New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Lvc Run App

by open-edge-platform in open-edge-platform/edge-ai-suites

Run, start, or smoke-test the Live Video Captioning app (Docker Compose stack with dashboard on :4173).

Apache-2.0Auto-check passedTesting & QA

Install Lvc Run App

skills CLI
$ npx skills add open-edge-platform/edge-ai-suites --skill lvc-run-app -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install open-edge-platform/edge-ai-suites lvc-run-app --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/open-edge-platform/edge-ai-suites.git skills-src && mkdir -p .claude/skills && cp -r skills-src/metro-ai-suite/live-video-analysis/live-video-captioning/.github/skills/lvc-run-app .claude/skills/lvc-run-app && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
lvc-run-app
GitHub stars
140
Token cost
~796 tokens
SKILL.md length
281 words
Files
2
Skills in repo
13
Repo updated
First seen
Licence
Apache-2.0

At a glance

Run, start, or smoke-test the Live Video Captioning app (Docker Compose stack with dashboard on :4173).

  • Launch the stack
  • SKILL.md covers Mandatory, Driver commands, Gotchas and Validation, plus 1 more section
  • Runs Shell scripts from its folder; calls docker and curl
  • Start a captioning run against an RTSP stream

What it does

Lvc Run App is an agent skill from open-edge-platform/edge-ai-suites. Run, start, or smoke-test the Live Video Captioning app (Docker Compose stack with dashboard on :4173). Use to launch the stack, start a captioning run against an RTSP stream or simulator, verify captions flow, or check the dashboard.

Its SKILL.md is about 800 tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `smoke.sh`).

It sits in Testing & QA, covering Containers and QA and bug reports. It works with Docker. The repository describes itself as: A curated collection of sample applications intended for reference in developing optimized AI solutions and testing hardware performance across various industry use cases. The licence is Apache-2.0.

When your agent uses it

  • Launch the stack
  • Start a captioning run against an RTSP stream
  • Verify captions flow
  • Check the dashboard

Example prompts

  • “/lvc-run-app”

Requirements

  • A Bash shell
  • Docker

What it can do on your machine

Read from SKILL.md and the folder at commit f4e2089. 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 script files (Shell), which the agent can run.

    Shell commands in SKILL.md call:

    • docker
    • curl

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

  • Network

    No URLs in SKILL.md. Its commands use docker and curl, which can reach the network depending on how they are called.

    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

Lvc Run App loads about 796 tokens when it runs. Until then it costs about 62 tokens; SKILL.md has 281 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~62
When it runs · the whole SKILL.md, loaded when a task matches
~796

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

Auto-check passed

The automated check found no risky patterns in SKILL.md.

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-suites at commit f4e2089, republished under its Apache-2.0 licence (© open-edge-platform). 281 words, ~796 tokens.

Download SKILL.mdSave it as .claude/skills/lvc-run-app/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
lvc-run-app
description
Run, start, or smoke-test the Live Video Captioning app (Docker Compose stack with dashboard on :4173). Use to launch the stack, start a captioning run against an RTSP stream or simulator, verify captions flow, or check the dashboard.

Run Live Video Captioning

All paths relative to live-video-captioning/. Driver: .github/skills/lvc-run-app/smoke.sh — use it instead of raw commands.

Mandatory

  • One-time model download before first launch (confirm license prompt interactively):
    bash
    ./model_download_scripts/download_models.sh --model OpenGVLab/InternVL2-1B --type vlm --weight-format int8
  • Launch + wait healthy: .github/skills/lvc-run-app/smoke.sh up (runs scripts/setup_env.sh + docker compose up -d).
  • Video source must be rtsp:// or /dev/videoN — the API rejects file://. If the user has a real RTSP camera, ask for its URL and pass it: smoke.sh start-run GenAI_Pipeline_on_CPU rtsp://<camera>. Otherwise simulate: smoke.sh start-sim — with no argument it downloads the Intel sample video (worker-zone-detection.mp4 from intel-iot-devkit/sample-videos) to /tmp/lvc-smoke.mp4; pass a local .mp4 path to use your own.
  • Full end-to-end check (launch → simulate → run → caption → UI check → cleanup):
    bash
    .github/skills/lvc-run-app/smoke.sh all
  • Always smoke.sh stop-run && smoke.sh stop-sim when done.

Driver commands

text
up | status | start-sim [video.mp4] | start-run [pipeline] [rtsp_url]
wait-captions [secs] | check-ui [secs] | stop-run | stop-sim | all [video.mp4]

Gotchas

  • GPU pipeline (GenAI_Pipeline_on_GPU, the product default) fails instantly with no element "vah264dec" when VA-API is missing in the container → driver defaults to GenAI_Pipeline_on_CPU. stream-ready returning "state":"error" right after POST = pipeline failed to build; check docker logs dlstreamer-pipeline-server.
  • The stack's mediamtx has RTSP disabled (MTX_RTSP=no); the simulator runs a second mediamtx-server container on :8554.
  • First caption on CPU takes ~2–4 min (model load + first inference); ~20 s each afterwards. SSE /api/metadata-stream emits only {"type":"status"} heartbeats until then — not a hang.
  • Always curl --noproxy '*' — corporate proxy env breaks localhost calls.
  • Canonical router: .github/copilot-instructions.md. Real API: GET /api/health, /api/vlm-models, /api/pipelines, POST|GET|DELETE /api/generate_captions_alerts[/{run_id}], GET /api/generate_captions_alerts/{run_id}/stream-ready, SSE GET /api/generate_captions_alerts/metadata-stream.
  • modelName must match a directory name in ov_models/ (see GET /api/vlm-models).
  • docker compose warns about unset EMBEDDING_*/VDMS_*/LLM_* vars — harmless (EMBEDDING profile only).

Validation

  • smoke.sh status → all containers Up, {"status":"healthy"}.
  • smoke.sh wait-captions prints a "result": "<caption>" line.
  • smoke.sh check-ui prints "caption event reached UI stream" (heartbeats-only means no caption landed in the watch window — lengthen it or run wait-captions first).

Stop stack

bash
docker compose down

© 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 1 other file in metro-ai-suite/live-video-analysis/live-video-captioning/.github/skills/lvc-run-app of open-edge-platform/edge-ai-suites.

  • SKILL.md
  • smoke.sh

Open the folder on GitHubat commit f4e2089

Compare with similar skills

Lvc Run App next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Lvc Run App compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Lvc Run App this skillopen-edge-platform/edge-ai-suites140—~796Automated safety check: PassApache-2.0
DeerFlow Smoke Testbytedance/deer-flow84k—~2.5kAutomated safety check: NotesMIT
Sceneeye Maintenanceisetbio/isetbio115—~579Automated safety check: PassMIT
PR TestElite588/AUTOGPT103—~9.4kAutomated safety check: NotesCustom licence
PgjevrealZachi/pg-jev1.1k—~2.9kAutomated safety check: PassCustom licence
Lineth QuickstartLFDT-Lineth/lineth-monorepo126—~1kAutomated safety check: NotesAGPL-3.0

Similar skills

  • DeerFlow Smoke Test

    bytedance/deer-flow

    Walks through an end-to-end smoke test of a DeerFlow deployment: pull the latest code, deploy with Docker or locally, verify services, run health checks and write a report.

    84k GitHub stars~2.5k tokensUpdated today
    Testing & QAAuto-check: notes

  • Sceneeye Maintenance

    isetbio/isetbio

    Repair, promote, reorganize, or evaluate sceneEye tutorials and examples.

    115 GitHub stars~579 tokensUpdated 14 days ago
    Testing & QAAuto-check passed

  • PR Test

    Elite588/AUTOGPT

    E2E manual testing of PRs/branches using docker compose, agent-browser, and API calls.

    103 GitHub stars~9.4k tokensUpdated 5 mo ago
    Testing & QAAuto-check: notes

  • Pgjev

    realZachi/pg-jev

    Install, configure, query and explain pgjev (the jev PostgreSQL extension that filters, ranks and classifies rows with plain-language conditions via TypeSafe's Jev model).

    1.1k GitHub stars~2.9k tokensUpdated 3 days ago
    Writing & ContentAuto-check passed

  • Lineth Quickstart

    LFDT-Lineth/lineth-monorepo

    Operating manual for the Lineth Stack quickstart — the Docker-Compose dev/demo stack at docs/getting-started/lineth-stack in the lineth-monorepo that boots a local Linea/Lineth L2 with Sepolia or…

    126 GitHub stars~1k tokensUpdated today
    DevelopmentAuto-check: notes

  • Kermt Setup

    NVIDIA/skills

    Official

    Bootstrap the KERMT agent environment — verify host docker + nvidia-container-toolkit, build the kermt:latest image from the repo's Dockerfile if it doesn't yet exist, and run a GPU smoke test…

    3.5k GitHub starsUsed in 1 repo~1.7k tokens
    DevOps & CloudAuto-check passed

More from open-edge-platform/edge-ai-suites

All 13 skills in this repo

  • Onboarding Validation

    open-edge-platform/edge-ai-suites

    Validate the get-started experience of Open Edge Platform (OEP) software components from the perspective of a first-time user.

    140 GitHub stars~3.3k tokensUpdated today
    Auto-check passed

  • Sc QA

    open-edge-platform/edge-ai-suites

    Ask a natural-language question against indexed content via the Content Search RAG Q&A endpoint.

    140 GitHub stars~2.3k tokensUpdated today
    Auto-check passed

  • Sc Upload

    open-edge-platform/edge-ai-suites

    Upload a file to the Content Search backend and poll the ingestion task until the file is fully indexed (status COMPLETED).

    140 GitHub stars~2.6k tokensUpdated today
    Auto-check passed

  • Uav Vision Analytics

    open-edge-platform/edge-ai-suites

    Build an end-to-end UAV object detection and telemetry overlay application on Intel hardware using DL Streamer Pipeline Server with MAVLink telemetry.

    140 GitHub stars~2.6k tokensUpdated today
    Auto-check: notes

  • Knowledgebase

    open-edge-platform/edge-ai-suites

    Generic RAG query skill - Retrieve any information from the local knowledge base and generate structured reports, summaries, or Q&A responses.

    140 GitHub stars~900 tokensUpdated today
    Auto-check passed

  • Sc Doctor

    open-edge-platform/edge-ai-suites

    Diagnose Content Search backend availability by probing the health endpoint, then surface connectivity issues between Flutter and backend when unhealthy.

    140 GitHub stars~1.4k tokensUpdated today
    Auto-check: notes

Works with

Categories

Questions about Lvc Run App

What does Lvc Run App do?

Run, start, or smoke-test the Live Video Captioning app (Docker Compose stack with dashboard on :4173). Lvc Run App is an agent skill from open-edge-platform/edge-ai-suites. Run, start, or smoke-test the Live Video Captioning app (Docker Compose stack with dashboard on :4173).

When should I use Lvc Run App?

Lvc Run App fits situations like: launch the stack; start a captioning run against an RTSP stream; verify captions flow; check the dashboard.

How do I install Lvc Run App in Claude Code?

Run `npx skills add open-edge-platform/edge-ai-suites --skill lvc-run-app -a claude-code`. Or copy the skill folder (metro-ai-suite/live-video-analysis/live-video-captioning/.github/skills/lvc-run-app in open-edge-platform/edge-ai-suites) into .claude/skills/lvc-run-app in your project. Claude Code loads it when a task matches its description.

How do I install Lvc Run App in Codex?

Run `npx skills add open-edge-platform/edge-ai-suites --skill lvc-run-app -a codex`. Or copy the skill folder (metro-ai-suite/live-video-analysis/live-video-captioning/.github/skills/lvc-run-app in open-edge-platform/edge-ai-suites) into .agents/skills/lvc-run-app in your project. Codex loads it when a task matches its description.

Can I use Lvc Run App in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add open-edge-platform/edge-ai-suites --skill lvc-run-app -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/lvc-run-app, .gemini/skills/lvc-run-app, .github/skills/lvc-run-app and .opencode/skills/lvc-run-app in your project.

What does Lvc Run App need to run?

Going by SKILL.md and its folder, Lvc Run App needs a shell for the scripts in its folder and the command-line tools its instructions call (docker and curl). Our summary lists: A Bash shell; Docker.

Does Lvc Run App access the network?

SKILL.md contains no URLs. Its commands use docker and curl, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Lvc Run App safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Lvc Run App use?

Lvc Run App is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Lvc Run App use?

About 796 tokens (SKILL.md is roughly 3.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Lvc Run App?

Skills that share tags, products or a category with Lvc Run App: DeerFlow Smoke Test (bytedance/deer-flow, 84k stars), Sceneeye Maintenance (isetbio/isetbio, 115 stars), PR Test (Elite588/AUTOGPT, 103 stars) and Pgjev (realZachi/pg-jev, 1.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Lvc Run App?

open-edge-platform (a GitHub organization) maintains it in open-edge-platform/edge-ai-suites, which has 140 GitHub stars. The repository holds 13 skills in this directory. The repository was last updated on October 9, 2026.

Source: open-edge-platform/edge-ai-suites on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.