Write or refine Kling AI image prompts, including prompt-only requests, or generate and edit images through the Kling AI MCP in Claude Code. Use for posters, product photography, portraits, covers, ad
Kling Ai Generate Image connects to an MCP server. It can need an account, an API key, or paid credits, and copying the prompt alone will not work. See the source repository for pricing and setup.
/plugin marketplace add klingai-tech/claude-plugin
/plugin install kling-ai@klingai
Deliver the user's current step. For writing or refining an image prompt only,
return the requested prompt and finish. Preserve composition requirements such
as left-side copy space; do not append model, aspect-ratio, resolution or output
count recommendations, or invitations to generate. The workflow and quality
defaults below apply only when preparing or submitting generation, not to
prompt-only writing.
For generation, follow the Claude Code OAuth, billing confirmation,
single-submission, status, and result rules in the [core Kling Skill](../kling-ai/SKILL.md).
Read [prompt construction](references/prompt-construction.md) for reference images, exact copy, branded assets, or controlled variants. Read [scene patterns](references/scene-patterns.md) for product, advertising, portrait, poster, or cover work. For Element reuse or local media, also read the core [asset workflows](../kling-ai/references/asset-workflows.md).
text_to_image for a new image. Use image_to_image when source media controls identity, product structure, composition, editable content, or style. An attachment alone does not determine the mode.taskTraceId for this objective, follow [capability discovery](../kling-ai/references/capability-discovery.md), and select a compatible tool/model pair from this account's who_am_i response. Apply [model parameters](../kling-ai/references/model-parameters.md) before constructing arguments or reference bindings.query_tasks from the model. If no App mounts, follow the core Skill's headless polling fallback; never resubmit.element_get, and choose a model that explicitly supports the resource type and binding argument. Check individual and combined reference caps, and bind the exact ID with the model's declared prompt and structured syntax.query_tasks; it does not create an image.2k for normal delivery, 4k for commercial work, advertising, fine materials, or crop-heavy post-production, and 1k only for drafts, speed, or credit savings. Never lower a higher live default.1:1 for square social or product media, 4:5 for portrait feeds, 9:16 for stories or vertical covers, and 16:9 for banners or thumbnails.Before submission, internally check focal subject, visual hierarchy, safe area, lighting, reference roles, and conflicting instructions. Claim visual QA only when the result was actually inspected.
Weekly roundup of top Claude Code skills, MCP servers, and AI coding tips.