agentleFS
wangjs-jackywangjs-jacky/jacky-skills/skills/android-live-photo/SKILL.md

android-live-photo

Skill15 starsChanged 29 days agoMITView on GitHub

Convert a user-provided MP4 video into a verified standard Android Motion Photo (often called Android Live Photo): a JPEG cover with the original MP4 embedded and Google Motion Photo XMP metadata. Use when users ask to turn a video into a Live Photo, dynamic photo, Motion Photo, or social-media-compatible Android live image.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 2 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Create an Android/Google Motion Photo from a supplied MP4.

    line 8
  2. Distinctive:

    Use the exact video attachment path supplied by the user.

    line 12
  3. Very specific:

    Run ffprobe on the MP4. Stop and report the issue if it has no readable video stream or duration.

    line 13
  4. Distinctive:

    Run the bundled script, defaulting the cover to the midpoint:

    line 14
  5. Very specific:

    Use --cover-at <seconds> only when the user specifies a preferred cover moment.

    line 22

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Android Live Photo

Create an Android/Google Motion Photo from a supplied MP4. The output is one untouched .jpg binary containing a JPEG cover, standard XMP metadata, and the original MP4 bytes.

Workflow

  1. Use the exact video attachment path supplied by the user. Do not scan attachment folders.
  2. Run ffprobe on the MP4. Stop and report the issue if it has no readable video stream or duration.
  3. Run the bundled script, defaulting the cover to the midpoint:
node scripts/convert_motion_photo.mjs \
  --input /absolute/input.mp4 \
  --output /absolute/output_MP.jpg

Use --cover-at <seconds> only when the user specifies a preferred cover moment.

  1. Trust completion only after the script reports validation: passed. It verifies JPEG SOI, Motion Photo XMP, declared embedded-video length, MP4 signature, and byte-for-byte equality of the embedded MP4 with the source.
  2. State the output path and compatibility boundary: the result has worked with social platforms that recognize standard Android Motion Photos; Honor Gallery may not register imported generic Motion Photos as native Live Photos.

Delivery

Do not send the dynamic JPEG through an image renderer or editor: recompression strips the embedded MP4 and turns it into a static image. Preserve the exact generated binary. If the environment supports general file attachment, send it unchanged; otherwise provide the absolute output path or package it in an untouched archive using the available file-delivery mechanism.

Requirements

Require Node.js 20+, ffmpeg, and ffprobe on PATH. The script supports MP4 input only and does not alter source media.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.