Model Download Dev

What it does

When your agent uses it

• A developer wants to: add a new plugin to the microservice
• Write tests for a plugin (including mocking subprocess calls
• The Ollama server)
• Debug a job stuck in downloading

Example prompts

• “downloading”
• “converting”
• “add plugin”
• “/model-download-dev”

Requirements

• Python 3
• Docker

Workflow steps

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

1. 1examples-prompts/plugin-blueprint.md for the reusable class skeleton
2. 2examples-prompts/new-downloader-plugin.md for the end-to-end wiring
3. 3examples-prompts/writing-tests.md for the unit-test shape

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:

  • curl
  • docker
  • python3

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

• Network

  No URLs in SKILL.md. Its commands use curl and docker, 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

Model Download Dev loads about 2k tokens when it runs, and up to ~7.2k if it reads all its reference files. Until then it costs about 224 tokens; SKILL.md has 572 words of instructions outside code blocks.

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

~224

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

~2k

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

~7.2k

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). 572 words, ~1,986 tokens.

name

model-download-dev

description

Extend, test, debug, or integrate the Model Download microservice codebase. Use this skill when a developer wants to: add a new plugin to the microservice; write tests for a plugin (including mocking subprocess calls, async methods, or the Ollama server); debug a job stuck in "downloading" or "converting"; understand the plugin interface or registration mechanism; trace how a request flows through ModelManager; extend the OpenVINO conversion parameters; add a new ModelHub value; or embed model-download into an app, Docker Compose stack, Helm deployment, CI/CD flow, or startup path. Trigger on phrases like "add plugin", "write test", "stuck job", "extend microservice", "plugin not working", "how does model_manager work", "mock subprocess", "register new hub", "integrate model-download", "call the model-download API", "poll model job", or "mount downloaded models".

argument-hint

Describe what you want to build or debug (e.g. "add a new downloader plugin for an internal model hub" or "wire model-download into our compose stack")

src/
├── api/
│   ├── main.py          ← FastAPI app, endpoints, job dispatch
│   └── models.py        ← Pydantic models, ModelHub enum, ModelType, Config
├── core/
│   ├── interfaces.py    ← ModelDownloadPlugin ABC (plugin_name, plugin_type, can_handle, download)
│   ├── model_manager.py ← Job lifecycle, ThreadPoolExecutor, status tracking
│   ├── plugin_registry.py ← Auto-discovery, activation check, find_plugin_for_model
│   └── plugin_venv.py   ← Per-plugin venv management
└── plugins/
    ├── __init__.py      ← PLUGINS tuple mapping — register module path + class name here
    ├── huggingface_plugin.py
    ├── ollama_plugin.py
    ├── openvino_plugin.py
    ├── ultralytics_plugin.py
    ├── geti_plugin.py
    ├── hls_plugin.py
    └── pipeline_zoo_models_plugin.py

PLUGINS = {
    # ... existing entries ...
    "myhub": ("src.plugins.myhub_plugin", "MyHubPlugin"),
}

# 1. Check service logs for exceptions
docker logs model-download 2>&1 | tail -100

# 2. Inspect the job status
curl -s http://localhost:8200/api/v1/jobs/<job-id>

# 3. Verify the plugin was activated and discovered
curl -s http://localhost:8200/api/v1/plugins

# 4. Test the plugin in isolation
python3 -c "
import asyncio
from src.plugins.myhub_plugin import MyHubPlugin
p = MyHubPlugin()
result = asyncio.run(p.download('my-model', '/tmp/test'))
print(result)
"

© 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/model-download/.github/skills/model-download-dev of open-edge-platform/edge-ai-libraries.

• SKILL.md
• evals/evals.json
• examples-prompts/new-downloader-plugin.md
• examples-prompts/plugin-blueprint.md
• examples-prompts/writing-tests.md
• references/integration-patterns.md
• references/plugin-architecture.md
• references/testing-patterns.md

Open the folder on GitHubat commit 3084578