メニュー
End-to-end video generation via fal.ai through Starchild paid proxy. Covers text-to-video, image-to-video, video-to-video, model selection, billing, polling, and serving local reference assets via a public preview.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
TQX (tqx.trade) HK/US stock quant workflow via tqx-cli: cross-sectional factor analysis, event-driven strategy backtests on the panda_backtest engine, and agent-driven automated paper trading. Use when the user wants to run factor IC/IR analysis, backtest a Python trading strategy on Hong Kong or US stocks, or set up agent-automated trading (e.g. "backtest a moving-average strategy on AAPL", "analyze a momentum factor on HK stocks", "let the agent trade my paper account").
End-to-end blog management for AI agents. Write, import, build, preview, and publish articles using the blog template. Covers draft workflow, article import, SEO, OG images, and deployment.
中学物理实验教学参赛方案套件。包含四个完整实验（单摆测g、声悬浮测声速、向心力定量演示仪、电磁阻尼定量研究），每套含固件源码、3D打印图纸、教学PPT、教学文稿、采购清单、调试手册、视频分镜脚本、模拟器。Use when a teacher/student needs a complete, classroom-ready physics experiment package for competition or teaching.
自动搜索全网前沿实验方案（学术论文、开源硬件、竞赛项目、创客社区）， 评估可行性后生成完整实现（BOM采购清单、固件代码、电路图、3D打印件、 Web仪表盘、教学文档）。 Use when exploring new experiment ideas, searching for cutting-edge DIY/physics/engineering project implementations, or when the user says "找一下XX实验/项目/方案" and wants a complete, buildable solution.
ESP8266/ESP32 + 磁簧开关/霍尔传感器 单摆测重力加速度实验套件。 硬件搭建→固件烧录→数据采集→Web仪表盘→g值计算→教学文档，一站式完成。 Use when the user wants to build a pendulum g-measurement experiment, measure gravity with a micro-controller, or needs a complete physics experiment package with hardware + firmware + dashboard + teaching materials.
Single-command cross-chain token bridge for USDC/USDT across 6 EVM chains with Alchemy Account Abstraction gas sponsorship.
| name | @554/video |
| version | 3.0.0 |
| description | End-to-end video generation via fal.ai through Starchild paid proxy. Covers text-to-video, image-to-video, video-to-video, model selection, billing, polling, and serving local reference assets via a public preview. |
| metadata | {"starchild":{"emoji":"🎬","skillKey":"video","requires":{"env":["FAL_KEY"]}}} |
| user-invocable | true |
| disable-model-invocation | false |
Use this skill for all video-generation requests on Starchild.
Core principle: call the provided scripts. Do not re-implement proxy/billing/upload plumbing.
exec(open('skills/video/generate_video.py').read())
result = generate_video(
prompt="A cinematic drone shot over snowy mountains at sunrise",
model="balanced", # "budget" | "balanced" | "premium"
duration=5,
)
# result -> {"success": True, "cost": 0.70, "video_url": "...", "local_path": "output/videos/..."}
generate_video automatically: submits → polls → fetches result → downloads mp4 to output/videos/.
fal.ai needs the reference asset as a public https URL. fal storage upload requires a Serverless permission your key currently does not have. The reliable path is to expose the asset via a published Starchild preview.
output/fal_assets/ using publish_asset.py.fal-assets is running and published (one-time setup, see §3).<preview_base>/<filename>.generate_video(... image_url=public_url).# Step 1: publish a local image into the asset folder
exec(open('skills/video/publish_asset.py').read())
asset = publish_local('/path/to/your/photo.jpg')
# or: publish_from_url('https://example.com/photo.jpg')
filename = asset['filename']
# Step 2: combine with the preview's public base URL (see §3)
public_url = f"https://community.iamstarchild.com/<user_slug>-fal-assets/{filename}"
# Step 3: image-to-video
exec(open('skills/video/generate_video.py').read())
result = generate_video(
prompt="gentle cinematic camera push-in",
model="balanced",
duration=5,
image_url=public_url,
)
generate_video auto-rewrites the model path from */text-to-video to */image-to-video whenever image_url is provided. The same approach works for video-to-video models — pass an mp4 URL instead.
publish_asset.py).jpg .jpeg .png .webp .gif .bmp, max 10 MB.mp4 .mov .webm .mkv .m4v, max 100 MBfal-assets public preview setupRun this once per workspace. The preview keeps running across sessions.
# 3.1 ensure the asset folder exists with a placeholder index
import os, pathlib
pathlib.Path('output/fal_assets').mkdir(parents=True, exist_ok=True)
if not os.path.exists('output/fal_assets/index.html'):
open('output/fal_assets/index.html', 'w').write(
'<!doctype html><html><body><h1>fal asset host</h1></body></html>'
)
# 3.2 start the preview
preview(action='serve', dir='output/fal_assets', title='fal-assets')
# 3.3 publish to a public URL
preview(action='publish', preview_id='<id from step 3.2>', slug='fal-assets', title='fal-assets')
# → public base: https://community.iamstarchild.com/<user_slug>-fal-assets/
After publish, the public base URL is reusable for every future image-to-video / video-to-video task. Files dropped into output/fal_assets/ become reachable as <base>/<filename> immediately — no re-publish needed.
Verify with:
curl -sI https://community.iamstarchild.com/<user_slug>-fal-assets/<filename>
# expect: HTTP/2 200, content-type: image/* or video/*
If preview(action='serve') returns No available ports in pool, ask the user which existing preview can be stopped to free a port — never silently kill one.
| Tier | Model | Cost / 5s | Notes |
|---|---|---|---|
| budget | fal-ai/wan/v2.5/text-to-video | $0.25 | Fastest, cheapest; good for prompt iteration |
| balanced | alibaba/happy-horse/text-to-video | $0.70 | Default; best lip-sync, most use cases |
| premium | bytedance/seedance-2.0/fast/text-to-video | $1.20 | Best motion + camera direction |
Override by passing the full model id to generate_video(model=...). Image-to-video variants are auto-derived by replacing text-to-video with image-to-video.
Pricing details and model registry live in generate_video.py::estimate_cost.
exec(open('skills/video/poll_status.py').read())
result = poll_video("019ded6c-d871-7290-bbf1-ddc6993f8958")
Use this when an earlier generate_video call timed out or you only have a request_id.
generate_video.py — submit → poll → download. Handles text-to-video and image-to-video.publish_asset.py — copy local files (or download remote URLs) into output/fal_assets/ so they can be served by the fal-assets preview.poll_status.py — resume polling by request_id, downloads the result on completion.| Problem | Fix |
|---|---|
image_url must be a public HTTP(S) URL | Use publish_asset.py + fal-assets preview, then pass the public URL |
No available ports in pool (preview serve) | Ask the user which preview to stop; do not auto-kill |
downstream_service_error after COMPLETED | Reference asset host failed mid-render — re-encode/resize to 16:9, re-publish, retry |
HTTP 402 insufficient_credits | Top up balance; cost is pre-charged on submit |
HTTP 403 endpoint_not_allowed | sc-proxy only allows approved fal video endpoints; pick one from the model table |
Generation FAILED upstream | Shorten prompt, drop unusual tokens, retry once before changing model |
Job stuck IN_PROGRESS >15 min | Save request_id, resume later with poll_status.py |
sc-proxy → queue.fal.run (and api.fal.ai) → fal model providersAuthorization: Key fake-falai-key-12345 (proxy injects the real FAL_KEY)403 endpoint_not_allowed.https://*.fal.media/... — public CDN, no auth needed for download.generate_video.py::estimate_cost and in transparent-proxy/apis/falai.py::_VIDEO_PRICING.FAL_KEY lacks Serverless permission. Keep using the preview-based approach until that changes.