发现 Claude mods
这里默认只列出有证据的 Claude Code Mod：插件的钩子配置声明了函数钩子模块（modules）。服务器每 6 小时在 GitHub 上找新的 Mod，也接受你提交的仓库。
第 361–380 条，共 393 条结果
★ 是仓库级 Star，不代表包的质量；下载请求不等于安装。指标定义
-
tao-train-reid技能
Person re-identification (ReID). Learns discriminative embeddings to match the same person across different camera views, based on metric learning. Use when training, evaluating, exporting, or runnin…
-
tao-train-rtdetr技能
RT-DETR (Real-Time DEtection TRansformer) for 2D object detection. Designed for real-time inference with competitive accuracy and supports distillation and quantization for deployment optimization. U…
-
tao-train-segformer技能
SegFormer for semantic segmentation. Lightweight transformer-based architecture with hierarchical feature extraction, efficient for real-time segmentation tasks. Use when training, evaluating, export…
-
tao-train-single-step技能
Standard single-step train/eval/export workflow for any TAO model. Use when training a TAO model on a dataset without iterative data augmentation, AutoML, or DEFT loops. Trigger phrases include "sing…
-
tao-train-sparse4d技能
Sparse4D for multi-camera temporal 3D object detection and tracking. Uses sparse queries with deformable attention across camera views and time for end-to-end 3D perception, with an instance bank for…
-
tao-train-visual-changenet技能
Visual ChangeNet for binary image classification and segmentation in AOI defect detection. Use when training, evaluating, exporting, or running inference for PCB defect detection or visual inspection…
-
tao-validate-dataset-format技能
Run `tao-daft validate` to check NVIDIA TAO DAFT datasets for structure, schema, and cross-reference errors. Do not use for non-DAFT formats. Use when the user asks to validate a DAFT dataset, check …
-
tao-validate-recipe-transfer技能
Port a published computer vision paper's official code and training recipe onto a customer's own dataset, or diagnose why such a transfer produced bad numbers. Use this whenever someone wants to repr…
-
tilegym-adding-cutile-kernel技能
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 …
-
tilegym-converting-cutile-to-julia技能
Converts cuTile Python GPU kernels (@ct.kernel) to cuTile.jl Julia equivalents. Handles kernel syntax translation, 0-indexed to 1-indexed conversion, broadcasting differences, memory layout (row-majo…
-
tilegym-converting-cutile-to-triton技能
Converts cuTile GPU kernels (@ct.kernel) to Triton (@triton.jit). Handles standard in-repo conversion, debugging (cudaErrorIllegalAddress, shape mismatch, numerical mismatch), and mapping cuTile idio…
-
tilegym-cutile-autotuning技能
Use when adding, modifying, optimizing, or debugging CuTile autotuning code. Trigger signals: `exhaustive_search` / `replace_hints` / `hints_fn` / `cuda.tile.tune` in code, `autotune` in filenames, o…
-
tilegym-cutile-python技能
Expert cuTile programming assistant. Write high-performance GPU kernels using cuTile's tile-based programming model with proper validation and optimization. Supports deep agent orchestration for comp…
-
tilegym-improve-cutile-kernel-perf技能
Iteratively optimize cuTile kernel performance through systematic profiling, bottleneck analysis, IR comparison, and targeted tuning. Covers tile sizes, occupancy, autotune configs, TMA, latency hint…
-
tilegym-monkey-patch-kernels-to-transformers技能
Integrate TileGym kernels into Hugging Face `transformers` models by replacing the library's submodule(s) and certain class(es)' implementations, and patching certain class(es)' init/forward/load wei…
-
vss-ask-video技能
Use this skill to ask the VSS agent's video_understanding tool a fresh visual question about a recorded clip. Not for prior tool output, search hits, or metadata-answerable questions.
-
vss-deploy-dense-captioning技能
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.
-
vss-deploy-detection-tracking-2d技能
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',…
-
vss-deploy-detection-tracking-3d技能
Deploy and operate the RTVI-CV-3D microservice as MV3DT (`MODE=mv3dt`): per-camera DeepStream perception plus BEV Fusion over calibrated cameras. Supports the bundled sample dataset, custom video fil…
-
vss-deploy-profile技能
Use to select, configure, deploy, verify, debug, or tear down a VSS profile (base, search, lvs, warehouse, edge). Not for standalone microservices — use the vss-deploy-* skill.
注册表状态
- Claude Mod
- 5
- 包
- 2,636
- 仓库
- 175
- 版本
- 2,758
- 下载请求
- 3
- 最近采集
- 成功 运行详情
发现队列还有 1,179 个仓库待处理，当前收录并不完整。