AI Skill MartBrowse skillsPromptsProgramsLearnWhat is a Skill?
 
← Back to list

oil-cover · AI-Tool Video Cover Generator

Picks real frames from your video and generates 3:4 / 4:3 / 16:9 thumbnails for Xiaohongshu and Bilibili in one run.

Image & VideoIntermediate★ 284⑂ 29AI score 8/10Last updated: Oct 28, 2026

What it does

  • Scans the whole video with ffmpeg at low resolution, scores sharpness/brightness/content and filters out black, blurry and loading frames before handing real HD candidates to a vision model.
  • The vision model picks the best semantic frame and writes a full cover prompt (line-broken headline, subtitle, accents), which an image model renders.
  • Outputs three aspect ratios by default: 3:4 for Xiaohongshu, 4:3 as the main Bilibili cover, 16:9 for the Bilibili profile page.
  • Optionally composites a transparent creator portrait into the bottom-right corner with deterministic local code, logged in portrait_composite.json.
  • Keeps prompt sidecars, analysis.json and cover_plan.md next to the video so reruns and rollbacks are safe.

Who it's for

  • Creators publishing AI-tool walkthrough videos on Xiaohongshu / Bilibili
  • Solo video makers tired of screenshot → editor → text overlay busywork
  • Content teams that need consistent cover art across multiple platform sizes

Examples

  • "Use oil-cover to make a thumbnail for this video" → reads the subtitles, extracts the strongest claim, renders all three ratios
  • Rerun only --aspect 4x3 to refresh just the Bilibili main cover
  • Use --skip-generate to inspect the chosen frame and prompt before spending image-API credits

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/oil-oil/oil-cover/HEAD/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on AI Skill Mart.
Copy the SKILL.m folder from the GitHub repo oil-oil/oil-cover into my ~/.claude/skills/oil-cover/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/oil-oil/oil-cover.git ~/.claude/skills/oil-cover

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal and create the skills folder: mkdir -p ~/.claude/skills
  2. Clone the repo: git clone https://github.com/oil-oil/oil-cover.git ~/.claude/skills/oil-cover
  3. Install prerequisites: ffmpeg, python3, and pip install pillow
  4. For script mode, export an image/vision service key as ZENMUX_API_KEY, or prepare a secure key file path.
  5. Create ~/.oil-cover/config.json with mode (script or agent-native), plus optional creator_portrait and video_library_root. You can skip this — the skill asks once on first use.
  6. Restart Claude Code and invoke it by name, e.g. "oil-cover: make a thumbnail for this video". It will not trigger on generic cover requests.
View source on GitHub ↗License: NOASSERTION