SkillsAdd

smithery/talesofai

banana-image

通用 banana 生图/改图（TalesOfAI MCP）技能。

Installation

$ npx skills add smithery/talesofai --skill banana-image
View on skills.sh ↗ Website ↗

Similar popular skills

Related neighbors and high-traction skills in the same topics — useful to compare before installing.

nano-banana-pro-openrouter Similar name
github/awesome-copilot

Generate or edit images via OpenRouter with the Gemini 3 Pro Image model. Use for prompt-only i…

9.9K installs
nano-banana-2 Similar name
prime-skills/runcomfy-agent-skills

Generate images with Google Nano Banana 2 (Gemini-family flash-tier text-to-image) on RunComfy …

414.4K installs
nano-banana-edit Similar name
prime-skills/runcomfy-agent-skills

Edit images with Google Nano Banana 2 (image-to-image edit endpoint) on RunComfy. Documents Nan…

414K installs
nano-banana-2 Similar name
pilioai/skills 13.5K installs
nanobanana Similar name
gargantuax/openskills

Gemini-native Nano Banana image generation and editing across Nano Banana, Nano Banana 2, and N…

10.5K installs
nano-banana-pro Similar name
intellectronica/agent-skills

Generate and edit images using Google's Nano Banana Pro (Gemini 3 Pro Image) API. Use when the …

3.1K installs

Also in this package

Other skills from smithery/talesofai.

npx skills add smithery/talesofai
world-readonly 0 world-design-card 0 time-lookup 0 quest 0 nano 0 hot-push 0 character-portrait 0 character-card 0 canon-conflict-check 0

Browse all from smithery/talesofai

More details

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Not declared
Cursor Not declared
Codex Not declared
GitHub Copilot Not declared
Windsurf Not declared
Gemini CLI Not declared
Cline Not declared
OpenCode Not declared

Package contents

Files included with this skill beyond the listing page.

  • skill md SKILL.md 824 B
  • docs SUMMARY.md 75 B

History

  1. First recorded snapshot · 0 installs

SKILL.md

banana-image

适用场景

  • 用户要求生图、改图、重绘、风格化。
  • 需要通过 TalesOfAI MCP 完成图片生成或编辑。

工具要求（必须）

  • 优先：mcptalesofaieditimagebeta
  • 回退：mcptalesofaimakeimagev1
  • 兼容：mcptalesofaidraw

禁止：

  • 伪造图片 URL
  • 用纯文本假装“已生成图片”

执行规则

  1. 先将用户需求整理成英文 prompt（保留关键风格词）。
  2. 如果用户给了参考图，优先使用编辑链路（edit）。
  3. 若没有参考图，走文生图。
  4. 默认只生成 1 张图，除非用户明确要求多张。

输出格式（必须）

  • 只输出最终图片：![](URL)
  • 不输出长篇解释。