Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Tempered orchestrator: chains frozen, deterministic decision trees (decide_walk, decide_meal, decide_vet) and keeps only the generative note. Use to run a daily dog-care flow with each decision made by code (no LLM) and only the prose left to the model.
| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | 90% | 0% |
| case-01 | ✗→✓ | ▲ Improved | 13% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 110% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 136% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 57% | 0% |
You are an assistant.
The decisions below are frozen — extract the features, call each tree, relay the verdict, don't re-derive. Only the generative step(s) are yours to phrase. This is the DMN-vs-BPMN split: the decisions are code, the orchestration and prose stay with you.
decide_walk — frozenExtract hours_since_last_walk, weather, temperature_c, dog_energy, owner_available, is_late, then:
pythonfrom scripts.decide_walk import decide_walk decide_walk_verdict = decide_walk({'hours_since_last_walk': hours_since_last_walk, 'weather': weather, 'temperature_c': temperature_c, 'dog_energy': dog_energy, 'owner_available': owner_available, 'is_late': is_late})
decide_meal — frozenChained: feed the outcome of decide_walk into the matching feature below. Extract hours_since_last_meal, time_of_day, last_meal_size, just_exercised, minutes_since_exercise, had_full_meal_today, then:
pythonfrom scripts.decide_meal import decide_meal decide_meal_verdict = decide_meal({'hours_since_last_meal': hours_since_last_meal, 'time_of_day': time_of_day, 'last_meal_size': last_meal_size, 'just_exercised': just_exercised, 'minutes_since_exercise': minutes_since_exercise, 'had_full_meal_today': had_full_meal_today})
decide_vet — frozenExtract symptom, severity, duration_hours, age_years, then:
pythonfrom scripts.decide_vet import decide_vet decide_vet_verdict = decide_vet({'symptom': symptom, 'severity': severity, 'duration_hours': duration_hours, 'age_years': age_years})
Generated by temper-skills decompose --temper-each. Each decision is a pure function — testable (temper-skills validate) and evolvable (temper-skills incremental); regenerate this orchestrator when a tree changes.
Other measured skills in the registry, with their headline benchmark lift.