media-use

Resolve, generate, and operate on media assets for HyperFrames video compositions.

13|17|Updated Jan 30, 2025
One-click install
npx skills add https://github.com/CodeWithSally/CodeWithSally-Apex-English --skill media-use-codewithsally
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: media-use
Source: https://github.com/CodeWithSally/CodeWithSally-Apex-English/tree/main/Sessions/ClaudeCode/Session007/.agents/skills/media-use
Command: npx skills add https://github.com/CodeWithSally/CodeWithSally-Apex-English --skill media-use-codewithsally

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve? Building video compositions requires sourcing background music, sound effects, images, icons, logos, voiceovers, and color grades, then tracking them across projects. This Skill consolidates every media need into one resolve verb that returns frozen local files plus a ledger record, eliminating scattered asset hunting and context noise. ## Core Features & Use Cases - Unified media resolution: Resolve BGM, SFX, images, icons, brand logos, TTS voices, color grades, and LUTs through one command, with catalog search, generation fallback, and cross-project reuse via a local asset ledger. - Audio engine: Produce voiceovers with word-level timestamps, background music, sound effects, captions, transcription, and background removal through a shared audio pipeline. - Media operations and treatments: Cut, reframe, dither, and apply source-aware color treatments (VHS, camcorder, halftone, ASCII, film memory) with deterministic persistence through the hyperframes CLI. - Use Case: While building a product promo composition, run one resolve command per asset type to fetch a music bed, transition SFX, and brand logo, then apply a measured corrective grade to underexposed footage and generate a TTS voiceover with synced captions. ## Quick Start Ask the agent to resolve a background music track for your project with an intent like upbeat corporate promo, then verify setup with the resolve script's doctor flag.

Frequently Asked Questions about media-use

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I add background music and sound effects to a video composition?

Run the resolve script with --type bgm or --type sfx and a one-line intent description. It searches the HeyGen catalog and bundled library, freezes the chosen file locally, and records it in the project ledger for reuse.

How do I generate a TTS voiceover with word-level captions?

Use the shared audio engine with an audio_request.json listing your lines. It produces voice files plus an audio_meta.json containing word timestamps, which feed directly into caption generation and GSAP volume ducking keyframes.

What tool applies color grading or VHS effects to video footage?

The hyperframes media-treatment CLI persists grading presets, adjustments, and shader effects like tape damage or halftone onto real img or video elements. Tested recipes in the references provide bounded starting payloads for each look.

Does the dither script support HDR video input?

No. The dither processor is 8-bit SDR only and rejects PQ or HLG tagged sources with an explicit error. Tone-map HDR footage to Rec.709 first before running error diffusion.

Can I reuse media assets across multiple projects?

Yes. Resolved assets are frozen into a local .media directory with a manifest ledger. Use the --candidates flag to list reusable assets before resolving fresh, and --from to ingest externally generated files like custom LUTs.

Why does resolve fail on first run?

The HeyGen CLI must be installed and signed in before catalog retrieval or TTS works. Run the resolve script with --doctor to verify setup, and consult the setup-providers reference for provider configuration and offline modes.