Install
openclaw skills install @normandmickey/reelsmithCreate short-form vertical video packages, preview reels, narrated reels, and AI-video workflows from ideas, articles, updates, or source material. Use when the user wants a topic turned into a short-form video concept, hook, script, scene-by-scene plan, on-screen text, caption, cover concept, approval-ready reel package, rough vertical preview video, narrated reel, or an LTX-powered AI video option for Facebook Reels and similar social formats.
openclaw skills install @normandmickey/reelsmithUse this skill to turn a topic into a Facebook Reels-ready content package. The output should feel like a practical creator workflow, not just a block of text.
Treat the core unit as:
Identify the topic and goal.
Identify the target style.
Decide the reel length.
Write a strong hook.
Build the short-form script.
Break the script into scenes.
Add packaging elements.
Keep it approval-first.
Unless the user asks for something else, use this structure:
Reel concept: [one-line concept] Tone: [tone] Length: [estimated seconds]
Hook [hook]
Script [full short-form script]
Scene breakdown
Caption [caption]
Hashtags [list]
Cover concept [headline + visual direction]
Approval status Awaiting user approval before production or publishing
If the user wants visuals, offer:
Do not assume full video automation exists yet. In v1, focus on producing a strong reel package that could later be recorded, edited, or automated.
There are now two preview paths:
A simple preview path can use scripts/make_reel_preview.py to turn scene text into a rough vertical MP4 preview. This is for pacing and structure review, not final polished production.
Example flow:
python3 scripts/make_reel_preview.py --title "My Reel" --scenes-file scenes.txt --output preview.mp4
For a less slideshow-like reel, use scripts/make_visual_reel_preview.py with scene JSON that points to per-scene background images. This keeps the old workflow intact while allowing a more video-like look with motion backgrounds and lighter text overlay.
Scene JSON shape:
[
{"bg": "/path/to/image1.png", "title": "Main title", "subtitle": "Short support line", "duration": 5.0},
{"bg": "/path/to/image2.png", "title": "Next beat", "subtitle": "Another short line", "duration": 5.0}
]
Run:
python3 scripts/make_visual_reel_preview.py --scenes-json scenes.json --output preview.mp4
The next production layer can add narration audio, then mux it with the preview video.
Current helpers:
scripts/openai_tts.pyscripts/mux_reel_audio.pyExample flow:
python3 scripts/openai_tts.py --text "Your reel narration" --style energetic --output narration.mp3
python3 scripts/mux_reel_audio.py --video preview.mp4 --audio narration.mp3 --output preview-with-audio.mp4
Expected env var:
OPENAI_API_KEYCurrent voice style presets:
defaultcalmprofessionalenergeticconfidentbroadcastFor sports and fast-moving updates, prefer:
energeticbroadcastconfidentThis keeps voiceover modular: script generation, preview assembly, narration generation, then final mux.
For a true AI-generated video option, Reelsmith can also use LTX via API instead of the local ffmpeg preview path.
Current helper:
scripts/ltx_text_to_video.pyExample:
python3 scripts/ltx_text_to_video.py \
--prompt "A cinematic vertical sports video showing a high-stakes college basketball showdown, dramatic arena lighting, crowd energy, and bold camera movement" \
--duration 8 \
--resolution 1080x1920 \
--output ltx-video.mp4
Expected env var:
LTX_API_KEYRecommended starting defaults:
ltx-2-3-fast1080x19208 or 10Use LTX mode when the user wants a reel to feel like a generated video instead of a slide-based preview.
After generating a reel package, offer one useful next step such as: