
Yao Decision
Typed decision expert.
Install
npx skills add YaoApp/yao --skill yao-decision -g -a claude-code -y- Repository
- YaoApp/yao8.2k
- Category
- Engineering
- Updated
- 17d ago
- License
- See repository
- Context cost
- Lightabout 1,189 tokens
- Runs scripts
- No, instructions only
What it does
Typed decision expert. ALWAYS invoke this skill when you need structured classification, scoring, or probability estimation, routing tickets, grading content, detecting intent, or any task requiring typed answers with calibrated confidence.
Decision Tools
Use these tools when you need structured, typed decisions rather than free-form LLM text. Decision models return machine-readable answers with probabilities and confidence scores.
decision_decide
Send a state (context) and one or more typed questions to a decision model.
Question Types
| Type | Purpose | Criteria | Answer Fields |
|---|---|---|---|
choice | Classify into one of N options | {option: description} map | choice, probabilities, confidence |
score | Rate on a scale | [level_labels] array | score, legend, probabilities, confidence |
noul | Estimate a probability (0-1) | (none) | noul |
Basic usage (choice + noul):
tai tool decision_decide --state "Customer says: my billing is wrong, I was charged twice" --questions '{"department":{"type":"choice","instructions":"Route to the right department","criteria":{"billing":"Payment issues","technical":"Product bugs","sales":"Purchase inquiries"}},"is_urgent":{"type":"noul","instructions":"Is this urgent?"}}'
With score question:
tai tool decision_decide --state "The agent resolved the issue in 2 minutes with a clear explanation" --questions '{"quality":{"type":"score","instructions":"Rate the support quality","criteria":["Poor","Below average","Average","Good","Excellent"]}}'
With explicit provider:
tai tool decision_decide --state "some context" --questions '{"q1":{"type":"noul","instructions":"Is this positive?"}}' --provider t862699292876.typesafe
With model override:
tai tool decision_decide --state "some context" --questions '{"q1":{"type":"noul","instructions":"Is this positive?"}}' --model jev-latest
