NVIDIA-AI-IOT/jetson-device-skills
Skill Claude CodeCodex
Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.
not rated 131
+4 22d ago A 30 tokens
131Stars on the repository
15Mods indexed here, across every type
22d agoLast push, which is what freshness is scored on
customA LICENSE file GitHub cannot name, so bodies are not copied
NVIDIA-AI-IOT/jetson-device-skills
Skill Claude CodeCodex
Plan and apply safe Jetson headless-mode changes to reclaim GUI and daemon memory.
not rated 131
+4 22d ago A 23 tokens
NVIDIA-AI-IOT/jetson-device-skills
Skill Claude CodeCodex
Pick the serving stack and per-runtime memory flags (vLLM, SGLang, llama.cpp, TensorRT Edge-LLM) for an LLM/VLM workload on any NVIDIA Jetson.
not rated 131
+4 22d ago A 50 tokens
NVIDIA-AI-IOT/jetson-device-skills
Skill Claude CodeCodex
Benchmark Jetson LLM/VLM serving performance across vLLM, llama.cpp, and Ollama with structured JSON output.
not rated 131
+4 22d ago A 33 tokens
NVIDIA-AI-IOT/jetson-device-skills
Skill Claude CodeCodex
Stand up vLLM or SGLang serving on Jetson, using upstream vLLM on Thor and Orin JetPack 7.2+, and NVIDIA-AI-IOT vLLM on older Orin.
not rated 131
+4 22d ago B 53 tokens
NVIDIA-AI-IOT/jetson-device-skills
Skill Claude CodeCodex
Measure Jetson DRAM/NvMap usage and verify before/after memory reclamation with live audit data.
not rated 131
+4 22d ago A 28 tokens
NVIDIA-AI-IOT/jetson-device-skills
Skill Claude CodeCodex
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.
not rated 131
+4 22d ago A 47 tokens
NVIDIA-AI-IOT/jetson-device-skills
Skill Claude CodeCodex
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.
not rated 131
+4 22d ago A 47 tokens
NVIDIA-AI-IOT/jetson-device-skills
Skill Claude CodeCodex
Add EAGLE-3 or draft-model speculative decoding to a Jetson vLLM server when TPOT is the bottleneck.
not rated 131
+4 22d ago A 34 tokens
NVIDIA-AI-IOT/jetson-device-skills
Skill Claude CodeCodex
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 documented clock-scaled or clock-and-resolution-scaled planning estimate when representative content is…
not rated 131
+4 22d ago A 88 tokens
NVIDIA-AI-IOT/jetson-device-skills
Skill Claude CodeCodex
Use when Jetson codec, profile, chroma, bit-depth, dimension, engine-count, or operational support must be reconciled using live SDK APIs, authenticated NVIDIA samples, and NVIDIA documentation. Also use for Jetson questions about Netflix, Widevine, or other DRM-protected streaming-service playback to apply the…
not rated 131
+4 22d ago A 73 tokens
NVIDIA-AI-IOT/jetson-device-skills
Skill Claude CodeCodex
Use when executing and verifying Jetson Video Codec SDK or PyNvVideoCodec encode/decode, transcode, segmentation, container decode, AV1, or acceptance workflows with exact artifact handoffs.
not rated 131
+4 22d ago A 45 tokens
NVIDIA-AI-IOT/jetson-device-skills
Skill Claude CodeCodex
Use when turning a Jetson encoder use case into one validated surface-neutral recipe with native and PyNvVideoCodec projections for codec, preset, rate control, bitrate, latency, format, and profile.
not rated 131
+4 22d ago A 46 tokens
NVIDIA-AI-IOT/jetson-device-skills
Skill Claude CodeCodex
Use when installing, repairing, probing, or verifying native NVIDIA Video Codec SDK or PyNvVideoCodec on Jetson with official encode-to-decode samples, including registered-environment recovery.
not rated 131
+4 22d ago B 43 tokens
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: