genielabsopensource
- 4 skills
- 0 followers
- 17 hours ago last updated
- ▌ Spine Animation · genielabsopensource bundleCreate Spine 2D skeletal animations from pre-existing character assets (separated body-part PNGs, atlas spritesheet, or a full character image). Use this skill whenever the user wants to animate a 2D character, create Spine JSON from existing art assets, rig a character with bones, build walk/idle/run/attack animations, produce an interactive Spine Web Player preview, or generate Spine-compatible export files (.json + .atlas + .png). Also trigger when the user mentions "Spine animation", "2D rigging", "skeletal animation", "bone animation", "cutout animation", "animate this character", "make this walk", "create walk cycle", or uploads separated character body parts and wants them animated. This skill handles the full pipeline: asset analysis, skeleton rigging, animation keyframing, Spine JSON export, and interactive HTML5 preview.
- ▌
- ▌ Model Integration · genielabsopensource bundleConnect to and invoke image and video generation models across providers (Gemini / Nano Banana, fal.ai, Replicate, OpenAI GPT Image, xAI Grok Imagine) from an agent. Use this skill whenever a task needs to actually generate or edit an image or video and it is unclear which capability is available or how to call it — setting up API keys, detecting configured providers or MCP image tools, choosing the right model for a job (especially reference-following for style/character consistency), or writing the call. This is the execution layer the consistency skills delegate to when they say "invoke whatever image capability is available".
- ▌ Character Consistency · genielabsopensource bundleMaintain character identity and style accuracy when generating or editing images of a recurring character with multimodal image models (e.g., Nano Banana, GPT Image, Flux Kontext, Seedream, or any reference-conditioned model). Use this skill whenever the user asks to generate, edit, or iterate on images of a named or established character — especially when they mention keeping the character "on-model", consistent, accurate, or in-style, when generations keep drifting from the character's design, or when they want to set up, improve, or debug a character-generation workflow, dataset, reference sheet, or pipeline. Trigger even if the user just says a character "doesn't look right" across generations.