Model-family-specific prompt craft for model endpoints. Trigger when the user mentions a specific model family by name and asks how to prompt it ("how do I prompt Kling", "GPT Image 2 prompt structure", "Happy Horse tips"), or when prompts to a routed endpoint keep coming back generic and the family's known nuances should be applied. For endpoint selection ("which model for X"), use `model-catalog` instead. This skill is about how to talk to a model once it has been chosen.
Model-family-specific prompt craft for model endpoints. Trigger when the user mentions a specific model family by name and asks how to prompt it ("how do I prompt Kling", "GPT Image 2 prompt structure", "Happy Horse tips"), or when prompts to a routed endpoint keep coming back generic and the family's known nuances should be applied. For endpoint selection ("which model for X"), use `model-catalog` instead. This skill is about how to talk to a model once it has been chosen.
Model Prompting
Runtime: All endpoint calls use the vg generate CLI (npm install -g vibedgames, or pnpm dogfood in this repo). The API key lives on the vibedgames server, so there is no per-machine setup. See the generate skill for the command reference.
Model families have meaningful prompting nuances. A prompt that works on GPT Image 2 (long, structured, exact text in quotes) will fail on Happy Horse (which wants ~20 plain-English words). This skill collects family-specific guides.
Style tags need visual targets. "Minimalist brutalist" → "cream background, heavy black sans serif, asymmetrical type block, generous negative space."
One controlled variable per iteration. Comparison only works when one axis changes at a time.
Inspect schema before assuming a control exists.vg generate schema <endpoint_id> --json. Negative prompt, seed, multi-prompt, and reference-image fields differ across families.
