claudemods
中文English

来源nvidia/skills

nvidia/skills 已索引

Agent Skills for NVIDIA products — install into Claude Code, Codex, and other coding agents to run Physical AI, robotics, simulation, CUDA, and RAG workflows end to end.

查看上游仓库

已索引 索引里有这个仓库的包记录。包数量是历史登记记录，不代表这些包现在仍可用。

仓库

规范名称
NVIDIA/skills
GitHub 仓库 ID
1167034425
包记录
394 （历史登记记录，不代表现在仍可用）

发现与队列

首个记录来源
marketplace:anthropics/claude-plugins-official
发现于
队列状态
ok
记录的错误次数
0
最近完成的处理
下次检查资格
起具备资格

首个记录来源是队列第一次保存的来源，不是完整的发现历史。错误次数在处理以错误状态结束时增加，成功处理后清零，不是全部尝试次数。「最近完成的处理」是结束时间，不是开始时间。

资格按 计算。它不是排期：采集器每次运行只处理有限数量的来源，具备资格也不保证何时检查。

最近保存的扫描

仓库元数据读取于
扫描状态
complete
扫描保存于
识别器版本
2
续扫记录
没有

扫描记录与队列状态分开：队列状态说明处理进度，扫描记录说明最近一次保存了什么。有续扫记录只表示存有未完成的状态，没有剩余数量。

源文件证据覆盖

已存储的包版本在这个仓库中引用的固定源文件的原始计数。它反映已记录了什么，不代表仓库有多完整。

范围与限制

统计所有已存储版本（来自任何包）中指向本仓库规范名称的不同固定文件链接（仓库、提交、路径）。本仓库所拥有的包的文件，只有被某个版本在这里链接时才会计入。不合并别名，也不会根据当前名称推测历史。

「已知」表示已记录普通文件身份，不表示整个目录或包已被覆盖。不是有效固定文件 URL 的链接不计入。

引用了 395 个固定源文件

  • 395 已知
  • 0 提交中不存在
  • 0 文件列表截断
  • 0 不受支持
  • 0 尚无记录
  • 0 读取失败

按仓库、提交和路径去重；同一路径出现在两个提交中，按两个文件身份计数。不是组件组数。

读取失败的提交 0

尚无记录的文件没有对应的提交读取失败记录。

关联的包 394

按仓库的已验证身份关联。数量是历史登记记录，不是当前可用性。

第 161–180 条，共 394 条结果

  • jetson-memory-audit技能

    Measure Jetson DRAM/NvMap usage and verify before/after memory reclamation with live audit data.

    392ab8ab2587

  • jetson-optimize-memory技能

    Reclaim DRAM by disabling unused subsystems across MB1 BCT, MB2 BCT, kernel reserved-memory, and SWIOTLB. Use for headless or no-camera Jetson deployments; not for CPU/GPU frequency tuning.

    392ab8ab2587

  • jetson-package技能

    Pick Jetson-compatible containers, vLLM runtime images, and Jetson AI Lab PyPI indexes; maps Orin SM 8.7 vs Thor SM 11.0 and JetPack-specific package choices.

    392ab8ab2587

  • jetson-print-bsp-info技能

    Use when you need to print Jetson BSP info (L4T version, board configs, rootfs state) from a Linux_for_Tegra root on the host PC. This is an example skill.

    392ab8ab2587

  • jetson-print-device-info技能

    Use when you need to print Jetson device info (module model, L4T version, kernel, OS version, current power mode) from a running Jetson target. This is an example skill.

    392ab8ab2587

  • jetson-promote-image技能

    Use to promote overlay files and built artifacts into the staged BSP image. Do NOT use to flash or build. Triggers: promote bsp image.

    392ab8ab2587

  • jetson-quick-start技能

    Entry skill for Jetson / IGX BSP customization. Asks one core click-to-select setup questionnaire and passes prefilled answers to downstream setup skills.

    392ab8ab2587

  • jetson-set-target技能

    Switch the active Jetson target-platform pointer to an existing profile YAML. Use before customize/build/flash to change target; not for authoring profiles — use jetson-init-target instead.

    392ab8ab2587

  • jetson-speculative-decoding技能

    Add EAGLE-3 or draft-model speculative decoding to a Jetson vLLM server when TPOT is the bottleneck.

    392ab8ab2587

  • jetson-validate-image技能

    Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.

    392ab8ab2587

  • jetson-video-benchmark技能

    Use when measuring Jetson Video Codec SDK or PyNvVideoCodec encode/decode throughput, comparing presets or surfaces, testing codec-worker capacity with authenticated samples and user media, or producing a clearly labeled documentation-deri…

    392ab8ab2587

  • jetson-video-capability技能

    Use when Jetson codec, profile, chroma, bit-depth, dimension, engine-count, or operational support must be reconciled from live APIs, authenticated NVIDIA samples, and NVIDIA documentation; also applies the content-DRM scope.

    392ab8ab2587

  • jetson-video-pipeline技能

    Use when planning, executing, and independently validating Jetson Video Codec SDK or PyNvVideoCodec encode/decode, transcode, segmentation, container decode, AV1, or concise acceptance workflows.

    392ab8ab2587

  • jetson-video-recipe技能

    Use when turning a Jetson encoder use case into one surface-neutral recipe with native Video Codec SDK and PyNvVideoCodec projections.

    392ab8ab2587

  • jetson-video-setup技能

    Use when installing, repairing, reusing, inspecting, or verifying readiness of the native NVIDIA Video Codec SDK or PyNvVideoCodec on Jetson, including the one-frame encode/decode smoke test with official samples, and when interpreting wha…

    392ab8ab2587

  • kermt-add-cmim-pretrain技能

    Convert a grover_base checkpoint (encoder-only or encoder + vocab heads) into a hybrid checkpoint by adding a randomly-initialized cMIM decoder + latent_dist, then continue pretraining on the user's corpus as hybrid (vocab + contrast). Eff…

    392ab8ab2587

  • kermt-continue-pretrain技能

    Continue KERMT pretraining on a custom SMILES corpus with a grover_base, cmim, or hybrid checkpoint. Use a local checkpoint or optionally download a pinned Hugging Face model bundle using HF_TOKEN if configured. Run containerized training …

    392ab8ab2587

  • kermt-embed技能

    Extract per-molecule embeddings from any encoder-bearing KERMT checkpoint. Use a local checkpoint or optionally download a pinned Hugging Face model bundle using HF_TOKEN if configured. Run containerized embedding extraction and write mode…

    392ab8ab2587

  • kermt-finetune技能

    Finetune a pretrained KERMT encoder on a labeled CSV. Validate the checkpoint and data, prepare features, and run containerized training. Use a local checkpoint or optionally download a pinned Hugging Face model bundle using HF_TOKEN if co…

    392ab8ab2587

  • kermt-infer技能

    Run predictions with a finetuned KERMT checkpoint on a SMILES-only CSV. The skill validates that the input ckpt has task FFN heads (refuses pretrain ckpts with a redirect to kermt-finetune), validates the CSV, prepares the data (clean + rd…

    392ab8ab2587

已保存的扫描说明 0

没有保存额外的扫描说明。

记录的别名 0

这些名称在上次记录时指向这个仓库。这是记录下来的解析结果，不是实时的 GitHub 检查；本站不会因此合并包或元数据。

没有记录到指向这个仓库的别名。

不支持的市场条目 0

这个仓库的市场清单里、本站暂不支持的条目。它们是原样保存的来源数据，不会被抓取或执行。

没有记录到不支持的条目。