‹ 首页

muapi-social-pack

@samuraigpt · 收录于 1 周前 · 上游提交 3 周前

Re-render a hero image into Instagram, TikTok, YouTube-shorts and Twitter/X aspect ratios.

适合你,如果需要在多个平台发布统一视觉内容

/ 下载安装
muapi-social-pack.skill双击,或拖进 Claude 桌面版 / Cowork,即完成安装↓ .skill↓ .zip
用别的 agent?下载 .zip 解压,把文件夹放进它的技能目录
Claude Code~/.claude/skills/(项目级 .claude/skills/)
Codex CLI~/.codex/skills/
Cursor自动读取上面两处目录
其他工具见其文档的「skills」目录;两个下载是同一份文件,只是名字不同
/ 通过 npx 安装 校验哈希
npx oh-my-skill add samuraigpt/generative-media-skills/muapi-social-pack
/ 通过 bash 安装
curl -fsSL https://oh-my-skill.com/install.sh | bash -s -- samuraigpt/generative-media-skills/muapi-social-pack
/ 已经装过?验证本机副本,不用重装
npx oh-my-skill verify samuraigpt/generative-media-skills/muapi-social-pack
安装目标可用 --agent / --scope 或 --to 明确指定;省略时只会在唯一已存在的 agent 目录上自动选择,零命中或多命中会停止并提示。content_hash 缺失或不一致均拒装。
3754GitHub stars
~520上下文体积 · 单文件
镜像托管

怎么用

商店整理自技能原文 · 版本 a1c4c98 · 表述以原文为准
它做什么

装上后,Claude 能把一张主图重新裁剪成 Instagram、TikTok、YouTube Shorts 和 Twitter/X 等平台的常用比例,并保持主体居中、色调一致。

什么时候触发

当你提到“社交包”、“调整尺寸”、“跨平台发布”等关键词,或要求把一张图适配多个社交平台时触发。

装好后可以这样说
Claude 会按 16:9 和 9:16 分别处理。
技能原文 SKILL.md作者撰写 · MIT · a1c4c98

Social Media Pack

Re-render a hero image into Instagram, TikTok, YouTube-shorts and Twitter/X aspect ratios.

Inputs

| Name | Type | Required | Default | Description | |:---|:---|:---|:---|:---| | source_image | image_url | yes | — | URL of the hero image (or asset_id from this session). | | caption_idea | text | no | — | Optional caption / overlay direction (kept short). | | formats | list | no | 1:1, 9:16, 4:5, 16:9 | Aspect ratios to produce. |

Steps

Use the plan to fan out one node per format.

  1. For each requested aspect ratio in {{formats}}:
  2. Call muapi image edit (model=nano-banana-2-edit) with the source image.
  3. Prompt: "Reframe the composition to {{aspect_ratio}} for social media. Keep the subject centred and uncropped. Match the original lighting and palette. {{caption_idea_hint}}".
  4. Where {{caption_idea_hint}} = "Leave headroom at the top for a caption: '<caption_idea>'." (only if caption_idea is non-empty).
  5. All formats run in parallel (no inter-node dependencies).
  6. Return one asset id per format, labelled with the platform it suits:
  7. 1:1 → Instagram feed
  8. 9:16 → TikTok / IG Reels / YT Shorts
  9. 4:5 → Instagram portrait
  10. 16:9 → Twitter / X / YouTube
  11. 21:9 → cinematic banner
Notes
  • Don't generate fresh images — only reframe / re-edit the source.
  • If the source already matches a format, skip that node and surface the original asset id for it.
Trigger Keywords

social pack, resize for social, cross-post, multi-platform


Notes for the Executing Agent
  • This recipe is LLM-orchestrated: read each phase, gather any missing inputs from the user, then call muapi CLI commands. Use muapi auth configure first if MUAPI_API_KEY is unset.
  • For model IDs without a CLI alias yet, fall back to the raw endpoint via curl -X POST https://api.muapi.ai/api/v1/<endpoint> -H "x-api-key: $MUAPI_API_KEY" -H 'content-type: application/json' -d '{...}' and poll with muapi predict wait <request_id>.
  • Substitute {{input_name}} placeholders with the user's actual inputs before issuing each call.
按 MIT 许可原样转载,未经改动 · 在 GitHub 查看 →

评论

登录即可评论;带「已验证安装」的,是发布者名下有本店的安装或持有记录。