qwencloud-vision

Name: qwencloud-vision
Author: QwenCloud

32stars0forks

How to install qwencloud-vision?

qwencloud/qwencloud-ai/qwencloud-vision

$npx -y skills add QwenCloud/qwencloud-ai --skill qwencloud-vision

Installs into the current project.

Summary

[QwenCloud] Understand images and videos with Qwen vision models. TRIGGER when: user wants to analyze, describe, or extract information from images or videos, OCR text extraction, chart/table reading, visual reasoning, multi-image comparison, screenshot understanding, video compr

Files · 1

View on GitHub

SKILL.md

1	> Agent setup: If your agent doesn't auto-load skills (e.g. Claude Code),
2	> see [agent-compatibility.md](references/agent-compatibility.md) once per session.
3
4	# Qwen Vision (Image & Video Understanding)
5
6	Analyze images and videos using Qwen VL and QVQ models.
7	This skill is part of qwencloud/qwencloud-ai.
8
9	## Skill directory
10
11	Use this skill's internal files to execute and learn. Load reference files on demand when the default path fails or you need details.
12
13	\| Location \| Purpose \|
14	\|----------\|---------\|
15	\| `scripts/analyze.py` \| Image/video understanding, multi-image, thinking mode \|
16	\| `scripts/reason.py` \| Visual reasoning (QVQ, chain-of-thought, streaming) \|
17	\| `scripts/ocr.py` \| OCR text extraction \|
18	\| `scripts/vision_lib.py` \| Shared helpers (base64, upload, streaming) \|
19	\| `references/execution-guide.md` \| Fallback: curl, code generation \|
20	\| `references/curl-examples.md` \| Curl for base64, multi-image, video, OCR \|
21	\| `references/visual-reasoning.md` \| QVQ and thinking mode details \|
22	\| `references/prompt-guide.md` \| Query prompt templates by task, thinking mode decision \|
23	\| `references/ocr.md` \| OCR parameters and examples \|
24	\| `references/sources.md` \| Official documentation URLs \|
25	\| `references/agent-compatibility.md` \| Agent self-check: register skills in project config for agents that don't auto-load \|
26
27	## Security
28
29	NEVER output any API key or credential in plaintext. Always use variable references (`$DASHSCOPE_API_KEY` in shell, `os.environ["DASHSCOPE_API_KEY"]` in Python). Any check or detection of credentials must be non-plaintext: report only status (e.g. "set" / "not set", "valid" / "invalid"), never the value. Never display contents of `.env` or config files that may contain secrets.
30
31	When the API key is not configured, NEVER ask the user to provide it directly. Instead, help create a `.env` file with a placeholder (`DASHSCOPE_API_KEY=sk-your-key-here`) and instruct the user to replace it with their actual key from the [QwenCloud Console](https://home.qwencloud.com/api-keys). Only write the actual key value if the user explicitly requests it.
32
33	## Key Compatibility
34
35	Scripts require a standard QwenCloud API key (`sk-...`). Coding Plan keys (`sk-sp-...`) cannot be used for direct API calls and do not support dedicated vision models (qwen3-vl-plus, qvq-max, etc.). The scripts detect `sk-sp-` keys at startup and print a warning. If qwencloud-ops-auth is installed, see its `references/codingplan.md` for full details.
36
37	## Model Selection
38
39	\| Model \| Use Case \|
40	\|-------\|----------\|
41	\| qwen3.6-plus \| Preferred — latest flagship, unified multimodal (text+image+video). Thinking on by default. Best balance of quality, speed, cost. \|
42	\| qwen3.5-plus \| Unified multimodal (text+image+video). Thinking on by default. \|
43	\| qwen3.5-flash \| Fast multimodal — cheaper, faster. Thinking on by default. \|
44	\| qwen3-vl-plus \| High-precision — object localization (2D/3D), document/webpage parsing. \|
45	\| qwen3-vl-flash \| Fast vision — lower latency, 33 languages. \|
46	\| qvq-max \| Visual reasoning — chain-of-thought for math, charts. Streaming only. \|
47	\| qwen-vl-ocr \| OCR — text extraction, table parsing, document scanning. \|
48	\| qwen-vl-max \| Qwen2.5-VL — best-performing in 2.5 series. \|
49	\| qwen-vl-plus \| Qwen2.5-VL — faster, good balance of performance and cost, 11 languages. \|
50
51	1. User specified a model → use directly.
52	2. Consult the qwencloud-model-selector skill when model choice depends on requirement, scenario, or pricing.
53	3. No signal, clear task → `qwen3.6-plus`. Use `qwen3-vl-plus` for precise localization or 3D detection.
54
55	> ⚠️ Important: The model list above is a point-in-time snapshot and may be outdated. Model availability
56	> changes frequently. **Always check the [official model list](https://www.qwencloud.com/models)
57	> for the authoritative, up-to-date catalog before making model decisions.**
58
59	> Model details: For more information about a specific model, direct the user to its detail page: `https://www.qwencloud.com/models/<model-name>` (replace `<model-name>` with the exact model ID, e.g. `qwen3.6-plus` → https://www.qwencloud.com/models/qwen3.6-plus). NEVER modify or guess the model name in the URL.
60
61	> **Dyna

People who liked this also viewed

6 picks

Type

qwencloud-vision

32stars0forks

View on GitHub

How to install qwencloud-vision?

qwencloud/qwencloud-ai/qwencloud-vision

$npx -y skills add QwenCloud/qwencloud-ai --skill qwencloud-vision

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	> Agent setup: If your agent doesn't auto-load skills (e.g. Claude Code),
2	> see [agent-compatibility.md](references/agent-compatibility.md) once per session.
3
4	# Qwen Vision (Image & Video Understanding)
5
6	Analyze images and videos using Qwen VL and QVQ models.
7	This skill is part of qwencloud/qwencloud-ai.
8
9	## Skill directory
10
11	Use this skill's internal files to execute and learn. Load reference files on demand when the default path fails or you need details.
12
13	\| Location \| Purpose \|
14	\|----------\|---------\|
15	\| `scripts/analyze.py` \| Image/video understanding, multi-image, thinking mode \|
16	\| `scripts/reason.py` \| Visual reasoning (QVQ, chain-of-thought, streaming) \|
17	\| `scripts/ocr.py` \| OCR text extraction \|
18	\| `scripts/vision_lib.py` \| Shared helpers (base64, upload, streaming) \|
19	\| `references/execution-guide.md` \| Fallback: curl, code generation \|
20	\| `references/curl-examples.md` \| Curl for base64, multi-image, video, OCR \|
21	\| `references/visual-reasoning.md` \| QVQ and thinking mode details \|
22	\| `references/prompt-guide.md` \| Query prompt templates by task, thinking mode decision \|
23	\| `references/ocr.md` \| OCR parameters and examples \|
24	\| `references/sources.md` \| Official documentation URLs \|
25	\| `references/agent-compatibility.md` \| Agent self-check: register skills in project config for agents that don't auto-load \|
26
27	## Security
28
29	NEVER output any API key or credential in plaintext. Always use variable references (`$DASHSCOPE_API_KEY` in shell, `os.environ["DASHSCOPE_API_KEY"]` in Python). Any check or detection of credentials must be non-plaintext: report only status (e.g. "set" / "not set", "valid" / "invalid"), never the value. Never display contents of `.env` or config files that may contain secrets.
30
31	When the API key is not configured, NEVER ask the user to provide it directly. Instead, help create a `.env` file with a placeholder (`DASHSCOPE_API_KEY=sk-your-key-here`) and instruct the user to replace it with their actual key from the [QwenCloud Console](https://home.qwencloud.com/api-keys). Only write the actual key value if the user explicitly requests it.
32
33	## Key Compatibility
34
35	Scripts require a standard QwenCloud API key (`sk-...`). Coding Plan keys (`sk-sp-...`) cannot be used for direct API calls and do not support dedicated vision models (qwen3-vl-plus, qvq-max, etc.). The scripts detect `sk-sp-` keys at startup and print a warning. If qwencloud-ops-auth is installed, see its `references/codingplan.md` for full details.
36
37	## Model Selection
38
39	\| Model \| Use Case \|
40	\|-------\|----------\|
41	\| qwen3.6-plus \| Preferred — latest flagship, unified multimodal (text+image+video). Thinking on by default. Best balance of quality, speed, cost. \|
42	\| qwen3.5-plus \| Unified multimodal (text+image+video). Thinking on by default. \|
43	\| qwen3.5-flash \| Fast multimodal — cheaper, faster. Thinking on by default. \|
44	\| qwen3-vl-plus \| High-precision — object localization (2D/3D), document/webpage parsing. \|
45	\| qwen3-vl-flash \| Fast vision — lower latency, 33 languages. \|
46	\| qvq-max \| Visual reasoning — chain-of-thought for math, charts. Streaming only. \|
47	\| qwen-vl-ocr \| OCR — text extraction, table parsing, document scanning. \|
48	\| qwen-vl-max \| Qwen2.5-VL — best-performing in 2.5 series. \|
49	\| qwen-vl-plus \| Qwen2.5-VL — faster, good balance of performance and cost, 11 languages. \|
50
51	1. User specified a model → use directly.
52	2. Consult the qwencloud-model-selector skill when model choice depends on requirement, scenario, or pricing.
53	3. No signal, clear task → `qwen3.6-plus`. Use `qwen3-vl-plus` for precise localization or 3D detection.
54
55	> ⚠️ Important: The model list above is a point-in-time snapshot and may be outdated. Model availability
56	> changes frequently. **Always check the [official model list](https://www.qwencloud.com/models)
57	> for the authoritative, up-to-date catalog before making model decisions.**
58
59	> Model details: For more information about a specific model, direct the user to its detail page: `https://www.qwencloud.com/models/<model-name>` (replace `<model-name>` with the exact model ID, e.g. `qwen3.6-plus` → https://www.qwencloud.com/models/qwen3.6-plus). NEVER modify or guess the model name in the URL.
60
61	> **Dyna

People who liked this also viewed

6 picks

Type