← All skills
deepstream-dev
72 / 100 · Review before installing
Check before installing. Some of what it can do is expected: a coding skill usually runs build and test commands.
By NVIDIA/skills (GitHub) · coding · 3,933 stars · scanned at commit 2630133
NVIDIA DeepStream SDK development with Python pyservicemaker API. Use when building video analytics pipelines, GStreamer-based video processing, TensorRT inference integration, object detection/tracking, or Kafka/message broker integration.
Works with any agent that supports SKILL.md skills.
What this skill can do
Runs commands on your computer
This is disclosed by the author in the skill's SKILL.md or README. Expected for a coding skill.
Found in 1 place.
Downloads and installs other software
The author does not mention this.
Found in 69 places.
Show 17 more
- skills/deepstream-dev/evals/evals.json, line 185
"pattern": "(pyservicemaker.*\\.whl|pip install.*pyservicemaker)" - skills/deepstream-dev/references/buffer_apis.md, line 105
import torch # pip install torch torchvision (not in base DS container) - skills/deepstream-dev/references/buffer_apis.md, line 138
import torch # pip install torch torchvision (not in base DS container) - skills/deepstream-dev/references/buffer_apis.md, line 296
import torch # pip install torch torchvision (not in base DS container) - skills/deepstream-dev/references/buffer_apis.md, line 386
import cv2 # pip install opencv-python-headless (not in base DS container) - skills/deepstream-dev/references/buffer_apis.md, line 387
import torch # pip install torch torchvision (not in base DS container) - skills/deepstream-dev/references/buffer_apis.md, line 481
import torch # pip install torch torchvision (not in base DS container) - skills/deepstream-dev/references/buffer_apis.md, line 542
import torch # pip install torch torchvision (not in base DS container) - skills/deepstream-dev/references/buffer_apis.md, line 597
import torch # pip install torch torchvision (not in base DS container) - skills/deepstream-dev/references/buffer_apis.md, line 598
import cv2 # pip install opencv-python-headless (not in base DS container) - skills/deepstream-dev/references/buffer_apis.md, line 640
import cv2 # pip install opencv-python-headless (not in base DS container) - skills/deepstream-dev/references/buffer_apis.md, line 641
import torch # pip install torch torchvision (not in base DS container) - skills/deepstream-dev/references/buffer_apis.md, line 845
import torch # pip install torch torchvision (not in base DS container) - skills/deepstream-dev/references/buffer_apis.md, line 920
import torch # pip install torch torchvision (not in base DS container) - skills/deepstream-dev/references/buffer_apis.md, line 921
import cv2 # pip install opencv-python-headless (not in base DS container) - skills/deepstream-dev/references/buffer_apis.md, line 1020
import torch # pip install torch torchvision (not in base DS container) - skills/deepstream-dev/references/buffer_apis.md, line 1151
import torch # pip install torch torchvision (not in base DS container)
and 49 more places
Sends data to these websites: api.example.com, packages.confluent.io, download.redis.io, host, api.ngc.nvidia.com
The author does not mention this.
Found in 15 places.
Show 12 more
- skills/deepstream-dev/references/kafka_messaging.md, line 1316
wget -qO /tmp/confluent-archive.key https://packages.confluent.io/deb/7.8/archive.key - skills/deepstream-dev/references/kafka_messaging.md, line 1523
wget http://download.redis.io/releases/redis-6.0.8.tar.gz - skills/deepstream-dev/references/rest_api_dynamic.md, line 127
curl -X POST 'http://localhost:9000/api/v1/stream/add' -d '{ - skills/deepstream-dev/references/rest_api_dynamic.md, line 138
curl -X POST 'http://localhost:9000/api/v1/stream/remove' -d '{ - skills/deepstream-dev/references/rest_api_dynamic.md, line 148
curl -X GET 'http://localhost:9000/api/v1/stream/get-stream-info' - skills/deepstream-dev/references/rest_api_dynamic.md, line 151
curl -X GET 'http://localhost:9000/api/v1/health/get-dsready-state' - skills/deepstream-dev/references/streaming_sources.md, line 143
- Verify Range support: `curl -I -H "Range: bytes=0-0" http://host:8080/video.mp4` should - skills/deepstream-dev/references/streaming_sources.md, line 407
curl -I -H "Range: bytes=0-0" http://localhost:8080/sample.mp4 - skills/deepstream-dev/references/tracker_config.md, line 751
wget 'https://api.ngc.nvidia.com/v2/models/nvidia/tao/reidentificationnet/versions/deployable_v1.0/files/resnet50_market1501.etlt' \ - skills/deepstream-dev/references/tracker_config.md, line 850
wget 'https://api.ngc.nvidia.com/v2/models/nvidia/tao/reidentificationnet/versions/deployable_v1.0/files/resnet50_market1501.etlt' \ - skills/deepstream-dev/references/tracker_config.md, line 854
wget 'https://api.ngc.nvidia.com/v2/models/nvidia/tao/bodypose3dnet/versions/deployable_accuracy_onnx_1.0/files/bodypose3dnet_accuracy.onnx' \ - skills/deepstream-dev/references/tracker_config.md, line 1054
curl -XPOST 'http://localhost:9000/api/v1/nvtracker/config-path' -d '{
Changes files outside its own folder
This is disclosed by the author in the skill's SKILL.md or README.
Found in 3 places.
Safer alternatives
Low-risk skills in the same category (coding) that look related. Check that one does what you need.
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'deepstream-dev' ] || [ -L ~/.agents/skills/'deepstream-dev' ]; then echo 'A skill folder named deepstream-dev already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/NVIDIA/skills' "$d" && git -C "$d" checkout --quiet '2630133f22e357f2005886567a39eddcc1b520e2' -- 'skills/deepstream-dev' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/deepstream-dev' ~/.agents/skills/'deepstream-dev' && rm -rf "$d"; fi
Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'deepstream-dev' ~/.claude/skills/'deepstream-dev' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.
Badge for your README
The badge for NVIDIA/skills shows the score of its lowest-scoring skill.
[](https://zalavijaysinh.github.io/skilltrust/repos/NVIDIA/skills/)
Score history
| Date | Version | Score |
|---|
| 2026-11-11 | 2630133 | 72 |
| 2026-11-08 | fce3cca | 72 |
| 2026-11-07 | fce3cca | 72 |