Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 16 additions & 0 deletions .claude-plugin/marketplace.json
Original file line number Diff line number Diff line change
Expand Up @@ -59,6 +59,22 @@
"perplexity"
]
},
{
"name": "minimax",
"description": "Configure MiniMax text models, regional API endpoints, capabilities, thinking behavior, and token pricing.",
"source": "./dist/plugins/minimax",
"strict": false,
"skills": [
"./skills/minimax"
],
"category": "ai-tools",
"keywords": [
"ai",
"minimax",
"regional-endpoints",
"model-configuration"
]
},
{
"name": "agent-md-refactor",
"description": "Refactor bloated AGENTS.md, CLAUDE.md, or similar agent instruction files to follow progressive disclosure principles. Splits monolithic files into organized, linked documentation.",
Expand Down
1 change: 1 addition & 0 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -98,6 +98,7 @@ Add skills to project knowledge or paste SKILL.md contents into the conversation
|----------|-------|-------------|
| 🤖 AI Tools | [codex](skills/codex/README.md) | Advanced code analysis with GPT-5.2 |
| 🤖 AI Tools | [gemini](skills/gemini/README.md) | Large-scale review (200k+ context) |
| 🤖 AI Tools | [minimax](skills/minimax/README.md) | Regional model configuration |
| 🤖 AI Tools | [perplexity](skills/perplexity/README.md) | Web search & research |
| 🔮 Meta | [agent-md-refactor](skills/agent-md-refactor/README.md) | Refactor bloated agent instruction files |
| 🔮 Meta | [command-creator](skills/command-creator/README.md) | Create Claude Code slash commands |
Expand Down
31 changes: 31 additions & 0 deletions dist/plugins/minimax/skills/minimax/README.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,31 @@
# MiniMax Skill

Configure MiniMax text models with the correct regional API base, model capabilities, thinking behavior, and token pricing.

## When to Use

Use this skill when a request mentions:

- MiniMax API configuration
- `MiniMax-M3` or `MiniMax-M2.7`
- Global or China-region MiniMax endpoints
- MiniMax model capabilities, thinking behavior, or cost estimates

## What It Covers

- Region selection for `global_en` and `cn_zh`
- Chat completions and messages API base URLs
- Model selection for text, image, and video inputs
- Context windows and thinking behavior
- Input, output, and cache token pricing
- API key handling through `MINIMAX_API_KEY`

## Installation

Install the plugin from the Agent Toolkit marketplace:

```text
/plugin install minimax@agent-toolkit
```

Then ask the agent to configure MiniMax, select a region or model, or estimate token costs. See `SKILL.md` for the full workflow and current configuration tables.
52 changes: 52 additions & 0 deletions dist/plugins/minimax/skills/minimax/SKILL.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,52 @@
---
name: minimax
description: Configure MiniMax text models, regional API endpoints, capabilities, thinking behavior, and token pricing. Use when users mention MiniMax-M3, MiniMax-M2.7, MiniMax API setup, or MiniMax regions.
---

# MiniMax Provider Guide

Use this skill when configuring a MiniMax text model or selecting a MiniMax API region.

## Configuration Workflow

1. Ask which region the user needs: `global_en` or `cn_zh`. Default to `global_en` only when no region is specified.
2. Ask whether the integration uses the chat completions API or the messages API.
3. Select the model from the capability table below.
4. Use the matching regional base URL. Do not combine endpoints from different regions.
5. Read the API key from `MINIMAX_API_KEY`. Never print, log, or commit it.
6. Present the chosen model, region, API style, base URL, and capability assumptions before making changes.

## Regional Endpoints

| Region | Chat completions base URL | Messages base URL | Documentation |
| --- | --- | --- | --- |
| `global_en` | `https://api.minimax.io/v1` | `https://api.minimax.io/anthropic` | `https://platform.minimax.io/docs` |
| `cn_zh` | `https://api.minimaxi.com/v1` | `https://api.minimaxi.com/anthropic` | `https://platform.minimaxi.com/docs` |

## Model Selection

| Model | Context window | Input modalities | Thinking behavior |
| --- | ---: | --- | --- |
| `MiniMax-M3` | 1,000,000 tokens | text, image, video | adaptive or disabled |
| `MiniMax-M2.7` | 204,800 tokens | text | always on |

Choose `MiniMax-M3` when the request needs image or video input, a context window above 204,800 tokens, or configurable thinking. Choose `MiniMax-M2.7` for text-only requests that require always-on thinking.

## Token Pricing

Prices are in USD per million tokens.

| Model | Input | Output | Cache read | Cache write |
| --- | ---: | ---: | ---: | ---: |
| `MiniMax-M3` | $0.60 | $2.40 | $0.12 | Not specified |
| `MiniMax-M2.7` | $0.30 | $1.20 | $0.06 | $0.375 |

Use these values for estimates only. State the assumptions and calculate each token category separately.

## Validation Checklist

- The model ID is exactly `MiniMax-M3` or `MiniMax-M2.7`.
- The endpoint belongs to the selected region.
- Image and video inputs are used only with `MiniMax-M3`.
- Thinking is always on for `MiniMax-M2.7`.
- The API key remains in `MINIMAX_API_KEY` and is never included in output.
31 changes: 31 additions & 0 deletions skills/minimax/README.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,31 @@
# MiniMax Skill

Configure MiniMax text models with the correct regional API base, model capabilities, thinking behavior, and token pricing.

## When to Use

Use this skill when a request mentions:

- MiniMax API configuration
- `MiniMax-M3` or `MiniMax-M2.7`
- Global or China-region MiniMax endpoints
- MiniMax model capabilities, thinking behavior, or cost estimates

## What It Covers

- Region selection for `global_en` and `cn_zh`
- Chat completions and messages API base URLs
- Model selection for text, image, and video inputs
- Context windows and thinking behavior
- Input, output, and cache token pricing
- API key handling through `MINIMAX_API_KEY`

## Installation

Install the plugin from the Agent Toolkit marketplace:

```text
/plugin install minimax@agent-toolkit
```

Then ask the agent to configure MiniMax, select a region or model, or estimate token costs. See `SKILL.md` for the full workflow and current configuration tables.
52 changes: 52 additions & 0 deletions skills/minimax/SKILL.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,52 @@
---
name: minimax
description: Configure MiniMax text models, regional API endpoints, capabilities, thinking behavior, and token pricing. Use when users mention MiniMax-M3, MiniMax-M2.7, MiniMax API setup, or MiniMax regions.
---

# MiniMax Provider Guide

Use this skill when configuring a MiniMax text model or selecting a MiniMax API region.

## Configuration Workflow

1. Ask which region the user needs: `global_en` or `cn_zh`. Default to `global_en` only when no region is specified.
2. Ask whether the integration uses the chat completions API or the messages API.
3. Select the model from the capability table below.
4. Use the matching regional base URL. Do not combine endpoints from different regions.
5. Read the API key from `MINIMAX_API_KEY`. Never print, log, or commit it.
6. Present the chosen model, region, API style, base URL, and capability assumptions before making changes.

## Regional Endpoints

| Region | Chat completions base URL | Messages base URL | Documentation |
| --- | --- | --- | --- |
| `global_en` | `https://api.minimax.io/v1` | `https://api.minimax.io/anthropic` | `https://platform.minimax.io/docs` |
| `cn_zh` | `https://api.minimaxi.com/v1` | `https://api.minimaxi.com/anthropic` | `https://platform.minimaxi.com/docs` |

## Model Selection

| Model | Context window | Input modalities | Thinking behavior |
| --- | ---: | --- | --- |
| `MiniMax-M3` | 1,000,000 tokens | text, image, video | adaptive or disabled |
| `MiniMax-M2.7` | 204,800 tokens | text | always on |

Choose `MiniMax-M3` when the request needs image or video input, a context window above 204,800 tokens, or configurable thinking. Choose `MiniMax-M2.7` for text-only requests that require always-on thinking.

## Token Pricing

Prices are in USD per million tokens.

| Model | Input | Output | Cache read | Cache write |
| --- | ---: | ---: | ---: | ---: |
| `MiniMax-M3` | $0.60 | $2.40 | $0.12 | Not specified |
| `MiniMax-M2.7` | $0.30 | $1.20 | $0.06 | $0.375 |

Use these values for estimates only. State the assumptions and calculate each token category separately.

## Validation Checklist

- The model ID is exactly `MiniMax-M3` or `MiniMax-M2.7`.
- The endpoint belongs to the selected region.
- Image and video inputs are used only with `MiniMax-M3`.
- Thinking is always on for `MiniMax-M2.7`.
- The API key remains in `MINIMAX_API_KEY` and is never included in output.