Menu
Optimal patterns for MiniMax MCP tools (web_search + understand_image)
The review-first prompt is selected by default. You can switch to a direct command or download a local copy.
Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
A direct command skips the review prompt. Inspect the source before running it.
npx skills add https://github.com/majiayu000/claude-skill-registry --skill minimax-mcp-usageThe command stays on one line. Scroll horizontally to inspect it before copying.
Prefer a local copy? Download the files currently available to SkillsMP.
LLM token logprobs and calibration. Per-decision confidence, ECE, Brier, reliability diagrams, low-confidence triage.
Analyze LLM token logprobs and calibration. Use for per-decision confidence, ECE, Brier scores, reliability diagrams, and low-confidence triage.
回顾最近 N 天的 Claude Code 使用记录——扫描原始会话数据，按主题分组汇总"我都做了什么"，并从个人操作系统视角输出模式、风险与增删建议。当用户说 /recap、"看看我这几天做了什么"、"回顾一下我最近的会话"、"这两天我用 claude 干了啥"、"活动回顾" 时使用。
Showing SKILL.md
Based on SOC occupation classification
| name | minimax-mcp-usage |
| description | Optimal patterns for MiniMax MCP tools (web_search + understand_image) |
ultrathink - Take a deep breath. We're not here to write code. We're here to make a dent in the universe.
MiniMax queries should be lean, accurate, and decisive.
This skill documents optimal usage patterns for MiniMax MCP tools.
Purpose: Web search with 8% cost of alternatives
Input:
query: string # 3-5 keywords, include year for recent topics
Output:
{
"organic"
Optimal Patterns:
# 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
Purpose: Image analysis for debugging and review
Input:
prompt: string # Clear, specific question about the image
image_source: string # Local path (no @) or HTTPS URL
Optimal Patterns:
# 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"
# 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.
| Operation | MiniMax MCP | Gemini CLI | Savings |
|---|---|---|---|
| Web search | ~$0.008 | ~$0.06 | 87% |
| Image analysis | ~$0.01 | N/A | New capability |
| 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 |
| 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 |