docs: add per-modality default model configuration to skill

[raylanlin]

Summary

Document the new per-modality default model configuration feature in the skill guide, README, and README_CN.

What Changed

• skill/SKILL.md: Added "Default Model Configuration" section with usage examples
• README.md: Added default-text-model example to config section
• README_CN.md: Same update for Chinese readers

Usage

# Set defaults
mmx config set --key default-text-model --value MiniMax-M2.7-highspeed
mmx config set --key default-speech-model --value speech-2.8-hd
mmx config set --key default-video-model --value MiniMax-Hailuo-2.3
mmx config set --key default-music-model --value music-2.6

# Use without --model
mmx text chat --message "Hello"
mmx speech synthesize --text "Hello" --out hello.mp3
mmx video generate --prompt "Ocean waves"
mmx music generate --prompt "Upbeat pop" --instrumental

# --model still overrides per-call
mmx text chat --model MiniMax-M2.7 --message "Hello"

Resolution priority: --model flag > config default > hardcoded fallback.

Related

Paired with PR #89 (source code + tests for the feature).