git:20260826.a3b9604 to git:20260922.10a5d60

+ description: Generate image assets through iPolloWork's image service, whether Image Studio is open or closed.

+ Use this Skill for a requested new image or a missing supporting image identified while authoring a PPT, website or video. Image Studio does not need to be open. Plan assets during initial creation/full redesign; preserve narrow edit scopes and explicit no-image requests. Reuse suitable assets first; visual clarity and context are valid reasons to generate, not only absolute necessity. Assess the visual purpose, existing assets and best medium internally; no separate assessment report is required. Keep diagrams editable, treat pure decoration as optional, and never present generated illustrative scenes as real evidence.

+ 2. Discover `openai-image-generation` using `ipollowork_extension_list_actions`, then call its `status` action. Call status first and check authorization, capabilities and supported parameters. Preserve a model explicitly selected for this task or captured workbench request. If it is unavailable or unsuitable, ask before substituting unless alternatives were already authorized, and continue independent file work. For no explicit model, use a verified suitable user-saved preference or existing automatic-selection policy, or the sole suitable authorized model within the task scope and allowed cost settings. With multiple suitable models and no such preference or policy, ask once for the task before committing any image-dependent page; never silently use `defaultModel` or downgrade to shapes merely to avoid the question. Continue independent text/layout work if useful, mark the asset pending, and do not claim the complete deliverable until the choice is answered or the user declines the image. Reuse the verified selection for compatible assets; recheck when the model, operation, parameters or authorization state changes or a service error requires it. A first-result/defaultModel fallback is not evidence of a saved user preference. Missing authorization or an unqueryable capability must not block the caller or open settings: report the state and continue. Never request keys in chat. Do not invent preferences or budgets. Pass the chosen stable model ID explicitly. Never submit variants outside scope; query or recover uncertain jobs before resubmitting. In this image status response, `defaultModel` is an automatic first-available candidate, not a persisted user preference. For an explicit workbench settings/annotation request, honor its captured selection instructions; do not change the workbench model through UI automation.

+ 3. After resolving the model by this policy, call `image_generate` through `ipollowork_extension_call` with that exact stable `model` ID, the prompt, and optional quality/size. Include style, camera, and lighting requirements in the prompt.

+ 4. Use this server action for ordinary chat requests even when Image Studio is open. UI tool discovery and opening the workbench are unnecessary. Use workbench tools only when the user explicitly requests the current workbench settings or selection. Never request, print, or place API keys in a prompt or workspace file.

+ 5. Save generated results as new workspace artifacts and include a Markdown image link to the exact returned path in the final response. Never claim success until the action returns the saved file. For a composition, place the saved image under its existing assets directory, use a project-relative reference, and verify loading, crop and export compatibility before delivering the composition. Standalone images can be opened in Image Studio from the conversation.

+ 6. Keep the first pass focused. Generate variants only when the user asks for alternatives.