图片免费 已验证

深绿扁平剪影分享封面图

以深绿色为底色,搭配超大白色文字、扁平剪影和鲜明色块,制作醒目的社交分享封面图。适用于产品发布和网页分享,尤其适合需要标题准确易读、系列视觉统一的场景。

sl-dark-green-flat-silhouettes-og-image sample output

你会得到

  • 一张适合链接预览裁切的 16:9 分享图。
  • 统一的深绿底色、白色大字与扁平剪影视觉系统。
  • 以用户提供的标题为中心的精简构图。

适合

  • 产品发布公告与社交平台链接预览。
  • 创作者或产品项目的系列封面图。

不适合

  • 需要容纳多段文案或大量细节的编辑版式。
  • 摄影广告或要求精确还原品牌标志的作品。

你需要提供

  • 准确的标题文本及大小写要求。
  • 产品或项目名称与简短说明。
  • 可选的剪影主题或辅助短句。

运行要求

  • Node.js 20+
  • A SkillLoom generation key (prepaid)

运行成本

Each image is generated with your prepaid SkillLoom generation key (about $0.05 per image at 1K). Subscriptions do not include generation credits.

一次典型运行约 $0.05(按 sub2api 价格,从你的预付费 key 扣除)

试试这个提示词

/sl-dark-green-flat-silhouettes-og-image 为 Fieldnote(一款简洁的项目进度更新工具)制作一张 16:9 社交分享封面。标题准确写为 "Make progress visible",辅助短句准确写为 "Project updates, without the noise." 画面呈现便笺堆叠和上升路径的扁平剪影。保持既定的深绿与白色风格,少量点缀洋红、橙色和钴蓝。

后续提示词

  • 放大标题,并简化剪影造型。
  • 保持相同视觉系统,为下一张发布图改用日历剪影。

验证情况

已验证

render-checkpass5.0 / 567s

常见问题

标题会准确呈现吗?

会。请提供最终文案与大小写要求;提示词会优先保证拼写准确,不会擅自添加文字。

可以用于一组系列图片吗?

可以。请在各张图片中保持深绿底色、白色大字、剪影处理和强调色分工一致。

SKILL.md

SKILL.md

Dark Green Flat Silhouettes OG Image

Make a bold, readable OG image that pairs oversized white type with a distinctive arrangement of flat silhouettes on deep green.

Style: Green Silhouette Blocks. Graphic and confident, with monumental white type grounded by playful, sharply cut silhouettes and precise color accents. Follow references/style-guide.md exactly.

Use this skill when

  • Product launch announcements and social link previews.
  • A repeatable visual series for a creator or product project.

Do not use

  • Text-heavy announcements that need multiple claims, feature lists, or fine print.
  • Photorealistic product imagery, portraits, or brand-specific logo reproduction.
  • To reproduce another company's brand, logo, product UI or copyrighted characters.

Inputs

  • Product or project name and a short description of what it does
  • Exact headline text, including preferred capitalization
  • Optional supporting phrase and desired silhouette subject
  • Optional series color or composition preference; preserve the locked green system

If something essential is missing, ask one short question before starting. Never invent facts, numbers, quotes or customer names; mark gaps as [needs source].

Workflow

  1. Collect the brief fields listed in references/prompt-framework.md. If any text will appear in the image, confirm it letter by letter and freeze it.
  2. Build the prompt with references/prompt-framework.md, following references/visual-system.md for subject, composition, light, palette and the text policy. Write it to prompt.txt.
  3. Check that the generation key is configured: SKILLLOOM_API_KEY and SKILLLOOM_BASE_URL (run npx skillloom doctor --write-env if not).
  4. Tell the user the image is paid from their prepaid key (see the cost note) and get explicit approval.
  5. Generate one image. The task id is saved first, so re-running the same command resumes instead of paying twice:

``bash node scripts/generate.mjs --prompt-file prompt.txt --output image.png --task-file image-task.json --confirm-paid ``

  1. Run the validator and fix every problem it reports:

``bash node scripts/validate-image.mjs image.png ``

What makes this excellent

  • Identify the one message that must survive a small social preview; use the supplied headline verbatim and omit nonessential copy.
  • Choose 2-5 simple silhouettes that make the product category recognizable without depicting a real person or brand.
  • Arrange silhouettes as bold, interlocking blocks that balance the headline rather than compete with it.
  • Keep white type and the dark-green field dominant; distribute magenta, orange, and cobalt accents sparingly.
  • Use a 16:9 composition at a minimum width of 1200 pixels and keep key elements in the central safe area.
  • For a series, retain the same green background, headline scale, silhouette treatment, and accent-color roles.

Output contract

  • One PNG at 16:9, at least 1200px wide, following the visual system; any approved text spelled exactly.
  • No logos, watermarks or real people's likenesses unless the user owns them.
  • A hand-off note with the final prompt, the task file path and the validator output.
  • Deliver one 16:9 image at 1200 pixels wide or greater, suitable for social link previews.
  • Render the requested headline exactly; do not add invented logos, labels, or supporting claims.

Reference demo and agent run

The preview image was generated from the sample brief in scripts/image-spec.json. In a real run the agent fills the brief from the user's request, generates with the user's key, checks the result against the output contract (required text, ratio, no extra words) and regenerates when it misses.

Failure rules

  • If the API reports a low balance or a limit, stop and tell the user; never switch providers or keys silently.
  • If text is misspelled or the composition misses the visual system, ask before generating again. Never retry automatically; every attempt is paid.
  • Never print or store the API key in files you hand over.

相似技能

深绿扁平剪影分享封面图 · SkillLoom