executing-plans
executing-plans
Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available
inference-workflowsGuides Krita AI Diffusion WorkflowInput construction, prompt preparation, inpaint, refine, upscale, control-image, and ComfyUI workflow lowering tasks.
Independent GitHub snapshot · Automated classification · Original documentation governs
Use this sub-skill when the task is about image-generation request payloads or how Krita AI Diffusion lowers plugin state into local ComfyUI/cloud work.
Trigger examples:
WorkflowInput.WorkflowKind.generate, refine, inpaint, refine_region,
upscale_simple, upscale_tiled, control_image, and custom.passes_count, cost, or request image payload shape without
running actual generation.backend.workflow or
backend.comfy_workflow.python sub-skills/inference-workflows/scripts/inspect_workflow_input.py --kind generate --round-trip
python sub-skills/inference-workflows/scripts/inspect_workflow_input.py --kind inpaint --round-trip
python sub-skills/inference-workflows/scripts/inspect_workflow_input.py --kind upscale-tiled --target 2048x1536 --round-trip
These commands construct tiny in-memory payloads and do not connect to ComfyUI, launch Krita, download models, call cloud APIs, or generate images.
WorkflowInput and related inputs.server-resources.DocumentModel.generate() enqueues a
particular workflow kind, route to ui-workspaces as well.custom-graphs.Image, Mask, Bounds, layer tokens, prompt comments, style JSON, or
PNG metadata, route to document-image-state.