Scenes Gathered Zine Live Flow V1 0 logo

Scenes Gathered Zine Live Flow V1 0

CommunityPopular
Zeejay0
scenes-gathered-zine-live-flow-v1-0

Run the complete Gathered Scenes workflow from a supplied photograph to a static poster, a scene-authored adaptive v0.2 flat paper-tear Apple Live Photo ZIP, and optional handoff of that ZIP to the local Live Photo Importer. Use when the user wants the full source-to-Live-Photo flow with a custom narrative tear path and broad rounded low-frequency contours; do not use for static-only posters, 3D paper curls, or motion inside the photographed scene.

Overview

PublisherZeejay0
Repositorygathered-scenes-zine-skill
Skill namescenes-gathered-zine-live-flow-v1-0
Stars
5.1K
Forks
499
Bundled files
13
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 13 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by Zeejay0 on GitHub. Read the source before you install it.

Installation

Install the Scenes Gathered Zine Live Flow V1 0 AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/Zeejay0/gathered-scenes-zine-skill.git /tmp/gathered-scenes-zine-skill
mkdir -p .claude/skills
cp -r /tmp/gathered-scenes-zine-skill/skills/scenes-gathered-zine-live-flow-v1-0 .claude/skills/scenes-gathered-zine-live-flow-v1-0
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Scenes Gathered Zine Live Flow V1 0 in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Scenes Gathered Zine Live Flow V1 0 on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Scenes Gathered Zine Live Flow V1 0 is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

拾景纸刊实况全流程 v1.0(实况版)

Turn one supplied photograph into one importer-ready Live Photo ZIP through two strictly separated modules:

  1. Create the finished poster with the frozen bundled module references/static-poster-v1-9/SKILL.md.
  2. Animate only a flat covering sheet tearing away from that finished poster.
  3. Pair the exact final frame as an Apple Live Photo JPG/MOV pair.
  4. Package only that pair in one ZIP.
  5. When import is requested, hand the ZIP to “实况照片导入器” through macOS file-open and stop.

Do not modify the bundled static-poster-v1-9 module. It remains the single source of truth for all static visual decisions.

Trigger Modes

  • Full flow / import: source photo → v1.9 poster → Live ZIP → importer handoff.
  • ZIP only: source photo or finished v1.9 poster → Live ZIP with --no-import.
  • Static only: follow references/static-poster-v1-9/SKILL.md directly and stop before animation.

For the established full-flow workflow, skip preview movies, contact sheets, visual review gates, metadata reports, and approval pauses. Continue automatically unless a step returns an explicit error. The user performs the final visual check.

Phase 1: Freeze the Poster

If the input is a raw photograph:

  1. Read and follow the complete bundled module references/static-poster-v1-9/SKILL.md.
  2. Generate the orientation-matched poster using its required image-generation path.
  3. Save the flattened result inside the current project output directory.

If the input is already a finished v1.9 poster, begin from it directly.

After this phase, treat the finished poster as an immutable bottom plate. Do not recolor, sharpen, clarify, regenerate, crop, resize non-proportionally, retouch faces, add detail, or otherwise redesign it during animation. Every fully revealed frame region must come directly from this frozen poster.

Phase 2: Choose the Tear

Compose the tear path only after seeing the finished poster. Read:

  • references/adaptive-path-selection.md
  • references/adaptive-tear-boundary.md

Always compose one custom source-derived path with 3–7 normalized points. Do not choose from preset directions. Start in quiet paper, establish the environment or a clue, reveal the structural relationship next, bring the primary subject into view during the middle third, and end at a clear visual resting point.

Follow a real ridge, shoreline, roofline, road, gaze, spatial-depth transition, or relationship between subjects. Complement the poster's guide color without tracing it. Avoid top-to-bottom and bottom-to-top reveals, one rigid straight diagonal, faces, bodies, text, and defining objects.

The visible opening follows one scene-aware global path. Its boundary uses broad, high-amplitude, low-frequency rises and falls, small unequal notches, changing opening width, and a narrow warm fiber fringe. Reject clean digital wipes, uniform saw teeth, regular zigzags, curled sheets, and 3D depth simulation.

Phase 3: Build the Live ZIP

Use scripts/build_live_zip_and_import.py with the frozen poster, chosen direction, and optional custom path. The accepted motion profile is fixed:

  • 3.0 seconds at 30 fps;
  • brief fully covered hold;
  • crack propagation;
  • asymmetric two-sided expansion with broad rounded low-frequency boundary variation;
  • exact unchanged poster from 2.7 seconds through the final hold;
  • no camera motion, subject motion, relighting, parallax, or internal animation.

Example ZIP-only build:

bash
python3 scripts/build_live_zip_and_import.py \
  --input /absolute/path/to/final-poster.png \
  --output-zip /absolute/path/to/GatheredScenesLivePhoto.zip \
  --direction custom \
  --path-points "0.04,0.72;0.26,0.60;0.52,0.44;0.76,0.34;0.98,0.24" \
  --no-import

Read references/apple-live-photo.md for pairing invariants. The ZIP contract is strict:

  • exactly one top-level folder;
  • exactly one paired .JPG and one paired .MOV inside it;
  • no poster, receipt, contact sheet, preview, source file, or sidecar inside the ZIP;
  • the ZIP is the only durable delivery artifact required from this workflow.

All render frames, unpaired media, and receipts remain temporary.

Phase 4: Importer Handoff

When the user asks for the complete automated flow or asks to place the result in Photos, omit --no-import. Read references/importer-handoff.md and let the build script open the completed ZIP with bundle id com.zeejay.live-photo-importer.

This skill includes the ready-to-run Apple-silicon macOS importer at assets/实况照片导入器.app. The build script checks an explicitly supplied app, the user's installed copy, and then this bundled copy automatically. Do not require a separate importer download.

Do not simulate drag-and-drop and do not operate the Photos app. Successful submission of the ZIP to “实况照片导入器” is the stopping point. The importer owns pairing validation, permissions, Photos-library insertion, and later iCloud synchronization.

If the importer cannot be found, first verify that the bundled app exists and is intact. Otherwise keep the finished ZIP and report the handoff error. Do not regenerate the poster or animation. Use --importer-app /absolute/path/实况照片导入器.app only when another exact app path is known.

Response Contract

For ZIP-only mode, return the absolute ZIP path. For full-flow mode, return the absolute ZIP path, state whether macOS accepted the importer handoff, and briefly describe the composed narrative path. Do not present intermediate files unless the user explicitly asks for them.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Scenes Gathered Zine Live Flow V1 0 AI skill do?

Run the complete Gathered Scenes workflow from a supplied photograph to a static poster, a scene-authored adaptive v0.2 flat paper-tear Apple Live Photo ZIP, and optional handoff of that ZIP to the local Live Photo Importer. Use when the user wants the full source-to-Live-Photo flow with a custom narrative tear path and broad rounded low-frequency contours; do not use for static-only posters, 3D paper curls, or motion inside the photographed scene.

Why use Scenes Gathered Zine Live Flow V1 0 on TypingMind?

Because you install it once and use it with any model. Scenes Gathered Zine Live Flow V1 0 is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Scenes Gathered Zine Live Flow V1 0 in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Zeejay0/gathered-scenes-zine-skill/tree/main/skills/scenes-gathered-zine-live-flow-v1-0. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Scenes Gathered Zine Live Flow V1 0?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Scenes Gathered Zine Live Flow V1 0?

As many as you like. As long as a model supports skills, you can use Scenes Gathered Zine Live Flow V1 0 with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Scenes Gathered Zine Live Flow V1 0 AI skill free?

It is published on GitHub by Zeejay0. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇