Skip to content
cccskills
FreePublished on GitHub

video-thumbnail-generator

Create platform-ready thumbnails from real video frames. Use when the user wants a thumbnail, cover image, YouTube cover, Shorts cover, Bilibili cover, Xiaohongshu cover, or other video poster image.

The English summary is being prepared. Showing the original description.

Works withYouTube
See how to install

Files included (1)

  • SKILL.md2.8 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

Video Thumbnail Generator

Use this skill to create a high-clarity thumbnail or cover image from the actual video content.

Non-Negotiables

  1. Use the real video as visual evidence.

    • If the thumbnail shows a person, product, UI, frame, or scene from the video, extract or inspect real frames.
    • Never invent a generic software interface, fake product screen, or unrelated person.
  2. Read style references before recommending styles.

    • Use references/thumbnail-styles.md and references/thumbnail-style-recipes.md.
    • Only offer style directions supported by those references or by the user's explicit instruction.
  3. Keep text short and readable.

    • Usually 2-5 words.
    • Avoid thin type, low contrast, small labels, and clutter.

Workflow

  1. Confirm platform and aspect ratio if missing.
    • YouTube / Bilibili: usually 16:9.
    • Shorts / TikTok / Douyin: usually 9:16.
    • Xiaohongshu / WeChat Channels: usually 3:4.
    • Correct ambiguous ratio language gently, especially 4:3 vs 3:4.
  2. Read project state, transcript, and available media context.
  3. Inspect candidate frames:
    • expressive face
    • product or UI clearly visible
    • dramatic action moment
    • clean composition
    • strong lighting or clear subject separation
  4. Classify the thumbnail job:
    • talking-head / opinion / tutorial
    • product / software / demo
    • cinematic / documentary / art
    • entertainment / challenge / reaction
    • education / business / concept
  5. Propose concise title text options.
  6. Offer 3-6 clearly different style directions.
    • Each option should name the composition, not only a channel/style label.
    • Exclude weak options.
    • Wait for user choice when the direction is not obvious.
  7. Generate thumbnail options using selected real frames and the selected style.
  8. Check mobile readability, subject fidelity, product/UI truthfulness, and visual contrast.
  9. Present results and offer targeted adjustments.

Prompt Shape

[Platform] thumbnail, [aspect ratio / dimensions], [style name].

COMPOSITION: [subject position, scale, background, graphic balance]
REAL REFERENCE: [describe selected frame zone by zone]
TEXT: "[short title]" in [high-contrast style]
STYLE: [one-line style recipe from references]
CONSTRAINTS: readable at mobile size, no fake UI, no watermark, no play button.

References

  • references/thumbnail-styles.md: style library from real thumbnail analysis.
  • references/thumbnail-style-recipes.md: quick style recipes and prompt patterns.
  • references/field-testing-notes.md: known failure modes.

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

Plan AI short films with story, shots, prompts, and continuity.

The English summary is being prepared. Showing the original description.

0xsline/OpenChatCut2.5KUpdated Oct 19, 2026

Use when acquiring or importing media into a OpenChatCut project asset library for video editing or creation, including local/attached videos, user-provided paths, public media URLs, web video/audio/image assets, upload fallback decisions, and deciding between import_media, download_media, or manual user action.

The English summary is being prepared. Showing the original description.

0xsline/OpenChatCut2.5KUpdated Oct 19, 2026

Turn one pool of existing project media into a batch of distinct, publishable montage cuts instead of a single hero edit. Use for batch montage, one-source-many-outputs, 一源多出, 批量混剪, 批量出片, 矩阵号, 多账号分发, variant batches, deduped cuts, 去重变体, 防搬运, or when the user asks for N different versions of the same footage.

The English summary is being prepared. Showing the original description.

0xsline/OpenChatCut2.5KUpdated Oct 19, 2026

Plan and build a finished beat-synced montage where cut placement serves the content, not just the metronome. Use for 卡点混剪, 卡点剪辑, 踩点视频, beat-sync montage, rhythm edit, 节奏剪辑, 音乐驱动剪辑, or when the user wants cuts that land on the beat.

The English summary is being prepared. Showing the original description.

0xsline/OpenChatCut2.5KUpdated Oct 19, 2026

Use whenever the agent needs to add, create, hand-author, patch, or place Motion Graphic JSX assets in a OpenChatCut project. This is the direct-authoring path: use create_motion_graphic_from_code / edit_asset / edit_item, not motion-graphic-gen or submit_motion_graphic. Covers project/timeline intake, project visual language, editable properties, asset binding, inline JSX authoring, existing asset updates, timeline placement, and verification.

The English summary is being prepared. Showing the original description.

0xsline/OpenChatCut2.5KUpdated Oct 19, 2026

Assemble product footage, UGC, and b-roll into a conversion-oriented montage with a hook → pain → demo → proof → CTA rhythm. Use for 带货混剪, 产品混剪, 商品短视频, 种草视频, ecommerce montage, product reel, UGC cutdown, or when the user wants selling footage cut into a short that converts.

The English summary is being prepared. Showing the original description.

0xsline/OpenChatCut2.5KUpdated Oct 19, 2026

See all skills by 0xsline

Report a problem with this skill