MiniMax Skills is a collection of development skills, APIs, and configuration formats for AI coding agents. Developers use it to get structured guidance for frontend, backend, Android, iOS, and shader work across several technology stacks. Catalogue entries package its skills, agents, and plugins for use with coding assistants.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add MiniMax-AI/skills --skill vision-analysisgit clone --depth 1 https://github.com/MiniMax-AI/skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/minimax-ai/skills/vision-analysis)<a href="https://agentmods.dev/skills/minimax-ai/skills/vision-analysis"><img src="https://agentmods.dev/badge/skills/minimax-ai/skills/vision-analysis/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/minimax-ai/skills/vision-analysis"><img src="https://agentmods.dev/badge/skills/minimax-ai/skills/vision-analysis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 59 uvx/uv tool run commands without ==version create a rug-pull risk.Fix: Pin the version: uvx package-name==1.2.3
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00250 | $0.01374 |
| Opus 5.5 | $0.00100 | $0.00550 |
| Sonnet 5.5 | $0.00050 | $0.00275 |
| Haiku 4.5 | $0.00025 | $0.00137 |
Grade A, and why
vision-analysis scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
1 near-identical copy found in the catalogue:
- vision-analysis — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vision Analysis
Analyze images using the MiniMax MiniMax_understand_image MCP tool available in the MiniMax Token Plan.
Prerequisites
- MiniMax Token Plan subscription with valid
MINIMAX_API_KEY - MiniMax MCP configured (
MiniMax_understand_imagetool available)
If MCP tool is not configured
Step 1: The agent should fetch setup instructions from: https://platform.minimaxi.com/docs/token-plan/mcp-guide
Step 2: Detect the user's environment (OpenCode, Cursor, Claude Code, etc.) and output the exact commands needed. Common examples:
OpenCode — add to ~/.config/opencode/opencode.json or package.json:
{
"mcp": {
"MiniMax": {
"type": "local",
"command": ["uvx", "minimax-coding-plan-mcp", "-y"],
"environment": {
"MINIMAX_API_KEY": "YOUR_TOKEN_PLAN_KEY",
"MINIMAX_API_HOST": "https://api.minimaxi.com"
},
"enabled": true
}
}
}
Claude Code:
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
Cursor — add to MCP settings:
{
"mcpServers": {
"MiniMax": {
"command": "uvx",
"args": ["minimax-coding-plan-mcp"],
"env": {
"MINIMAX_API_KEY": "your-key",
"MINIMAX_API_HOST": "https://api.minimaxi.com"
}
}
}
}
Step 3: After configuration, tell the user to restart their app and verify with /mcp.
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.
Analysis Modes
| Mode | When to use | Prompt strategy |
|---|---|---|
describe |
General image understanding | Ask for detailed description |
ocr |
Text extraction from screenshots, documents | Ask to extract all text verbatim |
ui-review |
UI mockups, wireframes, design files | Ask for design critique with suggestions |
chart-data |
Charts, graphs, data visualizations | Ask to extract data points and trends |
object-detect |
Identify objects, people, activities | Ask to list and locate all elements |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2mo ago First seen · 175 lines · 250 tokens per session scan A a3b4720bfc5f
vision-analysis is a skill published in the GitHub repository MiniMax-AI/skills (13,743 stars, last pushed 6mo ago), licensed MIT. It adds 250 tokens to every session and 1,374 once invoked, about $0.0010 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
google-cloud-solution-agentic-analytics-spark-knowledge-catalog
Discovers requirements and designs an end-to-end governed agentic analytics solution using Knowledge Catalog and Managed Service for Apache Spark (Lightning Engine). Use when designing data science and analytics workflows across structured and unstructured distributed data (including in S3, Azure Blob, AlloyDB, and…
training-check
Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.
finetuning
Fine-tune models on Microsoft Foundry using SFT (supervised), DPO (preference), or RFT (reinforcement with graders). Covers dataset preparation, training job submission, deployment, and evaluation. USE FOR: fine-tune, SFT, DPO, RFT, training data, grader, distillation, fine-tuned model, training job, large file…