Ipollowork Video Template Authoring logo

Ipollowork Video Template Authoring

CommunityPopular
Devin-AXIS
ipollowork-video-template-authoring

Create, repair, validate, or package a reusable iPollo Video template in an active HyperFrames template-authoring session. Use for video template structure, editable variables, reusable scenes, GSAP motion, component reuse, cover metadata, and save-ready validation; do not use for ordinary one-off video edits.

Overview

PublisherDevin-AXIS
RepositoryiPolloWork
Skill nameipollowork-video-template-authoring
Stars
6.9K
Forks
1.1K
Bundled files
2
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.

  • 2 bundled files

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

  • Open source

    Published by Devin-AXIS on GitHub. Read the source before you install it.

Installation

Install the Ipollowork Video Template Authoring 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.
    https://github.com/Devin-AXIS/iPolloWork/tree/main/examples/plugin-packages/video-agent/skills/ipollowork-video-template-authoring
  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/Devin-AXIS/iPolloWork.git /tmp/iPolloWork
mkdir -p .claude/skills
cp -r /tmp/iPolloWork/examples/plugin-packages/video-agent/skills/ipollowork-video-template-authoring .claude/skills/ipollowork-video-template-authoring
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Ipollowork Video Template Authoring 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 Ipollowork Video Template Authoring 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 Ipollowork Video Template Authoring 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.

iPolloWork Video Template Authoring

Build a brand-ready motion system, not a decorated slideshow and not a copy of the source template. Work only in the active iPolloWork Video template-authoring session.

Required entry

  • Read and follow the installed hyperframes-core, hyperframes-creative, and hyperframes-animation Skills before editing. Use hyperframes-keyframes, hyperframes-registry, media-use, and hyperframes-cli when their scope applies.
  • Do not continue with a generic HTML fallback if these Video plugin capabilities are unavailable. Tell the user that iPollo Video must be installed or enabled.
  • Set a concrete direction before implementation: audience, story promise, palette, type system, signature motif, layout families, and motion grammar.

Boundaries

  • Treat the injected session contract, exact video/<session-id>/ project, manifest, entry path, and validation report as authoritative.
  • Keep every change inside that session project. Do not create a second project, start another server, install a global Skill, or modify another session.
  • Use HyperFrames as the runtime. Do not import Remotion or another video runtime into the project.
  • Preserve the installed template's useful visual language, components, tokens, and motion grammar, but replace its sample story, copy, media, scene count, and timing whenever the user's content requires it.
  • Never retain instructions, placeholders, fake testimonials, invented metrics, broken media, or unrelated sample claims in a saved template. Defaults must be credible demonstration content or neutral editable values.

Visual quality contract

Every substantial scene must work as a strong still frame before animation is added:

  • Use an intentional foreground, content plane, and background treatment. Give the eye one primary focal point and at most one supporting focal point.
  • Fill the 16:9 or 9:16 frame at video scale. Avoid small web-card UI floating in empty space.
  • Give adjacent scenes different layout families: for example asymmetric editorial, media-led split, full-bleed crop, spatial deck, connected map, or typographic close. Never repeat the same centered title, giant circle, or equal three-card grid in consecutive scenes.
  • Use typography as composition. Prefer clear scale contrast, controlled line length, and optical alignment over many labels or pills.
  • Avoid generic AI styling: default purple-cyan gradients, gratuitous glow, glass cards everywhere, oversized circles behind centered text, and decorative grids with no narrative purpose.
  • Treat all media deliberately with crop, depth, mask, framing, pan, or zoom. Do not drop a raw image into a flat rectangle. Use a local replaceable media slot whenever the story needs real imagery.
  • Keep color roles sparse: one dominant field, one text system, one accent, and optional semantic colors. Decorative effects may support hierarchy but must not become the hierarchy.

Motion quality contract

  • Build exactly one gsap.timeline({ paused: true }) for the composition and register it in window.__timelines[compositionId].
  • Choreograph each scene in three phases: establish during roughly the first 30%, breathe or demonstrate during the middle 40%, and resolve or hand off during the final 30%.
  • Use two to four motivated motion patterns per scene. Vary direction, distance, duration, and easing according to meaning; entrances are normally longer than exits.
  • Prefer semantic transitions: cut for contrast, crossfade for continuity, dissolve for mood, and masks or shared geometry for transformation. Do not apply the same transition to every scene.
  • Use fromTo for clip-local state so direct seeking is stable. Put every ambient drift, counter, line draw, and emphasis beat on the paused timeline. Never use infinite CSS animation, clocks, timers, random values, or unregistered gsap.to calls.
  • Do not run competing transform tweens on one element. Split camera, entrance, and emphasis motion across parent and child layers.
  • Reserve the strongest motion for the story's strongest beat. Constant movement is visual noise, not polish.

Reusable template contract

  • Expose variables for content that the next user is expected to replace: headlines, labels, media paths, brand colors, numbers, calls to action, and repeated items.
  • Keep structure, timing, transitions, and visual grammar reusable. Do not turn the sample template's exact scene order or copy into the contract.
  • Design variable defaults as a coherent preview. Avoid strings such as “replace this text”, “your logo”, or arbitrary fake performance numbers.
  • Keep local assets and resilient fallbacks. A missing optional image must not reveal broken-image UI or alt text in the frame.

Workflow

  1. Read the current manifest, entry file, design-tokens.css, declared variables, existing scenes, and validation report.
  2. Resolve one unanswered decision at a time: purpose and audience, reusable content structure, editable variables, visual direction, then type-specific constraints. Skip decisions already supplied.
  3. Define a content-led shot plan. For a new or substantially restructured template, read shot-planning.md. Assign a different layout family and motion purpose to every adjacent story beat.
  4. Design the template contract before polishing:
    • stable scene and editor hooks;
    • deterministic duration, tracks, clips, and transitions;
    • useful content variables with defaults;
    • local, replaceable media slots;
    • a coherent token-driven visual system.
  5. Reuse the Video plugin's existing capabilities instead of duplicating them:
    • hyperframes-creative for narrative, pacing, typography, and composition;
    • hyperframes-registry to query and add approved blocks or components;
    • hyperframes-animation for motion rules and transition choreography;
    • hyperframes-keyframes for seek-safe GSAP timelines;
    • media-use for media resolution or generation;
    • hyperframes-cli for inspection, validation, preview, and snapshots.
  6. Implement the visual quality contract first, then the motion quality contract. A weak still frame cannot be rescued with effects.
  7. Keep manifest.json, cover metadata, design tokens, variables, defaults, and the apply checklist synchronized with structural edits.
  8. Inspect at least three frames per scene: after establishment, during the main demonstration, and at resolution. Check for collisions, empty framing, repeated composition, broken media, unreadable type, and discontinuities.
  9. Run the active session's HyperFrames check and server template validation against the exact project. Re-instantiate the saved package before claiming it is reusable.

Completion gate

Reject the result and revise it if any adjacent scenes share the same composition, any frame looks like a generic slide deck, any effect lacks narrative purpose, or any placeholder/fake/broken content is visible.

Report completion only when the composition seeks correctly, all media resolves, every declared variable is wired, the package validates, inspected frames are visually distinct and polished, and a fresh instance preserves the template contract without retaining the authoring sample content.

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 Ipollowork Video Template Authoring AI skill do?

Create, repair, validate, or package a reusable iPollo Video template in an active HyperFrames template-authoring session. Use for video template structure, editable variables, reusable scenes, GSAP motion, component reuse, cover metadata, and save-ready validation; do not use for ordinary one-off video edits.

Why use Ipollowork Video Template Authoring on TypingMind?

Because you install it once and use it with any model. Ipollowork Video Template Authoring 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 Ipollowork Video Template Authoring in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Devin-AXIS/iPolloWork/tree/main/examples/plugin-packages/video-agent/skills/ipollowork-video-template-authoring. 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 Ipollowork Video Template Authoring?

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 Ipollowork Video Template Authoring?

As many as you like. As long as a model supports skills, you can use Ipollowork Video Template Authoring with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Ipollowork Video Template Authoring AI skill free?

It is published on GitHub by Devin-AXIS. 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 👇