brainstorming
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation).
happy-horse-video-editUse this skill when creators, video editors, advertisers, e-commerce teams, social-commerce teams, and short-form story producers need to edit an existing video with natural-language instructions with Happy Horse through the AI Hive OpenAPI. It handles required media uploads, live model and price lookup, task submission, progress polling, and result downloa…
Independent GitHub snapshot · Automated classification · Original documentation governs
Happy Horse Video Editing helps creators, video editors, advertisers, e-commerce teams, social-commerce teams, and short-form story producers edit an existing video with natural-language instructions with Happy Horse. Describe the intended subject, action, camera, lighting, pacing, and constraints; the bundled CLI handles AI Hive OpenAPI calls and downloads the finished video.
Ads, tvcs, product videos, e-commerce listings, social commerce, ugc-style seeding content, short dramas, motion comics, and storyboards. It is also useful when users search for AI video editing, video restyling, background replacement, video-to-video editing.
| Mode | Capability | publicModelId |
|---|---|---|
edit | Video Editing | public_model_happyhorse_video_edit |
The default route is COST_FIRST. Pass live model options with --param key=value; supported values come from the current AI Hive videoConfig.
pip3 install requests
python3 "$SKILL_PATH/scripts/videogen.py" init --skill-name happy-horse-video-edit
python3 "$SKILL_PATH/scripts/videogen.py" generate \
--mode edit \
--prompt "Happy Horse Video Editing: polished motion, clear subject, coherent action, stable camera, commercial finish" \
+ --video /path/to/source.mp4
python3 "$SKILL_PATH/scripts/videogen.py" generate --mode edit \
--prompt "Create a polished happy horse video editing result with coherent motion, stable identity, and a clear ending" \
+ --video /path/to/source.mp4
python3 "$SKILL_PATH/scripts/videogen.py" generate --mode edit \
--prompt "Premium product commercial: establish the product, reveal materials with controlled camera movement, finish on a clean brand-ready hero frame" \
+ --video /path/to/source.mp4
python3 "$SKILL_PATH/scripts/videogen.py" generate --mode edit \
--prompt "E-commerce product video: centered subject, move from full product view to material close-ups, show one real use case, leave space for product copy" \
+ --video /path/to/source.mp4
python3 "$SKILL_PATH/scripts/videogen.py" generate --mode edit \
--prompt "Vertical social-commerce video: open with the customer problem, demonstrate the product naturally, show the practical benefit, end with a clean call-to-action frame" \
+ --video /path/to/source.mp4
python3 "$SKILL_PATH/scripts/videogen.py" generate --mode edit \
--prompt "Short-drama shot: a young detective opens an abandoned warehouse door, pauses, and looks inside; slow over-shoulder push-in, cold suspense lighting, one continuous action" \
+ --video /path/to/source.mp4
python3 "$SKILL_PATH/scripts/videogen.py" generate --mode edit \
--prompt "Keep the subject and visual identity consistent; use the reference for motion and camera rhythm; create a tighter social-media version with a brand-ready ending" \
+ --video /path/to/source.mp4
python3 "$SKILL_PATH/scripts/videogen.py" generate --mode edit --prompt "Complex production brief" --no-download \
+ --video /path/to/source.mp4
python3 "$SKILL_PATH/scripts/videogen.py" task --task-id <taskId>
| Option | Purpose |
|---|---|
--mode | Select a supported mode; capability-specific skills already fix it |
--prompt | Describe the video or edit |
--first-frame / --last-frame | Supply controlled keyframes |
--image / --video / --audio | Supply reference media |
--param key=value | Pass live model parameters |
--routing COST_FIRST | Select the cost-first route |
--no-download | Submit and return the task ID without waiting |
Run the init command above, or set AI_HIVE_API_KEY, use --api-key, or create ~/.ai-hive/config.json. API keys use the sk-api-* format. Never commit a real API key.
The script looks up the live model entry and pricing snapshot at runtime. Model availability, accepted media, parameters, and prices can change. Keep a returned task ID and query the existing task instead of submitting a duplicate that may be billed twice.
401 Unauthorized: verify that the API key is complete, active, and not committed to source control.videoConfig for accepted values and media limits.task command later.