Score for triage
0.1 credits / checkRuns the same content check but surfaces the full per-category score map as the primary output, ranked by confidence. Use this when you want to apply your own thresholds per category or sort a review queue by risk level rather than acting on the default flag.
Use when
You want to set your own per-category thresholds or rank a queue by confidence, not trust one flag.
Not for
A simple yes-or-no check where the default verdict is enough.
Cost
0.1 credits / check
What it accepts
Set these inside the intent when you run it.
Text content to score. Provide text, an image URL, or both.
A publicly reachable URL of an image to score alongside or instead of text.
What you get back
The full per-category calibrated score map (0 to 1) ranked by confidence, alongside the overall flag, so you can apply your own thresholds.
Run it
Run this sub-skill directly: pin it with operation and pass its inputs in the intent. (Omit operation and the Content Moderation skill will route from your intent instead.)
curl -X POST "https://skill.askfaro.com/skills/content-moderation/run" \
-H "Authorization: Bearer $FARO_TOKEN" \
-H "Content-Type: application/json" \
-d '{"intent":{"operation":"triage","text":"This content might be borderline -- score it for me.","image_url":"https://example.com/review/image.jpg"}}'Example requests
- ›Score this batch of comments so I can rank them by risk level
- ›Apply my own threshold of 0.8 for violence and 0.6 for hate speech to this post
- ›Give me confidence scores per category for this piece of content