danielhangan GitHub avatar

reelclaw-templates

danielhangan

A collection of reusable HyperFrames video templates for generating TikTok/Instagram Reels growth content with a single command.

Stars

41

7-day growth

No data

Forks

32

Open issues

0

License

No data

Last updated

2026-07-29

AI repository intelligence
FR-AI / ANALYSIS

Why it is worth attention

It automates the creation of short-form video content with deterministic rendering, cross-platform safe zones, and TikTok Sans typography, reducing manual editing for creators and marketers.

Who it is for

  • Content creators and influencers
  • Social media managers and marketers
  • Developers building automated video pipelines
  • Agencies producing bulk reel content

Use cases

  • Create reaction videos with captions and app demos
  • Generate product demo reels from source videos
  • Automate repetitive short-form video production for growth hacking
  • Batch produce TikTok-style content with consistent formatting

Strengths

  • Deterministic rendering ensures reproducible outputs
  • Shared platform rules enforce consistent typography and safe zones across all templates
  • Supports multiple input formats: local files, URLs (via optional yt-dlp), and automatic font embedding
  • Minimal input required: one command produces a 1080×1920 MP4

Considerations

  • Requires Node.js 18+ and ffmpeg/ffprobe on PATH
  • Only one template (reaction_demo) is currently documented in the table; the template library may be small
  • Relies on the external HyperFrames CLI and a headless Chrome instance, which may be resource-intensive

README quick start

reelclaw-templates

Reusable HyperFrames video templates for TikTok / Instagram Reels growth content. Each template is a self-contained HyperFrames project with a generator script: give it media + text, get a render-ready 1080×1920 MP4.

All templates follow the shared platform rules in RULES.md — TikTok Sans typography, classic white/black-outline captions, cross-platform safe zones, auto text sizing, and deterministic rendering.

See it in action

One command in, one reel out — the reaction_demo generator building and rendering a reel end-to-end:

Click the preview to watch the full-quality video.

Templates

TemplateFormatInputs
reaction_demoCreator reaction with hook caption → hard cut to app demoreaction video, demo video, hook text, optional music + second hook

Requirements

  • Node.js 18+
  • ffmpeg / ffprobe on PATH (media probing + frame extraction)
  • Headless Chrome is managed automatically by the HyperFrames CLI
  • Optional: yt-dlp for downloading page links (TikTok/IG/YouTube) as inputs

Quickstart

cd templates/reaction_demo

node new-reel.mjs \
  --reaction path/or/url/to/reaction.mp4 \
  --demo path/or/url/to/demo.mp4 \
  --hook "i was about to hit it and this app talked me out of it" \
  --render

# → renders/reel-1.mp4 (1080x1920 @ 30fps)

See each template's README for the full flag reference.

Repo layout

fonts/                      TikTok Sans (canonical copy + OFL license)
templates//           one self-contained HyperFrames project per template
  new-reel.mjs              generator: inputs → composition → render
  assets/fonts/             font embedded by generated compositions
  compositions/             generated per reel (gitignored)
  index.html                placeholder composition (real ones are generated)
RULES.md                    shared platform + style rules for all templates

Adding a new template

  1. npx hyperframes init templates/ --non-interactive --example=blank
  2. Copy fonts/ into templates//assets/fonts/
  3. Write a generator script that stamps out compositions from CLI inputs
  4. Follow RULES.md for typography, captions, safe zones, and audio defaults
  5. Add a README documenting the format and every flag

Related repositories

Similar projects matched by category, topics, and programming language.

react
Featured
react GitHub avatar

react

React is a JavaScript library for building user interfaces with declarative, component-based, and cross-platform design.

Web DevelopmentFrontend Frameworks
246,741
tandpfun
Featured
tandpfun GitHub avatar

wardrobe

A GPT‑image powered app that extracts individual garment cutouts from photos, organizes them into a digital wardrobe, and generates modeled outfit previews.

JavaScript
1,570
mshumer
Featured
mshumer GitHub avatar

Claude-of-Duty

A browser-based first-person shooter built entirely with procedural generation and orchestrated AI agents, featuring 55k lines of Three.js/WebGL2 code and no art assets.

AI & Machine LearningAI Agents
1,234