Generate and edit Draw.io, Mermaid, and Excalidraw diagrams from natural language using a structured JSON spec.
Coding
TikTok Creator Brief Stills
Try itTurn a TikTok creator homepage and recent posts into a collaboration brief still set. This TikTok creator brief studio reads the public profile and recent works, then lays out each already-written collab term as its own creator homepage brief card. Media buyers use it for TikTok creator briefs, collaboration brief stills, and a brief still pack they can hand off one file at a time.
What it does
Turn a TikTok creator homepage and recent posts into one collaboration brief still per chosen term. Deliver 4 to 8 stills.
The skill document
TikTok Creator Brief Stills
Turn a TikTok creator homepage and recent posts into one collaboration brief still per chosen term. Deliver 4 to 8 stills.
Scope and adjacent routes
Use this Skill when a media buyer already chose one TikTok creator and wants collaboration brief stills from that homepage and recent works, plus collab terms they already wrote.
Route a shortlist of who to approach to influencer-fit-analyzer.
Route an account diagnosis and first post to
creator-account-teardown. Route a talking clip out of this package.
This package reads one TikTok profile and one page of posts and makes brief stills. It does not post on TikTok. If this connection has no TikTok user or posts operation, work from pasted lines only.
Collect the creator and the terms
Hard inputs are:
- a public TikTok profile URL or
@handle, or the homepage facts and recent works already copied; - already-written collab terms the cards may print (product, deliverable, fee or barter, deadline, must-keeps);
- how many cards the pack should contain, or permission to use the default of 6.
Reuse already-known brand palette and destination. 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 handle, follower count, play count, or collab term. An optional brand still is a look reference, not a source for missing terms. File access is not consent.
Inspect every still the user supplies. 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, beatra.images.transform, or
beatra.images.edit.
Plan the free memo and still list
Write a labeled lookup memo and still list before any paid lookup or image. Default six slots unless the user names another count in 4 to 8. Each slot records the creator fact it uses (looked up or pasted), the printed collab term from operator-supplied copy, layout, canvas, and whether a brand still drives the look.
That list is the free visible result from whatever the user already pasted. Planning is not approval.
Safe defaults:
- one
beatra.images.generatecall per slot; model: "auto"unless the user chose a live SKU;count1 per slot;- square 2K unless the user named another destination ratio.
Look up the profile on its own card
A profile URL or handle does not authorize a lookup. When the user wants this connection to read the public TikTok homepage or recent works, follow creator lookup: search or inspect, then show a six-field lookup card and wait:
- Work — one public TikTok user search, profile read, or posts
page for the named creator (
beatra.social.executewith the inspectedoperation_key). - Credits — the live price
beatra.social.tools.getjust returned. Quote that live number, not a remembered one. - Count — one prepaid lookup. A user search is its own billed execute. The profile read is another. The posts page is another. The next page is another charge.
- Identity — one new opaque
client_request_idper execute. - If we stop here — the pasted-homepage plan 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 user says they have topped up. Do not recommend ¥198.
Do not show schema_hash to the user. A confirmed lookup does not
authorize image work. After a terminal lookup, report the payload,
task ID, terminal status, and billing.net_charged_credits. A
lookup has no model, dimensions, or duration to report.
Confirm generate, then optional transform or edit
Lookup and image work are separate paid stages. Each stage gets
its own six-field card and its own opaque client_request_id per
slot.
Before generate, call beatra.models.list for text_to_image:
{"capability": "text_to_image"}
Show the generate card and wait:
- Work — one collaboration brief still per named slot
(
beatra.images.generate). - Credits — the live
text_to_imageprice just read, times the slot count. Do not reuse a remembered number. - Count — one paid generate call per slot. Do not batch several
terms into one
count. - Identity — one new opaque
client_request_idper slot. - If we stop here — the labeled still 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 user says they have topped up. Do not recommend ¥198.
Submit each generate slot once through bundled
scripts/mcp_client.py. Poll beatra.tasks.get. Read actual image
MIME, dimensions, and size, and billing.net_charged_credits.
If the user wants the accepted cards to follow a brand still,
read the live image_to_image card and wait on a separate
transform card before beatra.images.transform:
{"capability": "image_to_image"}
Use beatra.images.edit only after the user accepts a card and
asks for a local correction, with that accepted image as
images[0]. Read the live image_edit card first:
{"capability": "image_edit"}
Approved generate does not authorize transform or edit.
Review, deliver, and recover
Review that each still prints the picked creator fact and only the
operator-supplied collab term. Report only the text the host can
actually see. Treat generated small type as a review item, not as a
certified offer. After each terminal paid task, deliver actual bytes
plus MIME, dimensions, and size when present, and
billing.net_charged_credits. Do not promise the prepaid estimate
is the final charge.
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 creator fact, collab term,
still, model, or canvas is a new card and a new ID. Cancel only
when the user 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"}
python3 scripts/mcp_client.py call beatra.models.list
{"capability": "image_to_image"}
python3 scripts/mcp_client.py call beatra.models.list
{"capability": "image_edit"}
printf '%s' '{"query":"creator","platform":"tiktok","capability_family":"creator"}' | python3 scripts/mcp_client.py call beatra.social.tools.search
printf '%s' '{"prompt":"Create the approved collaboration brief still for the named creator term. Print only the operator-supplied collab line.","model":"auto","count":1,"canvas":{"type":"preset","tier":"2K","aspect":"1:1"},"client_request_id":"opaque-tiktok-brief-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 still lists, lookup, payloads, and recovery, read brief still workflow and creator lookup.
- 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 lookup, generate, transform, or edit 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
Fetch raw ad creative, app, ranking, and revenue data from AdMapix as structured JSON.
Join a video meeting as an AI bot with voice, avatar, and screenshare across four operating modes.
Find why your productivity system keeps failing, then apply the smallest fix — capacity math, bottleneck routing, durable local notes.
Stores durable facts in a categorized, plain-markdown vault on disk, alongside your agent's built-in memory.
Site audit, content writing, and competitor analysis for organic search rankings.
More from beatra-ai
Browse all skillsTurn 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.
Turn a short video that already worked into your own version. Paste the link and this viral video teardown and short-video remake workflow reads the reference itself on TikTok, Douyin, Xiaohongshu, Instagram, YouTube, or X — caption, author, visible metrics, comments, and on YouTube the full transcript — or work from a file, screenshots, or your own description instead. It breaks the clip into its hook, body beats, and call to action, names the script pattern behind it, scores what carried the performance, then rewrites that structure around your product or topic — delivering a shot list with visuals and narration kept apart, reference frames from your own assets before any are generated, a narration track, and either an animated clip or segmented sources with a timecoded edit list. Use it to study a competitor's viral short, borrow a proven structure for Reels, Shorts, or WeChat Channels, rebuild a benchmark video under your own brand, or turn a saved reference into a content formula
Turn a comic panel, character sheet, webtoon frame, or frozen story beat into one dynamic comic-drama shot. This AI comic drama generator and motion comic maker animates an approved comic panel or manga frame into a short live shot, interpolates motion between a first and last comic panel, combines loose character, style, and scene references into a new comic-drama shot, or creates an original comic first frame and brings it to life. Use it for web-novel comic shots, motion comics, webtoon to video, manga panel animation, character entrances, emotional close-ups, action panels, dialogue reactions, and serialized creator workflows, with frozen character identity, approved art direction, and honest review of each independently generated shot.
Turn a novel chapter, web-novel excerpt, or story script into narrated vertical short video scenes with illustrated shots that keep every character looking the same from beat to beat. This AI story video maker pulls the hook and the beats out of your text, draws one shot for each, records the narration in a voice you choose, and sets each clip to its own narration, so a chapter arrives as an ordered set of scenes for story channels, book trailers, web-novel promotion, chapter recaps, and faceless storytelling accounts.
Turn written product answers and public note questions into one spoken wealth FAQ clip per question. This talking clip studio reads the questions buyers actually ask on public Xiaohongshu notes, records a speakable answer for each, and delivers separate short videos the advisor can post on their own.
Turn a user-supplied product factsheet and authorized stills into one wealth product talking clip per still. This product factsheet talking video studio writes a speakable product highlights talking clip for each photo, then animates a 2 to 15s product factsheet talking clip. Use it for wealth product talking pack and factsheet talking video pack work that stays one photo, one clip.