菜单
Publish AI-generated videos from a Google Sheet queue to YouTube and Instagram. Instagram Login API (graph.instagram.com), token exchange, Drive via gws. Use when publishing final_film.mp4 to social channels from Hermes VPS agents.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | social-publisher |
| version | 1.2.0 |
| description | Publish AI-generated videos from a Google Sheet queue to YouTube and Instagram. Instagram Login API (graph.instagram.com), token exchange, Drive via gws. Use when publishing final_film.mp4 to social channels from Hermes VPS agents. |
| triggers | ["social-publisher","publish-video","youtube-upload","instagram-reels"] |
Publish final_film.mp4 videos from a Google Sheet queue to YouTube and Instagram Reels.
Agent guide (prompting examples): README.md
Sheet quick guide: README tab in the Google Sheet
Uses Instagram Login API (graph.instagram.com), not Facebook Login.
| Env var | Purpose |
|---|---|
IG_APP_SECRET | Exchange/refresh tokens |
IG_SHORT_LIVED_TOKEN | From Meta dashboard Generate token (~1h) |
IG_ACCESS_TOKEN | Long-lived token (~60d) for publish |
IG_USER_ID | Instagram professional account ID |
SOCIAL_PUBLISHER_PUBLIC_BASE_URL | HTTPS — Meta fetches video_url from VPS |
Token scripts:
python scripts/exchange_instagram_token.py # short → long-lived
python scripts/refresh_instagram_token.py # extend before expiry
python scripts/verify_instagram_token.py # check token + user_id
If IG_ACCESS_TOKEN is empty but IG_SHORT_LIVED_TOKEN + IG_APP_SECRET are set, publish will auto-exchange for the session (prints reminder to persist token).
YT_CLIENT_ID, YT_CLIENT_SECRET, YT_REFRESH_TOKEN with youtube.upload scopecontainsSyntheticMedia=true (AI disclosure)thumbnail_drive_file_id in Queue sheetSee README.md for prompting examples.
python main.py --row <id> --platforms youtube --dry-run
python main.py --row <id> --platforms youtube
python main.py --row <id> --platforms instagram # needs HTTPS PUBLIC_BASE_URL
python main.py --row <id> --platforms youtube,instagram
python scripts/exchange_instagram_token.py
python scripts/verify_instagram_token.py --use-short-lived
Queue columns: id | brand | drive_file_id | thumbnail_drive_file_id | title | description | hashtags | platforms | visibility | status | yt_url | ig_url | errors
Accounts maps brand → credential_ref → env keys (YT_MAIN, IG_MAIN).
| Issue | Fix |
|---|---|
| IG token invalid | Regenerate in Meta dashboard; run exchange_instagram_token.py |
| IG container ERROR | Ensure PUBLIC_BASE_URL is HTTPS and video URL is reachable |
| Token exchange fails | Check IG_APP_SECRET is the Instagram app secret (not webhook verify token) |
| YT invalid_scope | Re-run setup_youtube_oauth.py |
ADK multi-agent story-to-video: vision-grounded LTX motion prompts, Grok refs, LTX 2.3 I2V.
Turn story manifests into scene images using agent-composed prompts (prompt.json) and config-driven workflow templates. Supports model swapping (Qwen, HiDream, etc.) without code changes. Covers character sheet generation (Gemini or ComfyUI T2I fallback), prompt composition, batch scene generation, and vision-based evaluation (OpenRouter Gemini 3.1 Flash Lite with thinking tokens, or Gemini API fallback).
Parse ComfyUI workflow JSONs, extract all required models (UNET, CLIP, VAE, LoRA, checkpoints) and custom node packs, research download URLs via HuggingFace CLI (never download!), and generate self-contained provisioning-ready bash scripts for $REPO_ROOT/workflows/setup/. Scripts must be platform-aware (Vast.ai + RunPod) and end with a ComfyUI restart.
Turn stories into highly consistent cinematic videos using a deterministic 9-step pipeline orchestrated by Google ADK and wave execution.
Turn stories into highly consistent cinematic videos using a cloud-based image generation backend (Grok Imagine via fal.ai) and self-hosted LTX-2.3 FLF2V video generation.
Turn story manifests into highly consistent cinematic videos using a 3-stage model chain: Ideogram 4 (T2I) for scene still generation and character sheets, Flux Klein 9B (I2I) for character consistency editing (edit pass), and LTX 2.3 FFLF Seed Hunter for video generation. Utilizes the batch-wave model with automated quality evaluation gates.