9899 tao-generate-referring-expressions nvidia/skills
Image Referring Expression Pipeline Generate referring-expression and grounding annotations from images with KITTI-format bounding box labels. A single VLM (Gemini or any OpenAI-compatible endpoint) runs four steps: per-object region descriptions, holistic image captions, grouped grounding expressions tied to bboxes, and an optional double-check verification pass. Purpose Transform (image, KITTI labels) pairs into a unified annotations.jsonl containing rich, grounded referring expressions. The V...
 1.6K
9900 tao-train-centerpose nvidia/skills
CenterPose CenterPose for keypoint / pose estimation. Detects object centers and regresses keypoint locations. Used for 6-DoF object pose estimation. Set model.backbone.pretrained_backbone_path. For TAO Deploy TensorRT actions ( gen_trt_engine , TensorRT evaluate , and TensorRT inference ), use the deploy spec templates packaged in this skill's references/ folder with the spec_template_deploy_*.yaml prefix. Dataclass Schemas Generated TAO Core schemas are packaged in schemas/<action>.schema.json...
 1.6K