minimax-mcp-usage

[DEPRECATED] Use /research skill with Zai MCP instead - Optimal patterns for MiniMax MCP tools

108 stars

Best use case

minimax-mcp-usage is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

[DEPRECATED] Use /research skill with Zai MCP instead - Optimal patterns for MiniMax MCP tools

Teams using minimax-mcp-usage should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/minimax-mcp-usage/SKILL.md --create-dirs "https://raw.githubusercontent.com/alfredolopez80/multi-agent-ralph-loop/main/.claude/skills/minimax-mcp-usage/skill.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/minimax-mcp-usage/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How minimax-mcp-usage Compares

Feature / Agentminimax-mcp-usageStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

[DEPRECATED] Use /research skill with Zai MCP instead - Optimal patterns for MiniMax MCP tools

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

> **DEPRECATED (v2.88.0)**: This skill is deprecated. Use the `/research` skill instead, which leverages Zai MCP for comprehensive web search with better features:
> - No API key required (free)
> - Chinese content support (CSDN, Juejin, Linux.do)
> - GitHub README extraction
> - URL reader with markdown conversion
> - Domain and recency filtering
>
> See: `.claude/skills/research/SKILL.md`

**ultrathink** - Take a deep breath. We're not here to write code. We're here to make a dent in the universe.

## The Vision
MiniMax queries should be lean, accurate, and decisive.

## Your Work, Step by Step
1. **Choose tool**: web_search vs understand_image.
2. **Craft query**: Specific, time-bound, and focused.
3. **Run analysis**: Collect results with minimal noise.
4. **Synthesize**: Convert outputs into clear guidance.

## Ultrathink Principles in Practice
- **Think Different**: Use the lowest-cost path to truth.
- **Obsess Over Details**: Precision in queries matters.
- **Plan Like Da Vinci**: Decide intent before search.
- **Craft, Don't Code**: Keep results actionable.
- **Iterate Relentlessly**: Refine queries until clear.
- **Simplify Ruthlessly**: Cut vague or broad requests.

# MiniMax MCP Usage Patterns (v2.24)

This skill documents optimal usage patterns for MiniMax MCP tools.

## Available Tools

### 1. mcp__MiniMax__web_search

**Purpose:** Web search with 8% cost of alternatives

**Input:**
```yaml
query: string  # 3-5 keywords, include year for recent topics
```

**Output:**
```json
{
  "organic": [{ "title", "link", "snippet", "date" }],
  "related_searches": [{ "query" }]
}
```

**Optimal Patterns:**

```yaml
# Good: Specific, time-bounded
mcp__MiniMax__web_search:
  query: "React 19 useOptimistic hook examples 2025"

# Good: Error-focused
mcp__MiniMax__web_search:
  query: "TypeError cannot read property undefined Next.js"

# Bad: Too vague
mcp__MiniMax__web_search:
  query: "javascript"  # Too broad
```

### 2. mcp__MiniMax__understand_image

**Purpose:** Image analysis for debugging and review

**Input:**
```yaml
prompt: string       # Clear, specific question about the image
image_source: string # Local path (no @) or HTTPS URL
```

**Optimal Patterns:**

```yaml
# Good: Specific analysis request
mcp__MiniMax__understand_image:
  prompt: "Identify the exact error message and stack trace in this screenshot"
  image_source: "/tmp/error.png"

# Good: UI review
mcp__MiniMax__understand_image:
  prompt: "List all accessibility violations in this form design"
  image_source: "./mockup.png"

# Bad: Vague prompt
mcp__MiniMax__understand_image:
  prompt: "What's this?"  # Too vague
  image_source: "./image.png"
```

## Integration with Ralph Loop

```yaml
# Research phase: Use web_search
Task:
  prompt: |
    Research latest patterns for $TOPIC using mcp__MiniMax__web_search.
    Compile findings into structured report.

# Debugging phase: Use understand_image
Task:
  prompt: |
    Analyze error screenshot at $PATH using mcp__MiniMax__understand_image.
    Identify root cause and suggest fixes.
```

## Cost Analysis

| Operation | MiniMax MCP | Gemini CLI | Savings |
|-----------|-------------|------------|---------|
| Web search | ~$0.008 | ~$0.06 | 87% |
| Image analysis | ~$0.01 | N/A | New capability |

## When NOT to Use

| Scenario | Alternative |
|----------|-------------|
| US-only search | WebSearch (free) |
| Code search | ast-grep MCP (v2.23) |
| Long-form generation | Gemini CLI (1M context) |
| Real-time data | Native WebFetch |

## Troubleshooting

| Issue | Solution |
|-------|----------|
| "API key invalid" | Check MINIMAX_API_KEY in ~/.claude.json |
| "Image too large" | Compress to <20MB |
| "Format not supported" | Convert to JPEG/PNG/WebP |
| "No results" | Refine query with more keywords |

Related Skills

minimax

108
from alfredolopez80/multi-agent-ralph-loop

Custom skill for minimax

context7-usage

108
from alfredolopez80/multi-agent-ralph-loop

Patterns for using Context7 MCP for library documentation (v2.25)

worktree-pr

108
from alfredolopez80/multi-agent-ralph-loop

Manage git worktrees with PR workflow and multi-agent review (Claude + Codex). Use when developing features in isolation with easy rollback.

vercel-react-best-practices

108
from alfredolopez80/multi-agent-ralph-loop

React and Next.js performance optimization guidelines from Vercel Engineering. Use when writing, reviewing, or refactoring React/Next.js code. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.

vault

108
from alfredolopez80/multi-agent-ralph-loop

Living knowledge base management. Actions: search (query vault), save (store learning), index (update indices), compile (raw->wiki->rules graduation), init (create vault structure). Follows Karpathy pipeline: ingest->compile->query. Use when: (1) searching accumulated knowledge, (2) saving learnings, (3) compiling raw notes into wiki, (4) initializing a new vault. Triggers: /vault, 'vault search', 'knowledge base', 'save learning'.

testing-anti-patterns

108
from alfredolopez80/multi-agent-ralph-loop

Custom skill for testing-anti-patterns

task-visualizer

108
from alfredolopez80/multi-agent-ralph-loop

Visualize task dependencies and progress (Gastown-style)

task-classifier

108
from alfredolopez80/multi-agent-ralph-loop

Classifies task complexity (1-10) for model and agent routing

task-batch

108
from alfredolopez80/multi-agent-ralph-loop

Autonomous batch task execution with PRD parsing, task decomposition, and continuous execution until all tasks complete. Uses /orchestrator internally. Stops only for major failures (no internet, token limit, system crash). Use when: (1) processing task lists autonomously, (2) PRD-driven development, (3) batch feature implementation. Triggers: /task-batch, 'batch tasks', 'process PRD', 'run task queue'.

tap-explorer

108
from alfredolopez80/multi-agent-ralph-loop

Tree of Attacks with Pruning for systematic code analysis

stop-slop

108
from alfredolopez80/multi-agent-ralph-loop

A skill for removing AI-generated writing patterns ('slop') from prose. Eliminates telltale signs of AI writing like filler phrases, excessive hedging, overly formal language, and mechanical sentence structures. Use when: writing content that should sound human and natural, editing AI-generated drafts, cleaning up prose for publication, or any content that needs to sound authentic rather than AI-generated. Triggers: 'stop-slop', 'remove AI tells', 'clean up prose', 'make it sound human', 'edit AI writing'.

spec

108
from alfredolopez80/multi-agent-ralph-loop

Produce a verifiable technical specification before coding. 6 mandatory sections: Interfaces, Behaviors, Invariants (from Aristotle Phase 2), File Plan, Test Plan, Exit Criteria (executable bash commands + expected results). Use when: (1) before implementing features with complexity > 4, (2) as Step 1.5 in orchestrator workflow, (3) when requirements need formalization. Triggers: /spec, 'create spec', 'write specification', 'technical spec'.