Install
openclaw skills install @beatra-ai/amazon-a-plus-module-packTurn seller-supplied selling points into one Amazon A+ module still per point. This A+ page still studio lays out each seller-supplied benefit as an Amazon A+ Content module for the A+ page. Use it for Amazon A+ modules, selling-point modules, and a brand-story A+ graphic.
openclaw skills install @beatra-ai/amazon-a-plus-module-packTurn seller-supplied selling points into one A+ module still per point. Use this Skill when a listing needs Amazon A+ Content stills that follow the seller's own benefits, not a six-slot hero gallery.
Use ecommerce-listing-image-set when the seller wants a hero, lifestyle,
and detail gallery. Use ecommerce-detail-module-studio when the work
starts from product photos and needs a scrollable photo-transform story.
Keep Amazon main-image rule work on amazon-main-image-set or
marketplace-main-image-preflight when those packages are installed.
Do not look up public posts or marketplace catalogs for missing benefits.
Hard inputs are the exact SKU name and the seller-supplied selling points that will appear on the modules. Do not invent a benefit, comparison number, certification, or award to finish a slot. Reuse brand palette, marketplace, language, and must-keeps already in the conversation.
Ask only for facts that change a module:
A photo is a visual reference, not a source for missing benefits. Uploading makes media available to Beatra and does not inspect it. When the host cannot view a file, keep the seller's declared role for it.
Default to one still per named selling point. If the seller wants a standard A+ set and has not numbered the slots, plan up to four modules from the facts already given: promise, feature, use, and comparison. Leave a slot whose fact is missing on the plan. A single-module request stays one still.
Keep the same product look, palette, and lighting across the set so the modules read as one A+ page.
Write a labeled module plan before any paid image. For each slot record the selling point, language, visual role, canvas, and any optional reference role. That plan is the free visible result. Planning is not approval.
Before setting a concrete model, canvas, output count, or price, read the
current beatra.models.list card for text_to_image. Keep model as
auto and count at 1 per module. A seller who wants another
candidate adds a distinct slot and approves that new work.
Use beatra.images.edit only after the seller accepts a still and asks
for a local correction, with that accepted image as images[0].
Read A+ module workflow when writing the payload or recovering a task.
Planning is free. Before the first billable call, show one current production card and wait:
beatra.images.generate).text_to_image price just read. Do not reuse a
remembered number.count.client_request_id per module. A changed
prompt, selling point, file, model, or canvas mints a new ID.Submit once through bundled scripts/mcp_client.py. Poll
beatra.tasks.get. Deliver actual bytes plus
billing.net_charged_credits. Do not promise the prepaid estimate is
the final charge.
After approval, submit each module once. Keep no more than two generation tasks in flight on one connection.
Review printed claims against the confirmed selling-point list. Report only the text the host can actually see. Treat generated small type as a review item, not as certified A+ copy.
Deliver the stills in module order, the module plan, observed dimensions
and formats, task IDs, resolved models, and returned
billing.net_charged_credits. A focused correction is new paid work
with its own card and ID.
After a returned task_id, poll that task. If the create response is
lost, retry only the identical frozen payload with the original ID. If
the task ID is missing, use beatra.tasks.list and verify candidates
with beatra.tasks.get before another submit. Use beatra.tasks.cancel
only when the seller asks.
Invoke every remote Beatra operation only through this package's bundled
scripts/mcp_client.py. Put the MCP tool name after call and send one
JSON object on standard input.
python3 scripts/mcp_client.py call beatra.models.list
{"capability": "text_to_image"}
printf '%s' '{"prompt":"Create the approved Amazon A+ module still for the named selling point. Show only the confirmed benefit. Keep the shared A+ page look.","model":"auto","count":1,"canvas":{"type":"preset","tier":"2K","aspect":"16:9"},"client_request_id":"opaque-aplus-module-01"}' | python3 scripts/mcp_client.py call beatra.images.generate
Do not configure or call a host Beatra Connector, and do not use REST/OpenAPI as a fallback.
When the user asks how many credits remain or whether a live estimate fits,
call beatra.wallet.get. When they ask what was charged, call
beatra.wallet.ledger. Both are read-only. Do not invent an account-balance or
top-up tool. Do not make wallet.get a required step before every paid submit.
When a model card comes back carrying a top_up block, relay its tiers as the
card lists them and in that order. Do not rank them, do not talk one down, and
do not pick one for the user. Which tier suits them is their call, made on
the wallet page with the whole list in front of them. Never quote a tier from
memory.
The bundled client silently checks for a newer release at most once every 24 hours per installation. When a newer version is available, it installs automatically without separate confirmation. It downloads only from the fixed official Beatra discovery and immutable CDN paths for this package, channel, and locale, verifies discovery data, archive, manifest, and every packaged file, and replaces only package-owned files.
Update checks, downloads, verification, replacement, rollback, and recovery fail open: the current installation remains usable and the original command continues. An update failure never authorizes retrying a paid image request. The setting persists for this installation. See automatic updates and safety.
python3 scripts/mcp_client.py update --auto off
python3 scripts/mcp_client.py update --auto on
python3 scripts/mcp_client.py update --check