vision-analysis

Name: vision-analysis
Author: nguyenphp

39stars12forks

How to install vision-analysis?

nguyenphp/antigravity-marketing/vision-analysis

$npx -y skills add nguyenphp/antigravity-marketing --skill vision-analysis

Installs into the current project.

Summary

Analyze, describe, and extract information from images using the MiniMax vision MCP tool. Use when: user shares an image file path or URL (any message containing .jpg, .jpeg, .png, .gif, .webp, .bmp, or .svg file extension) or uses any of these words/phrases near an image: "analy

Files · 1

View on GitHub

SKILL.md

1	# Vision Analysis
2
3	Analyze images using the MiniMax `MiniMax_understand_image` MCP tool available in the MiniMax Token Plan.
4
5	## Prerequisites
6
7	- MiniMax Token Plan subscription with valid `MINIMAX_API_KEY`
8	- MiniMax MCP configured (`MiniMax_understand_image` tool available)
9
10	### If MCP tool is not configured
11
12	Step 1: The agent should fetch setup instructions from:
13	https://platform.minimaxi.com/docs/token-plan/mcp-guide
14
15	Step 2: Detect the user's environment (OpenCode, Cursor, Claude Code, etc.) and output the exact commands needed. Common examples:
16
17	OpenCode — add to `~/.config/opencode/opencode.json` or `package.json`:
18	```json
19	{
20	"mcp": {
21	"MiniMax": {
22	"type": "local",
23	"command": ["uvx", "minimax-coding-plan-mcp", "-y"],
24	"environment": {
25	"MINIMAX_API_KEY": "YOUR_TOKEN_PLAN_KEY",
26	"MINIMAX_API_HOST": "https://api.minimaxi.com"
27	},
28	"enabled": true
29	}
30	}
31	}
32	```
33
34	Claude Code:
35	```bash
36	claude mcp add -s user MiniMax --env MINIMAX_API_KEY=your-key --env MINIMAX_API_HOST=https://api.minimaxi.com -- uvx minimax-coding-plan-mcp -y
37	```
38
39	Cursor — add to MCP settings:
40	```json
41	{
42	"mcpServers": {
43	"MiniMax": {
44	"command": "uvx",
45	"args": ["minimax-coding-plan-mcp"],
46	"env": {
47	"MINIMAX_API_KEY": "your-key",
48	"MINIMAX_API_HOST": "https://api.minimaxi.com"
49	}
50	}
51	}
52	}
53	```
54
55	Step 3: After configuration, tell the user to restart their app and verify with `/mcp`.
56
57	Important: If the user does not have a MiniMax Token Plan subscription, inform them that the `understand_image` tool requires one — it cannot be used with free or other tier API keys.
58
59	## Analysis Modes
60
61	\| Mode \| When to use \| Prompt strategy \|
62	\|---\|---\|---\|
63	\| `describe` \| General image understanding \| Ask for detailed description \|
64	\| `ocr` \| Text extraction from screenshots, documents \| Ask to extract all text verbatim \|
65	\| `ui-review` \| UI mockups, wireframes, design files \| Ask for design critique with suggestions \|
66	\| `chart-data` \| Charts, graphs, data visualizations \| Ask to extract data points and trends \|
67	\| `object-detect` \| Identify objects, people, activities \| Ask to list and locate all elements \|
68
69	## Workflow
70
71	### Step 1: Auto-detect image
72
73	The skill triggers automatically when a message contains an image file path or URL with extensions:
74	`.jpg`, `.jpeg`, `.png`, `.gif`, `.webp`, `.bmp`, `.svg`
75
76	Extract the image path from the message.
77
78	### Step 2: Select analysis mode and call MCP tool
79
80	Use the `MiniMax_understand_image` tool with a mode-specific prompt:
81
82	describe:
83	```
84	Provide a detailed description of this image. Include: main subject, setting/background,
85	colors/style, any text visible, notable objects, and overall composition.
86	```
87
88	ocr:
89	```
90	Extract all text visible in this image verbatim. Preserve structure and formatting
91	(headers, lists, columns). If no text is found, say so.
92	```
93
94	ui-review:
95	```
96	You are a UI/UX design reviewer. Analyze this interface mockup or design. Provide:
97	(1) Strengths — what works well, (2) Issues — usability or design problems,
98	(3) Specific, actionable suggestions for improvement. Be constructive and detailed.
99	```
100
101	chart-data:
102	```
103	Extract all data from this chart or graph. List: chart title, axis labels, all
104	data points/series with values if readable, and a brief summary of the trend.
105	```
106
107	object-detect:
108	```
109	List all distinct objects, people, and activities you can identify. For each,
110	describe what it is and its approximate location in the image.
111	```
112
113	### Step 3: Present results
114
115	Return the analysis clearly. For `describe`, use readable prose. For `ocr`, preserve structure. For `ui-review`, use a structured critique format.
116
117	## Output Format Example
118
119	For describe mode:
120	```
121	## Image Description
122
123	[Detailed description of the image contents...]
124	```
125
126	Fo

People who liked this also viewed

6 picks

Type

vision-analysis

39stars12forks

View on GitHub

How to install vision-analysis?

nguyenphp/antigravity-marketing/vision-analysis

$npx -y skills add nguyenphp/antigravity-marketing --skill vision-analysis

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Vision Analysis
2
3	Analyze images using the MiniMax `MiniMax_understand_image` MCP tool available in the MiniMax Token Plan.
4
5	## Prerequisites
6
7	- MiniMax Token Plan subscription with valid `MINIMAX_API_KEY`
8	- MiniMax MCP configured (`MiniMax_understand_image` tool available)
9
10	### If MCP tool is not configured
11
12	Step 1: The agent should fetch setup instructions from:
13	https://platform.minimaxi.com/docs/token-plan/mcp-guide
14
15	Step 2: Detect the user's environment (OpenCode, Cursor, Claude Code, etc.) and output the exact commands needed. Common examples:
16
17	OpenCode — add to `~/.config/opencode/opencode.json` or `package.json`:
18	```json
19	{
20	"mcp": {
21	"MiniMax": {
22	"type": "local",
23	"command": ["uvx", "minimax-coding-plan-mcp", "-y"],
24	"environment": {
25	"MINIMAX_API_KEY": "YOUR_TOKEN_PLAN_KEY",
26	"MINIMAX_API_HOST": "https://api.minimaxi.com"
27	},
28	"enabled": true
29	}
30	}
31	}
32	```
33
34	Claude Code:
35	```bash
36	claude mcp add -s user MiniMax --env MINIMAX_API_KEY=your-key --env MINIMAX_API_HOST=https://api.minimaxi.com -- uvx minimax-coding-plan-mcp -y
37	```
38
39	Cursor — add to MCP settings:
40	```json
41	{
42	"mcpServers": {
43	"MiniMax": {
44	"command": "uvx",
45	"args": ["minimax-coding-plan-mcp"],
46	"env": {
47	"MINIMAX_API_KEY": "your-key",
48	"MINIMAX_API_HOST": "https://api.minimaxi.com"
49	}
50	}
51	}
52	}
53	```
54
55	Step 3: After configuration, tell the user to restart their app and verify with `/mcp`.
56
57	Important: If the user does not have a MiniMax Token Plan subscription, inform them that the `understand_image` tool requires one — it cannot be used with free or other tier API keys.
58
59	## Analysis Modes
60
61	\| Mode \| When to use \| Prompt strategy \|
62	\|---\|---\|---\|
63	\| `describe` \| General image understanding \| Ask for detailed description \|
64	\| `ocr` \| Text extraction from screenshots, documents \| Ask to extract all text verbatim \|
65	\| `ui-review` \| UI mockups, wireframes, design files \| Ask for design critique with suggestions \|
66	\| `chart-data` \| Charts, graphs, data visualizations \| Ask to extract data points and trends \|
67	\| `object-detect` \| Identify objects, people, activities \| Ask to list and locate all elements \|
68
69	## Workflow
70
71	### Step 1: Auto-detect image
72
73	The skill triggers automatically when a message contains an image file path or URL with extensions:
74	`.jpg`, `.jpeg`, `.png`, `.gif`, `.webp`, `.bmp`, `.svg`
75
76	Extract the image path from the message.
77
78	### Step 2: Select analysis mode and call MCP tool
79
80	Use the `MiniMax_understand_image` tool with a mode-specific prompt:
81
82	describe:
83	```
84	Provide a detailed description of this image. Include: main subject, setting/background,
85	colors/style, any text visible, notable objects, and overall composition.
86	```
87
88	ocr:
89	```
90	Extract all text visible in this image verbatim. Preserve structure and formatting
91	(headers, lists, columns). If no text is found, say so.
92	```
93
94	ui-review:
95	```
96	You are a UI/UX design reviewer. Analyze this interface mockup or design. Provide:
97	(1) Strengths — what works well, (2) Issues — usability or design problems,
98	(3) Specific, actionable suggestions for improvement. Be constructive and detailed.
99	```
100
101	chart-data:
102	```
103	Extract all data from this chart or graph. List: chart title, axis labels, all
104	data points/series with values if readable, and a brief summary of the trend.
105	```
106
107	object-detect:
108	```
109	List all distinct objects, people, and activities you can identify. For each,
110	describe what it is and its approximate location in the image.
111	```
112
113	### Step 3: Present results
114
115	Return the analysis clearly. For `describe`, use readable prose. For `ocr`, preserve structure. For `ui-review`, use a structured critique format.
116
117	## Output Format Example
118
119	For describe mode:
120	```
121	## Image Description
122
123	[Detailed description of the image contents...]
124	```
125
126	Fo

People who liked this also viewed

6 picks

Type