Turn user-supplied assignment names and points into a four-to-eight still lab cover set. This lab report cover studio lays out each named assignment as its own still. Use it for assignment covers, experiment covers, lab report stills, and a matching cover pack.
Documents
RFP Cover Stills
Try itTurn seller-supplied tender facts into one RFP cover still per project. This tender cover studio lays out the seller-supplied project title and agency lines as a bidding-document cover and RFP cover graphic. Use it for tender document covers, bid-file covers, and RFP cover stills.
What it does
Turn seller-supplied tender facts into one RFP cover still per project. This tender cover studio lays out the seller-supplied project title and agency lines as a bidding-document cover and RFP cover graphic. Use it for tender document covers, bid-file covers, and RFP cover stills.
The skill document
RFP Cover Stills
Make one RFP cover still per project from facts the seller already wrote. Deliver 4 to 8 stills. Keep each still as its own file.
Scope and adjacent routes
Use this Skill when a seller wants short tender-cover listing stills from a written project note and named projects.
Route origin-story listing stills to origin-story-module. Route
nutrition-panel stills to nutrition-panel-art. Route Amazon
selling-point A+ stills to amazon-a-plus-module-pack. Route a full
listing gallery to ecommerce-listing-image-set. Do not look up
public posts for a missing agency name.
Collect confirmed facts
Hard inputs are:
- at least one named project;
- the tender facts the seller already wrote (project title, agency lines, and any deadline they supplied);
- how many stills the pack should contain, or permission to use the default of 4.
Reuse brand palette, destination, language, and must-keeps already in the conversation. Ask only for a missing hard input. A count outside 4 to 8 is still doable: confirm that pack size and its live cost.
Do not invent a tender number, agency, bid-opening date, official seal, or face. A letterhead photo is a visual reference, not a source for missing tender facts. File access is not consent.
Inspect every optional still. Record MIME type, width, height, aspect
ratio, byte size, and whether it has an alpha channel. For a local
file, upload only through the bundled client after inspection
(scripts/mcp_client.py / beatra.assets.upload). Keep the returned
artifact id. Never pass a local path to beatra.images.generate or
beatra.images.edit.
Plan the free card list
Write a labeled cover list before any paid image. Default four projects unless the seller names another count in 4 to 8. Each item records the project, the printed tender lines from the written note, language, layout, canvas, and any optional reference role.
That list is the free visible result. Planning is not approval.
Safe defaults:
- one
beatra.images.generatecall per project; model: "auto"andcount: 1;- canvas
{"type":"preset","tier":"2K","aspect":"1:1"}unless the seller named another destination; beatra.images.editonly after the seller accepts a card and asks for a local correction, with that accepted image asimages[0].
Confirm once, create by project
Planning is free. Before the first billable call, read
beatra.models.list for text_to_image:
{"capability": "text_to_image"}
Show one current production card and wait:
- Work — one RFP cover still per named project
(
beatra.images.generate). - Credits — the live
text_to_imageprice just read, times the project count. Do not reuse a remembered number. - Count — one paid call per project card. Do not batch several
projects into one
count. - Identity — one new opaque
client_request_idper card. - If we stop here — the labeled card list remains usable.
- If the balance is insufficient — relay the official message and
its top-up URL exactly
(
https://console.beatra.ai/wallet?intent=buy). Translate the prose; keep the URL. Do not retry until the seller says they have topped up. Do not recommend ¥198.
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 project once. Keep no more than two generation tasks in flight on one connection.
A later local correction is new paid work. Read the live image_edit
card first. Show a separate six-field edit card. Use a new
client_request_id.
Review, deliver, and recover
Review printed lines against the confirmed project note. Report only the text the host can actually see. Treat generated small type as a review item, not as a certified tender claim.
Deliver the stills in project order, the card list, observed
dimensions and formats, task IDs, resolved models, and returned
billing.net_charged_credits.
After a returned task_id, poll that task. If the create response is
lost, search with beatra.tasks.list and verify with beatra.tasks.get
before replay. Reuse an ID only with
byte-identical arguments. A changed project, tender line, canvas,
model, or prompt is a new card and a new ID. Cancel only when the
seller asks.
Execution
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 RFP cover still for the named project. Print only the confirmed tender lines.","model":"auto","count":1,"canvas":{"type":"preset","tier":"2K","aspect":"1:1"},"client_request_id":"opaque-procurement-project-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.
References by task
- For fact lists, payloads, confirmation, polling, recovery, and review, read RFP cover workflow.
- For authorization and the non-billable registration step, read installation and authentication and installation registration.
- For shared task, billing, and connection details, read tasks and results, billing, errors, and recovery, and Bundled MCP Client diagnostics.
- For update guarantees and controls, read automatic updates and safety. For removal, read uninstall and disconnect.
Runtime and safe automatic updates
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
Related skills
Turn user-supplied session names and themes into a four-to-eight still wealth cover set. This session cover set studio lays out each named investor education cover as its own still. Use it for session cover stills, education session covers, and a matching cover pack.
Use this skill when the user wants to analyze, design, optimize, recreate-in-spirit, or batch-produce thumbnails/covers for Bilibili, YouTube, Xiaohongshu, Douyin, WeChat Channels, public-account articles, courses, AI tools, knowledge IP, or product content. The skill produces strategy-first cover briefs, no-text image-generation prompts, platform-specific layout specs, portrait-consistent asset directions, A/B variants, technical QC, and iteration plans. It learns visual logic from references without copying protected designs.
Automatically convert tender documents (PDF/Word) into professional response bid documents following Chinese bidding standards. Use when the user needs to cr...
Turn an article title, topic, summary, or reference image into a WeChat Official Account cover, WeChat article cover, article hero image, post cover, headline image, or supporting article visual. This AI cover generator and article cover maker distills one clear visual hook, then creates either a rendered headline or a text-free headline-safe area. Use logos, portraits, products, and brand references to shape a brand cover image, and refine composition, focal point, color, thumbnail clarity, and crop resilience for a publish-ready WeChat cover design.
Create polished, editable SVG cover artwork for reports, articles, slide decks, social cards, ebook covers, posters, and landing-page hero images. Use when a...