{
 "schema": "aiblocks-page/1",
 "id": "visual-prompt-director",
 "type": "skill",
 "name": "Image and video prompt director",
 "summary": "Turn a rough idea or a bad result into an image or video prompt you can paste today. Get gaps flagged and one change to try next.",
 "headline": "Image and video prompt director",
 "subhead": "Share an image or video idea, rough prompt or bad result. Get a usable prompt, clear gaps and one focused next change. Bring the brief and any files you want it to use.",
 "job": {
  "id": "make-images",
  "name": "Make images and art"
 },
 "level": "intermediate",
 "thinking": "medium",
 "tested": true,
 "updated": "2026-10-28",
 "first_published": "2026-10-25",
 "inputs": [
  {
   "type": "brief",
   "required": true,
   "label": "Brief",
   "what": "a creative brief: goal, audience, angle, offer, mandatory claims (by ID), formats"
  },
  {
   "type": "image",
   "required": false,
   "label": "Image",
   "what": "a finished picture"
  }
 ],
 "outputs": [
  {
   "type": "image_prompt",
   "required": true,
   "label": "Image prompt",
   "what": "a render-ready image prompt plus the reference roles it uses"
  },
  {
   "type": "video_prompt",
   "required": true,
   "label": "Video prompt",
   "what": "a render-ready prompt for one video shot, with the references it uses"
  }
 ],
 "you_give": [
  "Your idea, rough prompt, or a bad result with the prompt that made it",
  "Reference images or clips you want it to follow (optional)",
  "Any words that must appear in the picture (optional)",
  "The image or video tool you plan to use (optional)"
 ],
 "you_get": [
  "A list of confirmed details, kept apart from the AI's own choices",
  "A copy-ready image or video prompt, with assumptions marked",
  "The missing layers, each with one or two ways to fill it",
  "One change to try next, and anything that was not checked"
 ],
 "use_when": [
  "You have an idea for an image or video and need a prompt you can paste today.",
  "You have a rough prompt that gives poor results and want it repaired.",
  "A result came out wrong and you want to know which one thing to change."
 ],
 "skip_when": [
  "You want the final image or video made: use an image or video generation tool, since this only writes the prompt.",
  "You need a logo or full brand look: work with a designer, because this writes one-off prompts, not brand identity.",
  "You already have a prompt that works and only want small word tweaks: edit it by hand."
 ],
 "output_sample": {
  "input": [
   "Your image or video idea, or a rough prompt",
   "A bad result you want fixed (optional)",
   "Reference images or clips (optional)",
   "The AI model you plan to use (optional)"
  ],
  "prerequisites": [
   "An AI that can view images, only if you share reference images"
  ],
  "output": [
   {
    "name": "CONFIRMED DETAILS",
    "contains": "The facts that came from you or your references, kept apart from the AI's own choices."
   },
   {
    "name": "PROMPT",
    "contains": "A copy-ready prompt block built from your brief, with any assumptions marked."
   },
   {
    "name": "OPTIONAL GAPS",
    "contains": "Missing layers such as light or camera, each with one or two concrete ways to fill it."
   },
   {
    "name": "NEXT ITERATION",
    "contains": "One controlled change to try if the result was bad or needs work."
   },
   {
    "name": "NOT RUN",
    "contains": "Anything that was not checked or made, such as image generation or a reference it could not see."
   },
   {
    "name": "CHECKS MISSED",
    "contains": "One line for each check that failed or could not run, or none."
   }
  ]
 },
 "how_to_use": [
  "Open Claude, ChatGPT or Gemini and paste in the skill text from the download.",
  "Paste your idea, rough prompt or bad result. Add reference images if your AI can view them.",
  "Say which image or video model you will use, if you know. If not, the prompt stays model-neutral.",
  "Read the confirmed details first. Fix anything the AI got wrong.",
  "Copy the prompt into your generation tool. Change only the one thing in the next step, then try again.",
  "If the result is still wrong, run it again with the new result. Keep the confirmed details and change one thing only. If the same fault shows after two rounds, stop and try a different tool or a different reference."
 ],
 "checks": [],
 "next": [
  {
   "name": "Multi-provider image maker",
   "url": "https://useaiblocks.com/skills/multi-provider-image-maker",
   "why": "Multi-provider image maker"
  }
 ],
 "source": null,
 "credits": [],
 "files": [
  "references/creator-product-style-presets.md",
  "references/reference-library-and-coverage.md",
  "references/visual-image-examples.md",
  "references/worked-example.md"
 ],
 "links": {
  "page": "https://useaiblocks.com/skills/visual-prompt-director",
  "markdown": "https://useaiblocks.com/skills/visual-prompt-director.md",
  "json": "https://useaiblocks.com/skills/visual-prompt-director.json",
  "instructions": "https://useaiblocks.com/skills/visual-prompt-director/SKILL.md",
  "download": "https://useaiblocks.com/skills/visual-prompt-director.zip",
  "api_item": "https://useaiblocks.com/api/v1/items/visual-prompt-director",
  "api_document": "https://useaiblocks.com/api/v1/documents/skill/visual-prompt-director",
  "mcp": "https://useaiblocks.com/mcp"
 }
}