Install
openclaw skills install @beatra-ai/art-demo-setTurn user-supplied drawing steps into one still per art demo page. This classroom art still studio lays out each step-by-step art demo from the supplied demo points. Use it for art demonstration stills, drawing step pages, and an art demo set.
openclaw skills install @beatra-ai/art-demo-setMake one classroom demo still per named step from facts the user already supplied. Use this Skill when an art lesson needs a step-by-step demo page set, not a four-to-eight product gallery and not a fund prospectus page.
Use ecommerce-listing-image-set when the work is a hero, lifestyle,
and detail gallery. Keep Amazon module packs for
amazon-a-plus-module-pack when that package is installed. Use
fund-page-set when the work is one prospectus still per named page.
Do not look up public posts for missing demo steps. Do not grade or
score student work.
Hard inputs are the exact lesson or demo title and the user-supplied step or demo points that will appear on the stills. Do not invent a missing step, a sample grade, a rubric score, or a completed student drawing to finish a page. Reuse destination (handout, board, screen), language, and must-keeps already in the conversation.
Ask only for facts that change the pages:
A scan or photo is a visual reference, not a source for missing steps. Uploading makes media available to Beatra and does not inspect it. When the host cannot view a file, keep the user's declared role for it.
Default to one still per named step. Several steps are several stills, each with its own fact list. Omit a line whose fact is missing and keep that gap on the plan so the user can add it later.
Write a labeled page list before any paid image. For each step record the printed lines, language, layout (title, body points, optional footer), canvas, and any optional reference role. That list 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 step. A user who wants another
candidate adds a distinct step and approves that new work.
Use beatra.images.edit only after the user accepts a page and asks
for a local correction, with that accepted image as images[0].
Read art-demo 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 step. A changed
prompt, fact line, 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 step once. Keep no more than two generation tasks in flight on one connection.
Review printed lines against the confirmed page list. Report only the text the host can actually see. Treat generated small type as a review item, not as a graded sample.
Deliver the stills in step order, the page list, 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 user 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 classroom art demo page still for the named step. Print only the confirmed demo points.","model":"auto","count":1,"canvas":{"type":"preset","tier":"2K","aspect":"3:4"},"client_request_id":"opaque-art-demo-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.
This Skill runs only the files installed with it and leaves them unchanged while it runs; it never downloads or executes other code. It talks to Beatra's official services over HTTPS, and a file you choose to upload goes only to the one-time upload address Beatra issues for it.
Once a day at most, the bundled client reads Beatra's public version list. When the store or tool you installed from has a newer version, it prints one line with the command that updates it there. Updating stays your choice, through that store or tool. See updates and security.