AI Poster Generator Skills Served By Craftsman Agent, Generate Editable AI Poster using sota Image models and design config, support various formats, ratio, design styles
Design & media
poster-design-studio
Try itTurn a topic description, a product photo, or brand references into a scroll-stopping event poster, promotional banner, or social media graphic. This AI poster maker and design generator creates photo-rich posters with strong visual hierarchy, category-matched styling, and text-safe zones for event, music, movie, product launch, and sale campaigns. Use it as an AI flyer maker for sale flyers, an event poster design tool, a movie poster generator, a music festival poster creator, a banner design AI for product launch posters, or a graphic design poster studio. Start from a campaign topic, transform a product or scene photo with style references, or refine an accepted draft toward a print-ready or share-ready result.
What it does
Turn a topic description, a product photo, or brand references into a scroll-stopping event poster, promotional banner, or social media graphic. This AI poster maker and design generator creates photo-rich posters with strong visual hierarchy, category-matched styling, and text-safe zones for event, music, movie, product launch, and sale campaigns. Use it as an AI flyer maker for sale flyers, an event poster design tool, a movie poster generator, a music festival poster creator, a banner design AI for product launch posters, or a graphic design poster studio. Start from a campaign topic, transform a product or scene photo with style references, or refine an accepted draft toward a print-ready or share-ready result.
The skill document
Poster Design Studio
Create one scroll-stopping poster, flyer, or promotional banner from a topic description, a product or scene photo, or an accepted draft. Reuse decisions already present in the conversation and move by the shortest route that completes the requested poster.
Choose the route
- Generate a poster from a topic: when the user describes an event, sale,
movie, music night, product launch, or social campaign and no source photo is
required, turn the brief into a complete poster visual using
beatra.images.generate. This is the default when the request is topic-led. - Transform a photo into a poster: with a product, scene, or brand photo,
elevate it into a polished poster or banner with strong hierarchy, category
styling, and a text-safe zone using
beatra.images.transform. This is the default when a source photo exists. - Refine an accepted draft: use
beatra.images.editwith the accepted poster asimages[0]to fix color, composition, text area, or background without changing the overall layout.
Follow poster routing for the precise branch and poster craft when turning the request into a visual specification that fits the poster type and category.
Shape one poster brief
Reuse the user's campaign topic, poster type, target audience, style preference, and any visual references. Ask only when a missing decision materially changes the result. For a standard poster, propose the canvas that matches the destination—A-series print, social media ratio, or standard poster proportion—with a clean text-safe zone for the headline.
Build the brief around:
- the poster type and category—event poster, promotional banner, music or concert poster, movie poster, product launch, sale or flyer, or social media graphic;
- the headline message—the event name, film title, sale offer, or campaign line that anchors the composition;
- one focal subject—the performer, product, hero scene, or key visual that anchors the poster;
- one style direction—clean and futuristic (tech), warm and appetizing (food), editorial and bold (fashion), vibrant and energetic (music), professional and clean (corporate), or friendly and approachable (education);
- the canvas and destination—A3 or A4 print, 1:1 square, 9:16 story, 16:9 banner, or 2:3 / 3:4 standard poster;
- a text-safe zone preference—top band, center, or lower third—so the user can place the headline and details later without clashing with the image;
- ordered visual references when available (brand color reference, style inspiration, composition reference).
If the user has already stated the topic or style, reuse it. If that choice is genuinely missing, propose the best default and include it in the single paid-call confirmation.
Prepare the call
Use only this Skill's bundled scripts/mcp_client.py for every remote MCP
operation. The tool name is a CLI argument and the tool arguments are the JSON
sent on stdin. Do not configure or call a host Beatra Connector, and do not use
REST/OpenAPI as a fallback. For exact commands and troubleshooting, use
Bundled MCP Client diagnostics.
- For a topic-led concept, call
beatra.images.generatewith the canvas that matches the destination and a prompt that captures the desired mood, color palette, hierarchy, and text-safe zone. - Upload the source photo through the bundled client helpers first, then call
beatra.images.transformwith the uploaded artifact as the first ordered reference. Label the photo's role explicitly in the prompt so the model preserves the subject. - For an accepted draft, call
beatra.images.edit. Use at most two normalizededit_regionsonimage_index=0for localized fixes; omit regions for a whole-image adjustment.
Uploading makes bytes available to the remote tool; it does not itself inspect the image. Review only visual facts the host can actually see.
Keep model=auto and count=1 unless the user explicitly chooses otherwise.
Call beatra.models.list only for a real model, availability, compatibility,
or price decision. The detailed request shapes and examples are in
workflow.
Confirm and execute once
Planning and brief preparation are free. Before the paid image call, show and freeze the final prompt, ordered references, canvas, poster type, style direction, text-safe zone, model, controls, and output count. Merge any still-material high-impact choice into this one confirmation.
After approval, create one stable opaque client_request_id for that exact
logical request and submit it once. A changed prompt, reference or order,
canvas, poster type, style direction, model, count, or control is new paid work
and needs a new confirmation and a new ID.
Track, review, and deliver
After receiving a task_id, poll only that task with beatra.tasks.get. If the
ID is lost, use beatra.tasks.list to find candidates and verify the selected
one with tasks.get. Only when the original response status is genuinely
unknown may the exact same parameters and same client_request_id be used for
idempotent recovery. Slow polling, an update failure, an authorization failure,
or a connection failure never creates a replacement paid task.
Use beatra.tasks.cancel only when the user asks. If cancellation returns
409, continue tracking the original task. See review and
recovery for the full recovery contract.
When the result is visible, review visual impact (does the poster stop the
scroll and read clearly at a glance?), text readability (is there a clean
text-safe zone for the headline and details?), brand consistency (do colors and
mood match the category and brand direction?), canvas fit (is the ratio correct
for print or social?), and overall craft. Deliver the artifact links, observed
dimensions, task ID, and billing.net_charged_credits. Offer at most one
focused, unexecuted revision. Generated assets can also be viewed and managed at
beatra.ai.
References by task
- Choosing among topic generate, photo transform, and draft refine, or planning for a specific poster type: poster routing
- Turning a request into a poster specification—composition, hierarchy, category styling, color, text-safe zones, and canvas sizes: poster craft
- Exact request shapes, ordered-reference labeling, and JSON examples for each route: workflow
- Lost task, slow task, cancellation, result review, or planning a revision: review and recovery
- First install or expired authorization: installation and authentication
- Bundled MCP Client commands and diagnostics: Bundled MCP Client diagnostics
- Installation registration: installation registration
- Task lookup, polling, and result fields: tasks and results
- Balance, validation, and structured errors: billing, errors, and recovery
- Disconnecting the installation: uninstall and disconnect
- Official sources, integrity checks, and update controls: automatic updates and safety
Installation, updates, and account operations
For first use and shared operations, follow installation and authentication, installation registration, tasks and results, billing, errors, and recovery, and uninstall and disconnect.
This Skill performs a silent check at most once per 24 hours while a public
command runs. When a newer package exists, it installs automatically without
separate confirmation. Updates come only from the fixed official Beatra
discovery address and immutable Beatra CDN path for the embedded identity.
Before replacement, the client verifies the discovery document, manifest,
archive, and every packaged file using identity, size, and SHA-256 checks. It
replaces only package-owned files in this installed Skill directory. If any
check, download, replacement, or rollback fails, the current installation stays
usable and the original command continues. Canonical English installs stay on
canonical/en, and SkillHub Chinese installs stay on skillhub/zh-CN.
The user can persistently control automatic updates:
python3 scripts/mcp_client.py update --auto off
python3 scripts/mcp_client.py update --auto on
python3 scripts/mcp_client.py update --check
Read automatic updates and safety for the official sources, integrity guarantees, replacement scope, failure behavior, and control details.
Related skills
Generate Minimal Zine Poster — poetic paper-poster prompts and the matching generated image. Use when the user gives a theme, sentence, object, mood, article idea, photo, or content brief and wants a quiet Japanese/Korean zine-like editorial poster with large negative space, aged paper texture, expe
Say "Help me install this skill from https://clawhub.ai/shuminliu026/story-invite-poster" to your local agent, then create custom invitation posters from pho...
Create WeChat Moments posters and campaign graphics from a product photo, event brief, promotion, recruitment message, seasonal greeting, brand assets, or accepted draft. Produce square or vertical social visuals with a clear focal point and headline-safe space for WeChat Moments, customer-community updates, launches, invitations, and marketing campaigns; refine the selected image while preserving the brand direction.
Generate images where the copy has to be exactly right: posters, packaging, ads, social graphics, UI mockups, menus, signage, infographics. Use when the user...
AI Poster Image Generator Skills to Generate Multi-Page Image Carousels from Templates such as AI Poster Sota Models Nano Banana, Nano Banana-2 ,Imagen-2 and more are available