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.
712 tokens
context cost
the whole folder, loaded on every use
1
files
instructions only
0
copies elsewhere
how many repositories repackaged it
778
stars on the repo
on the repository, not the skill itself
Install
one command, takes just this skill from the repository
Use this skill to create a high-clarity thumbnail or cover image from the actual video content.
Non-Negotiables
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.
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.
Keep text short and readable.
Usually 2-5 words.
Avoid thin type, low contrast, small labels, and clutter.
Workflow
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.
Read project state, transcript, and available media context.
Inspect candidate frames:
expressive face
product or UI clearly visible
dramatic action moment
clean composition
strong lighting or clear subject separation
Classify the thumbnail job:
talking-head / opinion / tutorial
product / software / demo
cinematic / documentary / art
entertainment / challenge / reaction
education / business / concept
Propose concise title text options.
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.
Generate thumbnail options using selected real frames and the selected style.
Check mobile readability, subject fidelity, product/UI truthfulness, and visual contrast.
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.
How to use it
Copy the folder
Take 0xsline/video-thumbnail-generator from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
Check the name does not clash
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.