Platform Desk / API
Get a token

Driving Platform Desk from code

Everything the web app does is available over HTTP. The base URL is https://api.skillsafe.ai/v1/app-api, every request carries Authorization: Bearer <token>, and every response is the same envelope.

The task field comes first

This app has five lanes behind one endpoint. Every run body must carry a task field naming the lane - it is what the system prompt routes on. Send the wrong one and you get a valid package of the wrong kind; omit it and the model picks the closest lane and tells you which it chose.

One more shape trap: the run body is the input object. Do not wrap it in an {"input": ...} envelope - that returns 200 while hiding task from the model, which is the most confusing way this API can fail.

taskLaneFieldsSections returned
planTurn a campaign brief into a delivery sheetbrief, knownSummary, The Sheet, The Numbers, Reasoning, Next Step
shipWhat one master actually delivers to this set, and what it cannotsheet, worrySummary, Verdict, Findings, Corrected Sheet, Next Step
frameCrops, chrome, and the shared safe area in master pixelssheetSummary, Every Platform's Crop, The Shared Safe Area, What Each Platform Costs, Next Step
weightDuration, file size and the bitrate nobody publishessheetSummary, Every Ceiling, The Binding Bitrate, Text At Delivered Width, Next Step
decideDecide what changes: the composition, the encode, or the target listsheet, fixedSummary, Recomposing Fixes, Only A Different Encode Fixes, Nothing Fixes While The List Stands, Next Step

Only task and the lane's own required fields are mandatory: sheet on ship, frame, weight and decide; brief on plan. Every field is a string - there are no number fields on this app. sheet is the delivery sheet itself: a header of KEY: value lines and a PLATFORMS: block.

MASTER is the line that matters most. It is the frame everything is measured from - every crop, every share and every text scale in the answer is relative to it, and they are all reported in MASTER pixels so the platforms are comparable. Getting it wrong makes every figure wrong in the same direction, so it is stated back on every answer; without it, 1080x1920 is assumed and the assumption is reported.

DURATION does more than it looks. It is checked against every platform's duration ceiling, and it is also the divisor that turns each platform's file-size cap into a bitrate cap - so a sheet with no duration has no trustworthy weight answer at all. 30s, 1500ms, 2min, 1:45 and a bare number read as seconds all parse.

SIZE and BITRATE describe the cut, so they are compared against the moving targets only - a still is a different file, and its own cap is reported rather than compared. 90MB, 4GB and a byte count parse for size; 12Mbps, 800kbps, 12M and a bits-per-second count parse for bitrate.

TEXT is the SMALLEST type in the master, in master pixels - not the size it ends up at on any platform. Text scales with the DELIVERED width (N × platformWidth ÷ cropWidth), so a crop that takes a narrow slice of the master makes type larger rather than smaller, and a thumbnail is judged at its mobile preview width rather than the width it is delivered at. Both numbers are in the answer, because only one of them decides anything.

The PLATFORMS block is one platform id per line: tiktok, reels, shorts, feed, linkedin, facebook, thumbnail. Every figure derived from them is a snapshot of published guidance on one day - platforms change their limits and their chrome without notice, so the answer states the date and the numbers are the ones to check rather than to trust.

Anything the reader cannot place is listed as a problem rather than skipped, and so is a platform named twice. A target that quietly vanished would make every intersection in the answer WIDER than it really is, which is the one direction of error that reads as good news.

A rectangle is reported as WxH at (x,y) in master pixels, a share as a percentage to one place, a duration in seconds, a file size in MB or GB, a bitrate in Mbps, and a type size in pixels with the width it is judged at. The engine works in rectangles, seconds and bytes: it has not decoded a frame, uploaded anything, or contacted a platform.

Add $model to any body to choose the model for that run: gpt-5.6-luna, gpt-5.6-terra (the default) or gpt-5.6-sol. Luna caps output at 4,096 tokens and will fail the ship, frame and weight lanes rather than shorten them - a findings table, a corrected sheet, or a row per platform with its crop and its ceilings, is several thousand characters before the reasoning starts.

The response envelope

Success and failure have the same outer shape, so one check covers both.

{
  "ok": true,
  "data": {
    "...": "the result"
  }
}
{
  "ok": false,
  "error": {
    "code": "VALIDATION_ERROR",
    "message": "seconds should be number, got string",
    "details": {}
  }
}
HTTPerror.codeWhat it means
400VALIDATION_ERRORThe body was not a JSON object, or a declared field had the wrong type. A number field sent as a string is the usual cause.
401UNAUTHORIZEDNo token, or a token that has expired or been revoked. Mint a new one.
402INSUFFICIENT_CREDITSThe balance is below the run's minimum. Call /estimate first and compare hold_credits against /me.
404NOT_FOUNDWrong path, or a job id that does not belong to this token.
409CONFLICTAn Idempotency-Key replay whose body differs from the original request.
429RATE_LIMITEDToo many requests. Back off; do not tight-loop.
503UPSTREAM_UNAVAILABLEThe model provider is unavailable. Retry with backoff.

1. Get a token

Open /tokens.html in a browser and copy the token this app already holds - no developer console needed. A guest token is minted automatically and is enough for /me and /estimate; writing a package is metered and needs a personal token, which comes from signing in on that page.

Keep it in an environment variable rather than in source:

export SKILLSAFE_TOKEN="YOUR_TOKEN"

2. Check the session and the balance

GET /me is free. It returns only three fields: subject_type, subject_id and credits. Signed-in means subject_type == "user" - there is no username or email to test.

curl -sS -X GET "https://api.skillsafe.ai/v1/app-api/me" \
  -H "Authorization: Bearer $SKILLSAFE_TOKEN"

3. Price the run before making it

POST /estimate costs nothing, creates no job, and returns the worst-case cost. Compare hold_credits against the balance from step 2 before you submit: a 402 after the fact is avoidable. hold_credits is a reservation priced at the full output cap - the actual charge is usually far lower.

It also echoes model, model_alias and markup_bps, which is the authoritative check that a run is bound to the model you think it is. Estimate each lane separately: their prompts and caps differ, so their holds do.

curl -sS -X POST "https://api.skillsafe.ai/v1/app-api/estimate" \
  -H "Authorization: Bearer $SKILLSAFE_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
  "task": "ship",
  "sheet": "<MASTER, DURATION, SIZE, BITRATE, TEXT and a PLATFORMS block; the grammar is in /llms.txt>",
  "worry": "it graded fine last time and this one will not come clean",
  "rules": "<the working rules for this lane, sent by the app>"
}'

4. Write a package

POST /run submits the job. Always send an Idempotency-Key: a network blip that replays the same request must not bill twice. A replay with the same key returns the stored result and is not charged again; a replay with the same key but a different body is a 409.

The response carries output.output (the Markdown package), charged_credits and truncated. If truncated is true the balance sat between min_credits and hold_credits and the output was cut short - render what arrived and say so rather than presenting it as complete.

curl -sS -X POST "https://api.skillsafe.ai/v1/app-api/run" \
  -H "Authorization: Bearer $SKILLSAFE_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
  "task": "ship",
  "sheet": "<MASTER, DURATION, SIZE, BITRATE, TEXT and a PLATFORMS block; the grammar is in /llms.txt>",
  "worry": "it graded fine last time and this one will not come clean",
  "rules": "<the working rules for this lane, sent by the app>"
}'

5. Stream a run

POST /run-stream is the same call with a text/event-stream response. Worth knowing before you build on it: from a server or from cURL you get event: delta frames carrying the output token by token; from a browser you get event: tick heartbeats and then one event: done with the whole output. Handle both, and treat ticks as liveness rather than progress.

Frame types are job (the job id), delta ({"text": "..."}), tick ({"t": seconds}), done, and error. An idempotent replay returns plain JSON with no stream at all, so check the content type before you start reading frames.

curl -sS -N -X POST "https://api.skillsafe.ai/v1/app-api/run-stream" \
  -H "Authorization: Bearer $SKILLSAFE_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Accept: text/event-stream" \
  -H "Idempotency-Key: cbd-$(date +%s)" \
  -d '{
  "task": "ship",
  "sheet": "<MASTER, DURATION, SIZE, BITRATE, TEXT and a PLATFORMS block; the grammar is in /llms.txt>",
  "worry": "it graded fine last time and this one will not come clean",
  "rules": "<the working rules for this lane, sent by the app>"
}'

6. Read the result

output.output is Markdown in the envelope this app's system prompt guarantees: every section is a level-two heading spelled exactly as listed in the lane table above, in that order; tables are GitHub pipe tables with the declared columns; prompts are in fenced blocks opened with three backticks and the word text; checklists are - [x] lines.

So parsing is a split on /^## / - but do it fence-aware, because a prompt block can legitimately contain a line starting with ##. Count the sections you got against the ones the lane declares: a short list means the run was truncated, not that the contract changed.

def sections(md):
    out, name, buf, fence = {}, None, [], False
    for line in md.split("\n"):
        if line.lstrip().startswith("```"):
            fence = not fence
        if not fence and line.startswith("## "):
            if name:
                out[name] = "\n".join(buf).strip()
            name, buf = line[3:].strip(), []
            continue
        if name:
            buf.append(line)
    if name:
        out[name] = "\n".join(buf).strip()
    return out

The artifact most callers want is the fenced text block inside ## The Sheet or ## Corrected Sheet - that is a complete sheet in the grammar above, so it can be fed straight back into another lane with nothing carried alongside it. Every other section is prose and tables meant to be read.

Rate limits and good manners