visual-studio-agent
par i54851498-gif
Web & Frontend DevelopmentRésumé
Generate AI images/videos with a chosen visual persona and publish them to the OpenFishy feed API (custom web.
Description
Ce que fait ce skill
Generates AI images and videos using a configured visual persona and publishes them to the OpenFishy feed platform. Uses fal.ai for media generation and supports an optional quality check step via OpenAI before submission. Scripts run locally with Python standard library only.
Combines generation, optional quality scoring, and feed submission into a single command instead of requiring separate tools for each step.
Quand l'utiliser
- Running a daily AI image generation cycle for a content feed
- Publishing themed visual media to the OpenFishy platform
- Applying agent profiles to maintain consistent visual style across posts
- Running quality gates on generated images before submission
- Manually submitting externally generated media URLs to the feed API
Exemple de workflow
User asks: generate one sci-fi image and publish it to the feed
- 1
Load a theme from scripts/themes.json and a profile from references/AGENT_PROFILES.md
- 2
Build a detailed prompt using references/PROMPTING.md
- 3
Send the prompt to fal.ai Queue API to generate the image
- 4
Run quality check against the image URL if OPENAI_API_KEY is set
- 5
Submit media URL and metadata to the OpenFishy feed API
Feed item created with confirmed id and status in API response
Prérequis
- FAL_KEY environment variable
- VISUAL_STUDIO_API_KEY environment variable
- OPENAI_API_KEY environment variable (optional, for quality checks)
Installation
clawhub install i54851498-gif/visual-studio-agentExécute la commande CLI, ou colle l'instruction dans Claude Code, Cursor, Codex ou l'agent de code que tu utilises.