Alicloud Ai Multimodal Qvq Test

Name: Alicloud Ai Multimodal Qvq Test
Author: cinience

cinience/alicloud-skills

120 installs
396 repo stars
Updated July 18, 2026
cinience/alicloud-skills

Test and integrate Alibaba QVQ multimodal vision-language models for image Q&A, document understanding, and visual reasoning inside agent-built features.

About

Integration skill for Alibaba QVQ multimodal models: send image-plus-text requests, parse vision-language answers, and run test calls for document understanding and visual Q&A so agents embed VLM features without bespoke SDK work.

QVQ multimodal API wiring
Image Q&A and doc understanding
Vision-language inference tests
Structured multimodal responses
Agent-friendly VLM hooks

Alicloud Ai Multimodal Qvq Test by the numbers

120 all-time installs (skills.sh)
Ranked #3,814 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
Data as of Aug 5, 2026 (Skillselion catalog sync)

npx skills add https://github.com/cinience/alicloud-skills --skill alicloud-ai-multimodal-qvq-test

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

[![Listed on Skillselion](https://skillselion.com/badge/skills/cinience/alicloud-skills/alicloud-ai-multimodal-qvq-test.svg)](https://skillselion.com/skills/cinience/alicloud-skills/alicloud-ai-multimodal-qvq-test)

Installs	120
repo stars	★ 396
Last updated	July 18, 2026
Repository	cinience/alicloud-skills ↗

What it does

Test and integrate Alibaba QVQ multimodal vision-language models for image Q&A, document understanding, and visual reasoning inside agent-built features.

Files

SKILL.mdMarkdownGitHub ↗

Category: service

Cloud Backup

Use Alibaba Cloud OpenAPI (RPC) with official SDKs or OpenAPI Explorer to manage resources for Cloud Backup.

Workflow

1) Confirm region, resource identifiers, and desired action. 2) Discover API list and required parameters (see references). 3) Call API with SDK or OpenAPI Explorer. 4) Verify results with describe/list APIs.

AccessKey priority (must follow)

1) Environment variables: ALIBABACLOUD_ACCESS_KEY_ID / ALIBABACLOUD_ACCESS_KEY_SECRET / ALIBABACLOUD_REGION_ID Region policy: ALIBABACLOUD_REGION_ID is an optional default. If unset, decide the most reasonable region for the task; if unclear, ask the user. 2) Shared config file: ~/.alibabacloud/credentials

API discovery

Product code: hbr
Default API version: 2017-09-08
Use OpenAPI metadata endpoints to list APIs and get schemas (see references).

High-frequency operation patterns

1) Inventory/list: prefer List* / Describe* APIs to get current resources. 2) Change/configure: prefer Create* / Update* / Modify* / Set* APIs for mutations. 3) Status/troubleshoot: prefer Get* / Query* / Describe*Status APIs for diagnosis.

Minimal executable quickstart

Use metadata-first discovery before calling business APIs:

python scripts/list_openapi_meta_apis.py

Optional overrides:

python scripts/list_openapi_meta_apis.py --product-code <ProductCode> --version <Version>

The script writes API inventory artifacts under the skill output directory.

Output policy

If you need to save responses or generated artifacts, write them under: output/aliyun-hbr-backup/

Validation

mkdir -p output/aliyun-hbr-backup
for f in skills/backup/aliyun-hbr-backup/scripts/*.py; do
  python3 -m py_compile "$f"
done
echo "py_compile_ok" > output/aliyun-hbr-backup/validate.txt

Pass criteria: command exits 0 and output/aliyun-hbr-backup/validate.txt is generated.

Output And Evidence

Save artifacts, command outputs, and API response summaries under output/aliyun-hbr-backup/.
Include key parameters (region/resource id/time range) in evidence files for reproducibility.

Prerequisites

Configure least-privilege Alibaba Cloud credentials before execution.
Prefer environment variables: ALIBABACLOUD_ACCESS_KEY_ID, ALIBABACLOUD_ACCESS_KEY_SECRET, optional ALIBABACLOUD_REGION_ID.
If region is unclear, ask the user before running mutating operations.

References

Sources: references/sources.md

interface:
  display_name: "Alibaba Cloud Backup HBR"
  short_description: "Cloud Backup vault and job workflows"
  default_prompt: "Use $aliyun-hbr-backup to complete this backup task on Alibaba Cloud."

#!/usr/bin/env python3
"""Fetch OpenAPI metadata API list for one product/version and save to output/.

Env:
- OPENAPI_META_TIMEOUT (seconds, default: 20)
"""

from __future__ import annotations

import argparse
import json
import os
import pathlib
import urllib.request

DEFAULT_PRODUCT_CODE = "hbr"
DEFAULT_VERSION = "2017-09-08"
OUTPUT_DIR = pathlib.Path("output/aliyun-hbr-backup")


def fetch_json(url: str, timeout: int) -> dict:
    req = urllib.request.Request(url, headers={"User-Agent": "codex-skill"})
    with urllib.request.urlopen(req, timeout=timeout) as resp:
        return json.loads(resp.read().decode("utf-8"))


def main() -> None:
    parser = argparse.ArgumentParser()
    parser.add_argument("--product-code", default=DEFAULT_PRODUCT_CODE)
    parser.add_argument("--version", default=DEFAULT_VERSION)
    parser.add_argument("--output-dir", default=str(OUTPUT_DIR))
    args = parser.parse_args()

    timeout = int(os.getenv("OPENAPI_META_TIMEOUT", "20"))
    output_dir = pathlib.Path(args.output_dir)
    output_dir.mkdir(parents=True, exist_ok=True)

    url = (
        f"https://api.aliyun.com/meta/v1/products/{args.product_code}"
        f"/versions/{args.version}/api-docs.json"
    )
    payload = fetch_json(url, timeout)

    raw_apis = payload.get("apis", {})
    if isinstance(raw_apis, dict):
        api_names = sorted(raw_apis.keys())
    elif isinstance(raw_apis, list):
        names = []
        for item in raw_apis:
            if isinstance(item, dict):
                name = item.get("name") or item.get("apiName")
                if name:
                    names.append(name)
            elif isinstance(item, str):
                names.append(item)
        api_names = sorted(set(names))
    else:
        api_names = []

    json_file = output_dir / f"{args.product_code}_{args.version}_api_docs.json"
    md_file = output_dir / f"{args.product_code}_{args.version}_api_list.md"

    json_file.write_text(json.dumps(payload, ensure_ascii=False, indent=2), encoding="utf-8")
    md_lines = [
        f"# {args.product_code} {args.version} API List",
        "",
        f"- Source: {url}",
        f"- API count: {len(api_names)}",
        "",
    ]
    md_lines.extend([f"- `{name}`" for name in api_names])
    md_file.write_text("\n".join(md_lines) + "\n", encoding="utf-8")

    print(f"Saved: {json_file}")
    print(f"Saved: {md_file}")


if __name__ == "__main__":
    main()