Analyse an existing Movie on the canvas — sample frames from each picture clip, describe what is happening, and write clip autocaptions into the film JSON (Desc lane). Load when the user asks to analyze a film/movie, caption the timeline, fill Desc, describe each shot, or prepare a cut for generative "fill the gap"…
Act on review state on canvas media — coloured labels ("tags"), free-form tags and comments. Load when the user says tagged / labelled / marked orange / approved / rejected / needs work, or asks to address comments or redo everything with a given label (findassetsbyreview).
Structural layout changes on the canvas — sort / group images with classifyassets (anything visible: clothing, logo, mood) or groupbyfacet (orientation / type / model), move nodes between sections, tidy / align / distribute. Load when the user asks to sort, group, reorganize, tidy, or clean up the board. Never loop…
Brand films, opening scenes, storyboards, or shot sequences on the canvas — especially with a named real person. Load to sequence reference sourcing, scene planning, section reservation, and generate / animate.
Movies in chat — cut rendered shots into one playable, editable video with titles, transitions and sound (createfilm / editfilm / readfilm / screenshotfilm). Load when the user wants a video that plays as one piece — a movie, trailer, promo, reel, montage, explainer, launch video, or several clips cut together.
Reverse-engineer and rebuild a real web page as a pixel-perfect Design on the canvas. Load when the user wants to clone, replicate, rebuild, reverse-engineer, or copy a website ("make a copy of this site", "rebuild this page", "pixel-perfect clone"). Requires a public http(s) URL. Uses inspectpage (headless-browser…
Designs — sandboxed HTML/CSS/JSX nodes (hero pages, slide decks, dashboards, mockups, mini-websites, video overlays) authored by the design sub-agent via delegatetodesignagent. Load when the user wants a design, website, landing page, deck, dashboard, mockup or screenplay, or refers to an existing Design on the board.
Generate the missing shots in an existing Movie and put them into the cut. Load when the user asks to fill a gap, bridge two shots, add a beat between clips, smooth an abrupt cut, or "generate whatever is missing" in a timeline. Covers the single-gap call, finding the gaps worth filling, and doing several in one pass.…
Turn a brief into a finished Movie on the canvas — shot list, generated shots, native title cards (composeframe), timeline assembly with createfilm / editfilm, basic fade/keyframe motion, and a screenshotfilm QA pass. Escalate to HTML motion scenes only for complex graphic beats. Load when the user wants a video…
Per-model prompt guides. On video turns the settled model's motion guide is already inlined under LOADED GUIDANCE; load one via filepath (references/seedance-2-prompting.md, references/kling-3-prompting.md, or references/models/ .md — not bare readskill) when it isn't, or before generateimage / editimage /…
Short launch / promo / teaser video (15–25s) showing off a product, site, app, feature or the user's own work — hook, reveal, highlights, punchline, beat-synced music, cover frame, share caption. Load for "launch video", "promo", "hype reel", "product video", or showing off what they built. Builds a Movie with…
Producing more than one image in a turn — variations, mood boards, NxM grids, storyboard panels, batches. Load to compute N correctly, reserve a section, and fan out one media call per cell.
Author a MOTION SCENE (a Motion) — a Design played frame by frame on the Motion stage or inside a Movie (logo builds, kinetic type, lower-thirds, data animations, transitions, end cards). Load before writing files for any brief marked MOTION SCENE, or when the user asks for animated graphics, titles, or a code-driven…
Motions — frame-driven motion graphics (kinetic type, logo reveals, titles, lower thirds, data and chart animations, animated end cards) built as a Design with a motion.json, previewed on the Motion stage, rendered to the user's Assets with rendermotion, and usable as a clip in a Movie. Load when the user wants…
Movies on the canvas — frame-exact multi-track timelines (createfilm / clonefilm / readfilm / editfilm / fillfilmgap / screenshotfilm). Load when the user wants something that plays as one piece — a video, film, spot, trailer, reel, montage, or titles and music over shots.
Compose editable slides, posters, and layouts as NATIVE canvas nodes (layout Frame + text/shape/media children) via composeframe. Load when the user wants a layout they can edit directly on the canvas with the toolbar, or a native multi-slide deck.
Fills and effects on canvas nodes via paintnode — drop shadow, glow, blur, inner shadow on any node; solid / gradient / image backgrounds on Sections and Frames. Load when the user asks for a shadow, glow, blur, gradient, background colour, or a frosted / glassy / neon look.
Run 2+ independent deliverables concurrently with spawnworker (media, design and research workers) — partition the board first, spawn in one step, check each worker's outcome. Load when the user asks for several concepts, variants or options at once, or for unrelated deliverables in one request.
Presentation or slide deck from the user's own LetzAI images — most liked, best work, portfolio review. Load before readusercreations and delegatetodesignagent.
Grounded sites, landing pages, product pages, portfolios, pitch decks, branded mockups about a real external subject (person, product, brand, company, app, event). Load before delegatetodesignagent / createdesign / generatecode when real-world accuracy matters and the user did not supply full copy — research the…
Write a film/TV screenplay (spec script) as an editable, paginated HTML Design — from a fresh idea or grounded in what's already on the board (a storyboard scene list, native frames/shots, or selected text/treatment notes). Load when the user wants to "write a screenplay", "write a script", "spec script", "turn my…
Which search tool for which intent — webfetch for a linked URL / PDF, imagesearch for reference pictures, websearch for text facts, getmodels for @handles. Load when the user asks to search, google, look something up, find images or reference photos, or pastes a link.
The user wants to save a rule, preference, tone, or repeatable workflow as one of their own Skills — or wants you to change an existing Skill of theirs. Load before the first requestskillwriteapproval call in a conversation. Triggers: "save this as a skill", "remember this rule", "always reply like X from now on"…
Turn an existing Section of native layout Frames (a slide deck on the canvas) into ONE faithful, publishable multi-slide HTML presentation — using every slide, in the exact order the user laid out. Load when the user wants to "make a deck/presentation from these frames", "publish these slides as HTML", "create an…
★not rated 2 2d agoA87 tokens
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: