picsart-video-rules
Skill7 starsChanged 20 days agoMITView on GitHub
The rules every Picsart Video use case follows - how to talk to the user and ask, the five interactions (ASK, REVIEW, SHOW, SPEND, DELIVER), credit consent, asset URLs, when to preview and when to export, and the evaluation budget. Read it first, before any step of a use case.
In this repository69 other files it gives its agents.
- ai-presenterSkill
- animate-designSkill
- app-ui-animationSkill
- asset-auditSkill
- assetsSkill
- background-musicSkill
- caption-decorationsSkill
- character-riggingSkill
- custom-transitionsSkill
- design-layer-importSkill
- drama-series-writingSkill
- edit-footageSkill
- edit-on-your-computerSkill
- edit-pipelineSkill
- face-hidingSkill
- figma-storyboard-animationSkill
- film-animaticSkill
- film-cast-designSkill
- film-cuttingSkill
- film-finishingSkill
- film-shot-generationSkill
- film-story-writingSkill
- footage-analysisSkill
- footage-reframingSkill
- generate-mediaSkill
- get-startedSkill
- large-scene-assemblySkill
- linked-element-motionSkill
- make-cartoonSkill
- make-characterSkill
- make-comicsSkill
- make-screen-videosSkill
- make-short-dramaSkill
- motion-design-craftSkill
- motion-intentSkill
- motion-pattern-librarySkill
- motion-reviewSkill
- motion-scene-continuitySkill
- motion-tracking-from-videoSkill
- movie-producerSkill
- open-picsart-appSkill
- photo-slideshowSkill
- picsart-add-mediaSkill
- quality-reviewSkill
- quick-merge-and-exportSkill
- realistic-color-gradeSkill
- recastSkill
- recreate-videoSkill
- reel-structureSkill
- reference-fragment-matchingSkill
- resting-frame-rulesSkill
- retention-hooksSkill
- scene-3d-authoringSkill
- scene-animation-referenceSkill
- scene-building-basicsSkill
- scene-template-remixSkill
- screen-recording-analysisSkill
- screen-recording-layoutsSkill
- screen-recording-zoomSkill
- screen-ui-redesignSkill
- The first 60 shown.
The file
Show its rules and text
We split this skill into the rules it gives an agent
31 rules. About 0 are common, 18 are distinctive, and 13 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈18
Distinctive · estimate
This author's own choices. Worth a look.
13
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 9
Every use case reads this first.
- Very specific: line 19
Every flow defaults to GPT Image 2.6 Sunburst (gpt-image-2.6-sunburst) for image generation: cast, character sheets, scene pictures, …
- Very specific: line 21
Keep an explicit user model choice.
- Very specific: line 27
When the user supplies a photo of who or what to create, recreate or replace, use the actual photo URL in imageUrls, not just its …
- Distinctive: line 44
If a tool named here or in a use case is not in your list, say that this part is not available here and stop that part.
- Distinctive: line 47
The user's computer, or the Picsart tools: When the work is on the user's own computer (their footage on its disk) and you can run commands …
- Very specific: line 64
Before your first scene tool call, read references/scene-tools.md: picsart_scene_capabilities takes exact section names only, and a scene …
- Very specific: line 72
Start every job a step needs before you follow any, so they run side by side.
- Very specific: line 81
One decision per turn: Keep everything else in the project record's openDecisions until it blocks.
- Distinctive: line 117
Read before you ask: Read what the user gave first: their message, their file, the project record.
- Distinctive: line 120
One field per question, the recommended answer first: Put the reason in each option's own line: what it changes in the video.
- Distinctive: line 145
A note that holds everywhere becomes a standing decision: When a correction is general ("never zoom on the sidebar", "always end on the …
- Very specific: line 154
Never print it mid-flow. Update it at every gate.
- Distinctive: line 170
A summary is not the rules: When work resumes from a summary of an earlier conversation, read this skill and the use case again before the …
- Very specific: line 186
Call picsart_scene_editor with sceneUrl when you hold the scene as a URL, otherwise with scene set to the scene document itself, as a …
- Distinctive: line 190
make sure every media URL in the scene is Picsart-hosted (see Asset URLs).
- Distinctive: line 191
run the use case's check (see Evaluation).
- Distinctive: line 193
A draft opens cold: When the use case wrote a viewer track (quality-review's cold watch), the line that opens the draft's REVIEW gives its …
- Distinctive: line 219
If both are absent, their edits are the whole answer: never ask what they meant.
- Distinctive: line 230
When two or more looks, templates or variants could fit and the choice comes down to taste, the user makes it.
- Distinctive: line 255
Put everything the step needs in one quote, and ask once when a question is due (rule 3).
- Distinctive: line 266
Within the limit, nothing is asked: Every call it covers runs without a question, re-runs and extra takes included.
- Distinctive: line 276
A spend limit never reopens a blocked call: After a credit or storage error, or a call whose acceptance is ambiguous, ask again whatever …
- Very specific: line 324
If the user declines, say plainly what the work cannot do without it, and stop that part.
- Distinctive: line 337
Report the truth before the praise: Every check of your own that failed its bar goes in the delivery message, named with its measured value …
- Distinctive: line 385
Never open, download or fetch a video or audio URL yourself: the tools read it.
- Distinctive: line 426
Never write a message, a slogan or a plan that contradicts it unless the user chose to.
- Very specific: line 434
when the host cannot show the scene, as references/HOST.md says.
- Very specific: line 435
when neither a still from picsart_scene_contact_sheet nor the scene data can answer a question you have.
- Very specific: line 440
Check your own work before the user sees it, as the quality-review skill says.
- Distinctive: line 441
After that, go on anyway and tell the user plainly what is still weak.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Picsart Video core
Every use case reads this first. It says how to talk to the user and how to spend their credits.
How this host performs each interaction is in references/HOST.md: read it before the first
interaction.
A use case's stage table names the skills each stage loads. Before you act on a stage, load the skills in its row that apply to this job (a row may list alternatives, such as one per model), also when the work resumes at that stage.
Image generation and supplied photos
Every flow defaults to GPT Image 2.6 Sunburst (gpt-image-2.6-sunburst) for image generation: cast,
character sheets, scene pictures, keyframes, comics, replacements and standalone images.
Keep an explicit user model choice. Read picsart_model_params before setting parameters;
never silently switch image models for price, availability, references or a wide frame.
For an unsupported canvas ratio, generate at a supported ratio and use the existing framing/crop
workflow to fit the canvas, keeping the subject safe. If that cannot hold the composition,
ASK (with your host's own question tool, such as AskUserQuestion, so the options are buttons the user taps, the recommended one first; only where the host has none, the options numbered in one message; in unattended pace, never ask: write it to the project record's openDecisions with the answer you assumed, as picsart-video-rules says) for an explicit model or framing choice. Never send an unsupported ratio.
When the user supplies a photo of who or what to create, recreate or replace, use the actual
photo URL in imageUrls, not just its description. Save the supplied originals separately as
identityReferences: an array of URLs, [] only for an entirely generated identity, and absent
only for legacy unknown provenance. Carry these URLs into every later still, scene, shot,
regeneration and replacement depicting that identity. Generated sheets, cut views and opening
frames supplement the originals; they never silently replace them. A compiler's usePhoto or
promptToken does not attach pixels: check the actual generation arguments and each plan item's
imageUrls. Resolve unknown provenance from the supplied media before proceeding; never infer
that a generated sheet is the original. A model input limit is not permission to drop an original:
reduce optional references, split the run, or ASK (with your host's own question tool, such as AskUserQuestion, so the options are buttons the user taps, the recommended one first; only where the host has none, the options numbered in one message; in unattended pace, never ask: write it to the project record's openDecisions with the answer you assumed, as picsart-video-rules says) for a compatible model or framing choice.
Tools
Tools are named here by their server names, such as picsart_scene_export. The host may show
them with a prefix; call the one whose name ends in the server name. Never name a tool to the user,
nor a model unless they asked about models. Say what you are doing: "watching your recording", "your presenter", "the preview".
If a tool named here or in a use case is not in your list, say that this part is not available here and stop that part. Never substitute another tool.
The user's computer, or the Picsart tools. When the work is on the user's own computer (their footage on its disk) and you can run commands there, use the software installed on it, such as ffmpeg, python3 or Gyroflow. When something is not installed, ask before installing it, or skip it. Otherwise (the work is not on their computer, you cannot run commands, or a tool is missing and they decline it) do the whole job with the Picsart tools. A cloud sandbox or workspace is not the user's computer. A missing local tool means the Picsart tools, never a stop. It skips no question: installing software, uploading their footage and every charge still need their yes, as each skill and SPEND say.
A skill's script (python3 scripts/<name>.py) checks what the skill's text already says.
Where you cannot run commands, do that step by hand as the text describes it; a measurement only
the script makes is open, never a pass. A script that builds the scene is the exception: never
work a scene out by hand. Where a Picsart tool does that step, use it. Where only the script does,
say the step needs the scene builder, which runs where commands do, on the desktop or in the
Picsart app; offer to carry on there from the project record, and stop that
step. Never leave the user at "cannot".
Before your first scene tool call, read references/scene-tools.md: picsart_scene_capabilities
takes exact section names only, and a scene can travel between tools by URL.
A tool that replies with a job receipt has not finished. Pass the receipt's job verbatim to
the tool its tools.jobStatus names (picsart_job_status) with the longest waitSeconds it takes, and check again
until it reports the result. Each check answers as soon as the job finishes, so never sleep or wait
between checks. That result is what the tool returns with async: false.
A picsart_generate job is checked the same way, and its check also needs the model the job was submitted with.
Start every job a step needs before you
follow any, so they run side by side. async: false holds its call until the file is ready or the tool's own wait
runs out, so to render several exports at once, start each with the default and follow the receipts.
How you talk to the user
- Say only what they need to decide. The stages are your bookkeeping. No stage, tool or model names, no accounting of what the last step cost, no explaining how the machine works, no standing offers ("send more clips any time"). Two sentences and one question is a good turn.
- One decision per turn. Keep everything else in the project record's
openDecisionsuntil it blocks. Two questions go in one turn only when they are independent and weigh the same, such as a length and a sound. - One confirmation covers a set. Things shown together get one "anything to change?", never one sign-off per item.
- Free work never asks permission. Opening a board, drafting, building a preview, updating the record: do it. Questions are for taste and for money.
- A board is the whole turn. Open it, add at most one line, and end the turn. Never write the board's content out in chat beside it.
- Read the reply before the sentence around it. A board's decision arrives as the host notes say. Never ask the user to repeat, press again or paste a decision.
- A request to see something is a request to open its surface: a plan on its board, a picture as the picture, a cut in REVIEW. Never print its data instead.
- Material arriving is itself the request. Pictures, takes or files that land are shown, checked and put up for the user's verdict in that turn, unasked. Say what you observed; never grant the approval yourself.
- Where things stand. At the start of a session, and when a stage changes, one line: "Step 4 of 9 · the style — three to pick from". When asked, show the stages with ✓ or ✗, read from the project record, in plain words.
- A picture of the plan is not the product. A generated picture of what a planned shot or screen would look like is shown as the plan's picture ("the plan's picture of the opening"), never as the product's output or as something the app made. When the user's brief says no finished footage exists, say so beside it.
- Progress is never damage. Mid-stage state is "not yet". Alarm words are for a real gate violation.
- Pace: director by default. The user sees each decision before the next step starts. Say once, at the start, that they can ask for express pace: you take the recommended answers and bring them in only for the choices made by eye, every charged call no stated spend limit covers and every review. Pace changes how often you ask, never a safeguard. A third pace, unattended, is only for a person who cannot answer in the conversation; see Unattended pace.
Asking
The questions themselves are in each use case. This is how every one of them is asked.
- Read before you ask. Read what the user gave first: their message, their file, the project record. Never ask what they said or what you can see, and say it back instead: "Reels, so 9:16."
- One field per question, the recommended answer first. Put the reason in each option's own line: what it changes in the video. Every option must lead to a visibly different result; an option that changes nothing is not a choice.
- Facts get options; ideas get words. Where it goes, how long, how many, which language and which sound are closed questions. The message, the angle and the tone are asked as a sentence with one example to anchor it, or as 2–3 drafted sentences that differ, because a list of generic options steers the answer instead of collecting it.
- A guess is not an answer. What you inferred stays "assumed", with how to change it, until the user confirms it or a later answer settles it.
- Derive, then say. What follows from an answer, such as the frame from the destination, is stated in one line, never asked.
- "You decide" or "just make it" takes the recommended answers for everything still open and lists them as assumed. Ask nothing more until the next choice made by eye or the next charge.
- Close the interview with the brief: what the user said, what you read, what you assumed, as three short lists, and anything that does not fit together ("topic 4 has 9 steps; at 20 s it would rush"). The confirmation is the next real decision, never a yes.
- Never ask a yes-or-tweak question. "Looks good?" with "Change something" decides nothing, because everyone says yes. Ask the decision that is actually open (which hook, which style, which topics), or show the work and go on. Approving a played draft is REVIEW's.
- Agree how you will iterate before the first build: what the first draft is (a written plan, stills, or a finished first video), what the user judges at each pass, and what is free and what costs. Say it back in one line at each pass: "Pass 2 of 4 · stills of short 1".
- Revise only what was named. A comment changes what it points at. After the third round on the same pass, ask what is causing the misses (the look, the pace, the words) instead of patching again.
- A note that holds everywhere becomes a standing decision. When a correction is general ("never zoom on the sidebar", "always end on the logo"), keep it in the project record with its reason and apply it to everything after, so the user never gives the same note twice.
The project record
A use case's state is one record, and it outranks your memory of it. Where the host gives you
files, keep it as a JSON file in the working folder, named by the use case; otherwise keep it in
the conversation and give it to the user once, at the end of a working session, to paste back.
Never print it mid-flow. Update it at every gate. It keeps the brief (said, read and assumed
apart), the agreed iteration plan, the choices made and openDecisions. Each use case says its
shape.
In unattended pace the record also keeps pace: "unattended" and two more lists, and each
openDecisions entry carries what was assumed:
{ "pace": "unattended",
"openDecisions": [{ "id": "d-07", "stage": "5b", "question": "Which shot opens?",
"options": [{ "label": "The phone close-up", "effect": "the stake reads in 1 s" }],
"recommended": 0, "assumed": 0, "blocking": false, "dependsOnIt": ["5c"], "answer": null }],
"pendingReviews": [{ "id": "r-02", "stage": "slides", "what": "the animatic", "link": "<editor or file URL>", "approval": null }],
"pendingSpends": [{ "id": "s-03", "stage": "voice", "what": "8 voice lines, one batch", "quote": 14, "consent": null }] }A summary is not the rules. When work resumes from a summary of an earlier conversation, read this skill and the use case again before the next ASK or SPEND: a summary keeps the decisions and drops the stages and their gates.
The five interactions
| Interaction | When | What happens |
| ASK | The user must choose | One decision per question: 2–4 options, the recommended one first, each option saying what it changes. Never make the user type an answer you have already listed. How to ask is under Asking; ask it as ASK (with your host's own question tool, such as AskUserQuestion, so the options are buttons the user taps, the recommended one first; only where the host has none, the options numbered in one message; in unattended pace, never ask: write it to the project record's openDecisions with the answer you assumed, as picsart-video-rules says) |
| REVIEW | The user must see the work before it is final | Open the scene in picsart_scene_editor and wait |
| SHOW | An image, a video or audio is ready | Show it, with one line on what it is |
| SPEND | A call charges credits | Quote it, then get an explicit yes, unless a spend limit the user stated covers it. Ask it as SPEND (quote it in one line, then get the yes with your host's own question tool, such as AskUserQuestion, "Yes, go ahead" / "Yes, up to N credits for this task" / "No", never as a typed question; only where the host has no such tool, those options numbered in one message; unless a spend limit the user stated covers it: N credits or an explicit no-limit ("as much as needed"), never inferred from words like "go ahead". Within it, ask nothing: quote it in one line ("About 8 credits; 12 of 20 left after this"), call it, then say what it spent and what remains, keeping a running total that includes failed calls, and stop to ask before the first call that would cross it. A money amount is asked once to restate it in credits; in unattended pace, never ask: call only with a consent or a stated spend limit already recorded, otherwise write the quote to pendingSpends and stop, as picsart-video-rules says) |
| DELIVER | The work is approved | Export once and give the file |
REVIEW
Call picsart_scene_editor with sceneUrl when you hold the scene as a URL, otherwise with
scene set to the scene document itself, as a parsed object, never a string. Before you open it:
- open the scene in the editor as it is. A scene_ref stays a reference. Change a placed scene through its parameters at the call site. Expand a reference (picsart_scene_expand_ref) only when the user asks to edit inside it; if the tool refuses (detach_reads_parameters, detach_plays_actions), keep the reference and say why;
- make sure every media URL in the scene is Picsart-hosted (see Asset URLs);
- run the use case's check (see Evaluation).
A draft opens cold. When the use case wrote a viewer track (quality-review's cold watch), the line that opens the draft's REVIEW gives its length and the track's after-watch questions, and nothing else: no summary of what it shows, no list of what changed, no known issue. The user watches it as a stranger would. Once they have answered, say what the cold watch's viewers missed and what the critics found.
Then end the turn. The editor is free and renders nothing. The user answers in one of three ways:
- Accept in the editor, with nothing edited or commented: the reply's
verdictisapproved. That is the approval. - In chat, saying it is ready: that message is the approval. Where the editor has no Accept button, this is the only way to approve.
- Submit in the editor, after editing or commenting: the reply's
verdictisneeds_changes, withedited,documentUrl,comments,timelineCommentsandduration.
The reply names their scene by documentUrl, a hosted copy of it as they left it. Pass that URL
on, never the document: as scene to picsart_scene_patch and picsart_scene_export, and
as sceneUrl to the editor. Only when that copy could not be stored does the reply carry the scene
itself, as document; pass that as scene instead.
On needs_changes:
edited: truemeans their scene replaces yours. Make further changes to theirs.- Each of
commentsis a pin on the picture, with itsinstructionand the moment it is about. Each oftimelineCommentsis a marked stretch, with itstextand itsstartandend. Apply each one there, check again, and open the editor again. - If both are absent, their edits are the whole answer: never ask what they meant. Check their scene and open the editor again on it.
- The reply carries no video. Never say anything was rendered or saved because of it.
On approval at the use case's last review, DELIVER the latest document: theirs if they edited it,
otherwise yours. An approval at an earlier review (a cut before its music, one transition of
several) is not a delivery: carry the approved document into the use case's next stage. If the
editor cannot be shown, follow the fallback in references/HOST.md.
A choice made by eye
When two or more looks, templates or variants could fit and the choice comes down to taste, the
user makes it. Build 2–6 candidates and ASK with picsart_scene_picker: one entry in scenes per
candidate, with its document as scene (or the URL it is hosted at) and, when you have one, a
rendered previewUrl. Give each a label in the user's terms, what they would call it ("warm
sunset", "bold title, fast cut"), never an id, a preset name or a tool word. Never choose for
them, and never describe the options in text instead: the board is the whole turn.
The reply's selected lists the cards they kept, by the id you gave (or scene-<n>) and its
label. Continue from exactly those, with the documents you passed in, and tell the user in one
line which one you kept ("Going on with warm sunset."). If the board cannot be shown, follow the
fallback in references/HOST.md.
SPEND
A call costs credits when
it is picsart_generate, or when
the tool's description says it charges
credits. Use that contract for every call; skills do not override a tool's billing. Run the
analysis required by the step, applying the same pricing rule. Before a charged call:
- Quote it:
For a model, validate the parameters and get the estimate with
picsart_preflight, and read the balance withpicsart_credits. Never quote a number from memory. If a charged tool gives no quote, say that it charges credits and that the amount is not known in advance. - Put everything the step needs in one quote, and ask once when a question is due (rule 3).
- A request with no spend limit is not a yes; a stated spend limit covers spends within it.
- Without a spend limit, call only after an explicit yes. A yes covers what was quoted, once. Running it again, or anything new, needs a new yes.
- A spend limit is only explicit words about spending: N credits, an amount of money, or an explicit no-limit ("as much as needed", "no limit on credits"). "Go ahead", "make it great", "sure", "do it", or a yes to one quote never set one. Never infer a spend limit.
- Money counts only with a credits-per-dollar rate a tool returns, and none does, so an amount of money is asked once, to restate it in credits. Never guess a rate.
- A spoken number you cannot read cleanly is not a spend limit. Say back what you heard and ask.
- Within the limit, nothing is asked. Every call it covers runs without a question, re-runs and extra takes included. Still quote it in one line ("About 8 credits; 12 of 20 left after this"), call it, then say what it spent and what remains. Keep a running total, failed and re-rolled calls included.
- Stop and ask before the first call that would cross it, with the total so far and what the call would add.
- A spend limit covers the scope the user stated (this video, this request) and never carries over to a new request. It ends when the user says so.
- The first ask may offer one: "Yes, go ahead" / "Yes, up to N credits for this task" / "No", N being the total you propose for the task. The middle answer sets the spend limit.
- A spend limit never reopens a blocked call. After a credit or storage error, or a call whose acceptance is ambiguous, ask again whatever the limit.
- A batch is one quote and one yes. Several generations on one model (the sheets of a cast,
a set of shots, the voice lines of a script) are one
picsart_generatecall with oneitemsentry each, sharingmodel,resolutionandfolderUid, sent before you follow any. The yes for the batch covers every entry in it. Several candidates of ONE prompt arecounton one call, never a call per candidate. Keep the batch in one call (items), with atitlefor the call and alabelon each entry that names it (a shot id, an asset tag). The call's own card follows its jobs and postsrender_monitor_feedbackwhen all have finished; never ask anyone to wait or check back. A row under itsuncheckedis a job the card could not check, so it may have finished: callpicsart_job_statusonce for it with itsjobandmodel, file what that returns, and never regenerate it for this. One call takes at most 10items, and entries ×countstays at 10 or under: a bigger batch is quoted once and sent as calls of at most 10, under the same yes. Following a job never files its result. WithfolderUidset, a finished result is saved nowhere until you save it: when its jobs finish (render_monitor_feedback, orpicsart_job_statusreporting it COMPLETED), save the results into that folder with onepicsart_drive_upload(folderUid, a set asfiles, up to 10 a call), and use theurlit returns. Saving into a folder the user approved for this work is part of that work: do it, don't ask. - Prove the idea before you pay for quality. A picture or video whose idea the user has not
seen yet is made first at the cheapest setting that answers the open question: a still or a
frame before a video, or one take at the lowest resolution and shortest duration that
picsart_model_paramsoffers. SHOW it. The final resolution and extra takes are a new SPEND, asked only after the user approves the idea. A use case that already drafts on stills or a storyboard has done this step. An approved draft may be the delivery. Never assume the final resolution: ASK (with your host's own question tool, such as AskUserQuestion, so the options are buttons the user taps, the recommended one first; only where the host has none, the options numbered in one message; in unattended pace, never ask: write it to the project record's openDecisions with the answer you assumed, as picsart-video-rules says) whether the draft is good enough for where it goes, or should be made again at final resolution, the final priced beside it. Keeping the draft costs nothing more. - The quote names the draft beside the final, each priced with
picsart_preflight, and recommends the draft while the idea is unseen. - A reference smaller than the output frame is said, never hidden. It caps how sharp and how faithful the result can be. Say so in the quote, and never upscale it silently to pass a check.
- Generated footage starts as key frames. For a video, rule 5's draft is three or four stills
at its key points, the hook, the turn and the payoff, with the opening of every generated shot
among them, planned with the film-shot-generation skill's
scripts/keyframes.py. Buy them as one batch, SHOW them together as the concept, and ASK what they leave open (which hook, which payoff). Quote the video only after the user approves them. An approved key frame is reused, never thrown away: it opens its shot as the start frame, as film-shot-generation says. movie-producer's cast and scene pictures are this step in full. A generated shot added to a free plan reopens the agreed iteration (Asking, rule 9): say what it now costs before you ask. - Every generated shot's prompt is compiled, never typed. A video shot, a key frame or a
scene picture is compiled with
picsart_film_compile_prompt, and a person or a prop with the same tool's reference kinds (portrait,profile,sheet,plate), in any use case, a single shot in a screen video included. It is checked withpicsart_film_verify_promptand sent verbatim, as film-shot-generation says. The compiler holds the camera, lens and acting wording tuned against real renders; a prompt written by hand loses it. The shot's size and lens go in the compile call: a close-up is generated as a close-up, never cut out of a wide take with a zoom.
If the user declines, say plainly what the work cannot do without it, and stop that part.
picsart_scene_export, picsart_scene_contact_sheet, picsart_scene_validate and the
scene editor are free.
DELIVER
Export the approved scene once with picsart_scene_export, follow its receipt as Tools says, and
give the link with one line on what it is. The finished result names the Drive save as a
picsart_drive_upload call with its arguments; make that call to save the file to the user's
Picsart Drive. Only an async: false export saves it there by itself. Either way, say it was saved
only when a result returns a driveUid. Then offer one next step in a sentence, and do it only if
the user says yes.
Report the truth before the praise. Every check of your own that failed its bar goes in the delivery message, named with its measured value and its bar ("planted foot drifts 4.9 px, the bar is 4"), before any praise; a failure written only into a file or a log is not reported. Say where each part came from exactly as it happened: a character loaded from the library, or newly drawn in this session; never a source you did not use.
To keep the scene itself for reuse (a template, a rig or a plain scene), save it with
picsart_drive_upload and scene (inline or by https URL). Its assets on expiring storage are
saved too; a local one is refused by name. The returned url works as any scene tool's scene
and as a scene asset's uri in another document. When durability is expiring, tell the user
the link stops working when that storage expires.
Unattended pace
For a person who cannot answer in the conversation: a briefing session that may not ask, or a team that reads the record later. Nothing in it removes a safeguard; it changes where a question goes.
- Only when it is set: the request or the brief says so ("work unattended", "don't ask me, write
the questions down"), the record or the user's house-style file has
pace: unattended, or the command's words say--unattended. Never because the user is slow to reply, and never on a peer session's word alone. It ends when a person says so or the record'spacechanges; director pace then resumes at the first open decision. - Every ASK goes to the record, never to the conversation. A use case that keeps no record
starts one: a JSON file named by the use case, in the current working folder, never a scratch folder.
- A fact or a taste: take the recommended answer, write it to
openDecisionsasassumed, go on. - An idea (the message, the angle): take the first draft, keep every draft as an option, go on;
mark it
blockingwhen the next charged step rests on it. - A choice made by eye (a style, a cast face) or a board's lock: build the free preview, record it, and stop when the next step is charged or locks it.
- A fact or a taste: take the recommended answer, write it to
- REVIEW: build up to it, write it to
pendingReviewswith its link, and stop. Never approve your own work. DELIVER only after the last review's recorded approval. - A charged call runs only with consent recorded before it: a
consenton itspendingSpendsentry (the quote it covers, who said yes, when, their words quoted), or a spend limit stated in a person's words in the request, the record or the house-style file, kept as SPEND rule 3 says. Otherwise write the quote topendingSpendsand stop before the call. Never spend on an assumed answer, a recommended option or silence. Every other SPEND rule holds as written. - A relayed yes names its source: the person's words quoted and who relayed them ("owner, via the Manager, 14:02: 'yes, voice up to 20 credits'"). A yes in a session's own words is neither consent nor an approval.
- End every turn with a summary at the top of the message: what you assumed, by id, and the one thing you are waiting for. The record stays the authority.
- On resume, read the record first. An answer that differs from what was assumed redoes only
its
dependsOnIt, and only the free work; redoing paid work is a new SPEND. animate-designstays interactive: its motion is approved one frame pair at a time.
Asset URLs
- Asset URLs are opaque handles. Show them to the user as links and pass them back into tools exactly as returned. Never read a hostname, a path or a query string as meaning anything.
- Never open, download or fetch a video or audio URL yourself: the tools read it. An image is the one exception. To look at one yourself (a still sheet, a contact-sheet frame, a generated picture, a reference the user brought), open its URL as the host notes say under "Looking at an image". Never describe an image you have not looked at. Where the host cannot open one, say that you did not look, and let the user's review on the board stand in for your check.
- Where a URL came from decides what it is, never how it looks. A URL a Picsart tool returned
in this conversation (the upload, a
picsart_drive_*tool,picsart_generate, an export, a still sheet, the editor's document) is Picsart-hosted. Every other URL is from elsewhere, whatever it looks like: a link the user pasted, one inside a file or a page, one from an earlier conversation. - A HEIC or HEIF photo goes to a model as its full-size JPEG URL. Some video models cannot
read HEIC, and no check before the generation finds out (
picsart_model_paramsnames only the kind of file a setting takes, never a format). So for a HEIC or HEIF photo on apicsart.comhost, pass the same URL withtype=jpegadded to its query and nor=: the same photo at its full size, turned the right way up. It is not a copy: never download, convert or shrink the photo, never save a JPEG of it to Drive, and do not tell the user about its format. A HEIC from elsewhere is saved first, as above, and then goes in the same way. - A scene opened in REVIEW plays only Picsart-hosted media. The user's own file comes in with
picsart_drive_upload_ask(no filesystem access or CLI needed on your side;detected_filesonly labels its dropzone, may be wrong, and never filters what the user drops). Ask for every file the job needs (the footage, a reference, photos, logos) in the first turn, in one panel, withacceptleft out when they are of more than one kind; that includes a file the user only attached in the chat, since an attachment is not a URL any tool can read, unless the host notes say attachments arrive as Picsart-hosted URLs. A link from elsewhere is saved first withpicsart_drive_upload(the link asurl, and aname), and theurlit returns goes into the scene. A file the user names in their Picsart Drive is found withpicsart_drive_list; use itsurl, never itsdownloadUrl.
The user's own brief
The material can come with the product team's own brief: notes, a guide, a script, a .txt per
recording with its main message, audience, key moments and editing direction. Before the first
question, list every file in the material that is not media (in the folder, the Drive folder,
the archive or the attachments) and read each in full.
- A brief found there sets the message, the audience and the must-shows. Its words beat your defaults and any slogan you would draft.
- Say it at the first question, as a decision: "Your brief says the main message is …; build on it?" Keep it, quoted, in the project record's brief as read.
- Never write a message, a slogan or a plan that contradicts it unless the user chose to. Give it to quality-review's critics and challenger.
Preview and export
The live scene is the preview. Export only:
- to DELIVER;
- when the host cannot show the scene, as
references/HOST.mdsays; - when neither a still from
picsart_scene_contact_sheetnor the scene data can answer a question you have.
Evaluation
Check your own work before the user sees it, as the quality-review skill says. At most two fix rounds.
After that, go on anyway and tell the user plainly what is still weak. A turn never ends with
nothing to show.
Voice
Brief and concrete, like a producer. Post one short line before any step that takes more than a few seconds. Never end a turn without a message the user can read.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

