Refs Desk / API
Get a token

Driving Refs 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
briefTurn a shot into a requestshot, have, targetSummary, Sheet, Channels, Reasoning, Next Step
checkWhich input actually decides whatsheet, prioritySummary, Verdict, Findings, Resolved Sheet, Next Step
assignGive every attribute one ownersheet, keepSummary, Assigned Sheet, Who Owns What, What To Drop, Next Step
textWrite a prompt that is not decorationsheet, voiceSummary, Prompt, What The Text Can Decide, What It Cannot, Next Step
modePick the mode from what you havehave, mustSummary, Mode, What It Needs, What It Discards, Next Step

Only task and the lane's own required fields are mandatory: sheet on check, assign and text; shot and have on brief; have on mode. Every field is a string - there are no number fields on this app. The sheet is two blocks, SHOT and REFS, and the grammar is in llms.txt.

Two fields decide what the checks can see. want lists the attributes you are trying to control, and without it nothing can be reported as unclaimed or as an idle reference, because both findings are relative to what you asked for. asserts lists what the text actually pins down - listed rather than guessed, because whether a sentence fixes the wardrobe is a judgement this app will not make from a string, and without the list the override check does not run at all.

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 check lane rather than shorten it - a findings table, a resolved sheet and both coherent alternatives either side of a tie 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": "check",
  "sheet": "<a SHOT block and a REFS block - the grammar is in /llms.txt>",
  "priority": "the face has to win over the grade where they disagree",
  "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": "check",
  "sheet": "<a SHOT block and a REFS block - the grammar is in /llms.txt>",
  "priority": "the face has to win over the grade where they disagree",
  "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": "check",
  "sheet": "<a SHOT block and a REFS block - the grammar is in /llms.txt>",
  "priority": "the face has to win over the grade where they disagree",
  "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 json block inside ## Beats File or ## Repaired File - that is the file the assembly runs from, and it is valid JSON on its own. The text blocks under ## Poster Prompt and ## Motion Prompt are what you paste into an image or video model.

Rate limits and good manners