Muapi Social Media Video
Generate platform-tuned social videos (aspect, duration, tier) from a director brief using Seedance 2.0 and optional reference frames.
Overview
muapi-social-media-video is an agent skill most often used in Grow (also Launch distribution) that orchestrates reference images and Seedance 2.0 videos with platform-specific social defaults.
Install
npx skills add https://github.com/samuraigpt/generative-media-skills --skill muapi-social-media-videoWhat is this skill?
- Bash orchestrator: run-social-video.sh with --platform instagram and extensible platform presets
- Wires reference-image generation (--gen-ref, --gen-ref-last) before Seedance 2.0 video
- Modes include t2v with tier (e.g. chinese), quality basic, optional async and view flags
- Loads SKILLS_ROOT .env and resolves generate-image.sh + generate-seedance.sh paths
- Requires bash 3.2+, curl, and jq for end-to-end CLI pipelines
Adoption & trust: 544 installs on skills.sh; 3.5k GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
You have a creative brief for social video but juggling separate image APIs, motion models, and per-platform aspect or duration settings slows every post.
Who is it for?
Indie makers batching Reels-style clips with consistent technical settings and agent-operable shell scripts.
Skip if: Builders without generative API keys, without the samuraigpt skills tree layout, or who need broadcast compliance review workflows.
When should I use this skill?
You have a director brief and need a Seedance 2.0 social video with optional first/last reference images and platform presets.
What do I get? / Deliverables
One bash-driven run produces a platform-aligned Seedance video (and optional reference frames) from your prompt using shared .env credentials.
- Rendered social video file from Seedance pipeline
- Optional reference images from --gen-ref / --gen-ref-last
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Short-form video is a core Grow motion for indie products; this skill automates creation with channel defaults rather than one-off exports. Content subphase is the canonical shelf because the orchestrator’s main output is social-ready motion assets, not store ASO or SEO copy.
Where it fits
Turn a weekly feature highlight brief into a 9:16 clip with default Instagram duration without reopening three different tools.
Ship a launch-day teaser video using the same orchestrator flags your agent already knows from content runs.
Test whether AI-generated motion matches your positioning before committing to a paid ad test.
How it compares
A workflow skill package that chains local shell generators—not a hosted Canva-style editor or a single-model chat prompt.
Common Questions / FAQ
Who is muapi-social-media-video for?
Solo builders and small teams using agentic CLIs to produce short-form social video as part of product marketing, not enterprise studio pipelines.
When should I use muapi-social-media-video?
In Grow when creating lifecycle content; at Launch when you need a distribution-ready announcement video with Instagram-oriented defaults; optionally in Validate when prototyping ad creative.
Is muapi-social-media-video safe to install?
It sources API secrets from .env and runs shell plus network calls—check the Security Audits panel on this page and rotate keys if you fork the scripts.
SKILL.md
READMESKILL.md - Muapi Social Media Video
#!/bin/bash # Social Media Video Generator — Orchestrator # # Generates reference images (if requested) then produces a Seedance 2.0 video, # all wired to platform-specific defaults (aspect ratio, duration, tier). # # Usage: # bash run-social-video.sh --prompt "director brief" --platform instagram [options] # # Requires: bash 3.2+, curl, jq set -euo pipefail # ============================================================ # Locate skills root (works regardless of CWD when invoked) # ============================================================ SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)" SKILLS_ROOT="$(cd "$SCRIPT_DIR/../../../.." && pwd)" GENERATE_IMAGE="$SKILLS_ROOT/core/media/generate-image.sh" GENERATE_SEEDANCE="$SKILLS_ROOT/library/motion/seedance-2/scripts/generate-seedance.sh" # Load .env from skills root if [ -f "$SKILLS_ROOT/.env" ]; then set +u; source "$SKILLS_ROOT/.env" 2>/dev/null || true; set -u fi # ============================================================ # Defaults # ============================================================ PROMPT="" PLATFORM="instagram" CAMERA="" MODE="t2v" TIER="chinese" FAST=false ASPECT="" DURATION="" QUALITY="basic" VIEW=false ASYNC=false IMAGE_FILES=() # Reference image generation GEN_REF_FIRST="" # --gen-ref "prompt" → generate first frame ref GEN_REF_LAST="" # --gen-ref-last "prompt" → generate last frame ref REF_MODEL="google-imagen4-ultra" # ============================================================ # Argument parsing # ============================================================ while [[ $# -gt 0 ]]; do case $1 in --prompt|-p) PROMPT="$2"; shift 2 ;; --platform) PLATFORM="$2"; shift 2 ;; --camera) CAMERA="$2"; shift 2 ;; --mode) MODE="$2"; shift 2 ;; --tier) TIER="$2"; shift 2 ;; --fast) FAST=true; shift ;; --aspect) ASPECT="$2"; shift 2 ;; --duration) DURATION="$2"; shift 2 ;; --quality|-q) QUALITY="$2"; shift 2 ;; --view) VIEW=true; shift ;; --async) ASYNC=true; shift ;; --file|-f) IMAGE_FILES+=("$2"); shift 2 ;; --gen-ref) GEN_REF_FIRST="$2"; shift 2 ;; --gen-ref-last) GEN_REF_LAST="$2"; shift 2 ;; --ref-model) REF_MODEL="$2"; shift 2 ;; --help|-h) cat <<'HELP' Social Media Video Generator Usage: bash run-social-video.sh --prompt "director brief" [options] REQUIRED --prompt, -p TEXT Seedance 2.0 Director Brief (the full cinematic prompt) PLATFORM (sets aspect/duration defaults) --platform NAME instagram | tiktok | linkedin | youtube | youtube-short | twitter | pinterest | instagram-feed (default: instagram) CAMERA STYLE (appends camera directive to prompt) --camera TYPE fpv | drone | flythrough | reveal | epic | product | narrative | tracking | orbit (default: from --platform) VIDEO OPTIONS --mode MODE t2v | i2v | first-last | omni (default: t2v) --tier TIER chinese | global | vip (default: chinese) Note: first-last requires global or vip --fast Use fast-queue variant (global/vip only) --aspect RATIO Override platform default aspect ratio --duration N Override platform default duration (seconds) --quality Q basic | high (Chinese tier only; default: basic) --view Download and open output (macOS) --async Return request_id without waiting REFERENCE IMAGES --file, -f PATH Provide an existing image file (repeatable, up to 9) --gen-ref TEXT Generate a first-frame reference image from this prompt --gen-ref-last TEXT Generate a las