Dlsps User

What it does

When your agent uses it

• A user wants to: deploy the pipeline server via Docker Compose
• Monitor pipeline instances through the REST API
• Configure pipeline definitions in config.json
• Publish inference metadata over MQTT

Example prompts

• “pipeline server”
• “start pipeline via REST”
• “deploy video analytics microservice”
• “/dlsps-user”

Requirements

• Python 3
• Docker

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

1. 1Gather requirements from user prompt (source, device, output type)
2. 2Start the service (cd microservices/dlstreamer-pipeline-server/docker && docker compose up)
3. 3POST to /pipelines/{name}/{version} with source + destination + parameters
4. 4Show RTSP URL, status-check command, and stop command

What it can do on your machine

Read from SKILL.md and the folder at commit 3084578. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • docker

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Links to these hosts (documentation or services it may open):

  • github.com

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Dlsps User loads about 2.2k tokens when it runs, and up to ~5.9k if it reads all its reference files. Until then it costs about 215 tokens; SKILL.md has 650 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~215

When it runs · the whole SKILL.md, loaded when a task matches

~2.2k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~5.9k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from open-edge-platform/edge-ai-libraries at commit 3084578, republished under its Apache-2.0 licence (© open-edge-platform). 650 words, ~2,162 tokens.

name

dlsps-user

description

Deploy and operate DL Streamer Pipeline Server — a microservice that wraps DL Streamer pipelines behind a REST API for containerized, no-code operation. Use this skill whenever a user wants to: deploy the pipeline server via Docker Compose or Helm; start, stop, or monitor pipeline instances through the REST API; configure pipeline definitions in config.json; publish inference metadata over MQTT, OPC UA, InfluxDB, S3, or ROS2; set up GPU/NPU device access for the container; troubleshoot service-level issues (container startup, REST errors, port conflicts). This skill is NOT for writing new DL Streamer applications or custom GStreamer code — use the dlstreamer-coding-agent skill for that. Trigger on phrases like "pipeline server", "DLSPS", "start pipeline via REST", "deploy video analytics microservice", "config.json pipeline definition".

REST API (port 8080, OpenAPI 3.0 / Connexion)
    │
    ▼
Pipeline Manager (lifecycle: start / stop / status)
    │
    ▼
GStreamer Engine + DL Streamer Plugins
    │
    ├── Decode: CPU or GPU (decodebin3) │ GPU (vah264dec) │ CPU (avdec_h264)
    ├── Inference: gvadetect / gvaclassify (CPU, GPU, NPU)
    └── Publish: MQTT │ OPC UA │ S3 │ InfluxDB │ ROS2 │ File
    │
    ▼
Output: RTSP stream │ WebRTC stream │ metadata files

{
  "source": {
    "uri": "file:///path/to/video.avi",
    "type": "uri"
  },
  "destination": {
    "metadata": {
      "type": "file",
      "path": "/tmp/results.jsonl",
      "format": "json-lines"
    },
    "frame": {
      "type": "rtsp",
      "path": "my-stream-name"
    }
  },
  "parameters": {
    "detection-properties": {
      "model": "/path/to/model.xml",
      "device": "CPU"
    }
  }
}

{
  "config": {
    "pipelines": [
      {
        "name": "my_pipeline",
        "source": "gstreamer",
        "queue_maxsize": 50,
        "pipeline": "{auto_source} ! decodebin3 ! videoconvert ! gvadetect name=detection model-instance-id=inst0 ! queue ! gvafpscounter ! gvametaconvert add-empty-results=true name=metaconvert ! gvametapublish name=destination ! appsink name=appsink",
        "parameters": {
          "type": "object",
          "properties": {
            "detection-properties": {
              "element": {
                "name": "detection",
                "format": "element-properties"
              }
            }
          }
        },
        "auto_start": false
      }
    ]
  }
}

© open-edge-platform, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 7 other files (references) in microservices/dlstreamer-pipeline-server/.github/skills/dlsps-user of open-edge-platform/edge-ai-libraries.

• SKILL.md
• benchmark/benchmark.md
• evals/evals.json
• example-prompts/detect-on-video-file.md
• example-prompts/gpu-inference-mqtt.md
• references/api-and-pipelines.md
• references/service-setup.md
• references/troubleshooting.md

Open the folder on GitHubat commit 3084578