Vss Dlstreamer Pipeline

What it does

When your agent uses it

• The user wants to change the DLStreamer/GStreamer pipeline
• Extract frames differently
• Modify the EVAM pipeline
• Add a detection model to video ingestion

Example prompts

• “Use the vss-dlstreamer-pipeline skill to help developers understand and safely modify the DLStreamer/GStreamer Pipeline Server (EVAM) video…”
• “/vss-dlstreamer-pipeline”

Requirements

• A Bash shell
• Docker

Workflow steps

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

1. 1The summary pipeline stores the input video in MinIO and obtains an HTTP object URL.
2. 2pipeline-manager/src/state-manager/services/pipeline.service.ts calls EvamService.startChunkingStub(stateId, videoUrl, state.userInputs…
3. 3EvamService POSTs to
4. 4DL Streamer Pipeline Server executes the matching GStreamer template from video-ingestion/resources/conf/config.json.
5. 5Frames pass through gvapython ... class=Publisher function=process module=/home/pipeline-server/gvapython/publisher/publish.py.
6. 6Publisher writes frame JPEGs and metadata JSON to MinIO and publishes a chunk message to RabbitMQ MQTT topic topic/video_stream.
7. 7pipeline-manager/src/evam/services/rabbitmq.service.ts consumes AMQP queue my_mqtt_queue bound to exchange amq.topic with routing key…
8. 8Captioning, summarization, and search embedding generation happen downstream from the extracted frames/metadata; EVAM itself only…

What it can do on your machine

Read from SKILL.md and the folder at commit 0ed0479. 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

  Ships 1 file in scripts/ (Shell), which the agent can run.

  Shell commands in SKILL.md call:

  • bash

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

• Network

  No URLs in SKILL.md.

  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

Vss Dlstreamer Pipeline loads about 1.8k tokens when it runs, and up to ~5.4k if it reads all its reference files. Until then it costs about 103 tokens; SKILL.md has 590 words of instructions outside code blocks.

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

~103

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

~1.8k

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

~5.4k

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); the scripts in this folder are not scanned.

SKILL.md

The full file from open-edge-platform/edge-ai-libraries at commit 0ed0479, republished under its Apache-2.0 licence (© open-edge-platform). 590 words, ~1,778 tokens.

name

vss-dlstreamer-pipeline

description

Helps developers understand and safely modify the DLStreamer/GStreamer Pipeline Server (EVAM) video ingestion pipelines in the video-search-and-summarization sample app. Use when the user wants to change the DLStreamer/GStreamer pipeline, extract frames differently, modify the EVAM pipeline, add a detection model to video ingestion, or tune chunk/frame extraction in the pipeline server.

# SKILL_DIR is THIS skill's own directory (shown to you when the skill loads);
# in-repo it is .github/skills/vss-dlstreamer-pipeline. Works the same if the skill is installed standalone.
SKILL_DIR=".github/skills/vss-dlstreamer-pipeline"
APP_ROOT="$(bash "$SKILL_DIR/scripts/vss-bootstrap.sh")"
cd "$APP_ROOT"

{
  "source": {
    "element": "curlhttpsrc",
    "type": "gst",
    "properties": { "location": "<MinIO object URL>" }
  },
  "parameters": {
    "detection-properties": {
      "model": "/home/pipeline-server/models/object-detection/ultralytics/public/yolov8l/FP32/yolov8l.xml",
      "device": "CPU"
    },
    "publish": {
      "minio_bucket": "<pipeline-manager MINIO_BUCKET>",
      "video_identifier": "<stateId>",
      "topic": "topic/video_stream"
    },
    "frame": 5,
    "chunk_duration": 10,
    "frame_width": 480
  }
}

© 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 13 other files (scripts, references) in sample-applications/video-search-and-summarization/.github/skills/vss-dlstreamer-pipeline of open-edge-platform/edge-ai-libraries.

• SKILL.md
• BENCHMARK.md
• evals/evals.json
• evals/trigger-evals.json
• example-prompts/01-tune-frame-extraction-rate.md
• example-prompts/02-add-detection-model.md
• example-prompts/03-debug-broken-pipeline-string.md
• example-prompts/04-add-new-pipeline-name.md
• example-prompts/05-explain-request-payload.md
• example-prompts/06-validate-publish-pipeline-change.md
• example-prompts/07-bootstrap-fresh-machine.md
• example-prompts/README.md
• references/evam-pipelines.md
• scripts/vss-bootstrap.sh

Open the folder on GitHubat commit 0ed0479