360 Secure SkillHub
360 安全技能中心

Kenerate AI Creative Workflow

该技能默认纯文本运行，配套只读MCP不消耗生成额度、不直接产出媒体；可协助梳理创意简报，匹配图/视/音频类适配的AI生成工作流，审核提示词合规性与合理性，提醒生成前校验实时模型能力、规格与成本，输出含迭代安排、合规检查项的可执行生成计划，适合AI创意生产前期筹备使用。

gpt-img-2
gpt-img-2
热度 16.39
最近更新 2026-10-09 22:24:02
分类：创作依赖：MCP 服务 / 内部调用大模型应用场景：图像生成 / 视频编辑 / 品牌素材

安装技能

复制下面的话术发给你的 Agent，它会通过 secure-skills 检索并安装该技能。

执行命令安装此 skill： npx secure-skills-cli add kenerateai-creative-workflow
Metadata
name
kenerateai-creative-workflow
description
Plan and review image, video, and audio generation workflows. Use for creative briefs, workflow selection, prompt design, prompt audits, reference-media checks, iteration plans, and Kenerate AI navigation; verify live model capabilities and costs before generation.
metadata
{"openclaw":{"homepage":"https://kenerateai.org/workspace","version":"1.0.0"}}

Kenerate AI Creative Workflow

Turn a creative goal into an inspectable image, video, or audio production plan. This Skill is text-only by default. Its optional MCP is deterministic and read-only: it does not call models, upload media, access accounts, consume credits, submit jobs, or promise output quality, pricing, or current availability.

Build the brief

State the objective, audience, subject, deliverables, required formats, deadline, brand constraints, and source-media rights. Use only references that the user owns or has permission to use. Do not imitate a living artist or clone a person's face or voice without authorization.

Choose the workflow

  • Use text-to-image when the starting point is a written visual description.
  • Use image-to-image for a permitted reference and a requested variation.
  • Use image-to-prompt to extract editable visible details from a reference.
  • Use PNG Maker for a transparent-background image when supported.
  • Use text-to-video for a written scene, action, and camera plan.
  • Use image-to-video to animate a permitted starting image.
  • Use text-to-music for genre, mood, tempo, instrumentation, and structure.

Model support, formats, duration, resolution, and credit cost can change. Check the live studio before submission.

Use the optional MCP

  • build_creative_brief structures the goal, audience, subject, deliverables, constraints, and rights check.
  • choose_generation_workflow maps the medium and available source material to a public Kenerate AI workflow.
  • audit_generation_prompt checks concrete direction, rights, vague wording, and changing claims.
  • get_kenerateai_resources returns canonical public Kenerate AI pages.

Connect the stdio server with:

openclaw mcp add kenerateai \
  --command npx \
  --arg -y \
  --arg github:gpt-img-2/kenerateai-creative-workflow-mcp \
  --include 'build_creative_brief,choose_generation_workflow,audit_generation_prompt,get_kenerateai_resources'

Then run openclaw mcp doctor kenerateai --probe. If the installed release lacks that command group, add npx -y github:gpt-img-2/kenerateai-creative-workflow-mcp as a Stdio server in MCP settings. Never imply that the MCP or Kenerate AI generated media when it did not.

Return an actionable plan

Return Objective, Audience, Workflow, Inputs, Prompt, Settings to verify, Rights check, Iteration plan, and Success criteria. Change one variable per iteration so differences remain attributable.

Canonical resources