reasoning-effort-throttle

SKILLFlusso di lavorocommunity
v0.0.0NeeeophyteeNOASSERTIONAggiornato 2 mesi faFonte →

Stop paying for deep reasoning on easy turns by setting a modest default reasoning effort and escalating per task. Use when the user runs a reasoning model in an agent and the bill is dominated by output or thinking tokens, or asks about reasoning_effort, thinking budgets, or why a cheap model is st

Community-submitted skill. Not yet reviewed by the Forge team. Full prompt content may not be available.Request review →
18Stelle del repo
1Client
1Formati
2 mesi faUltimo aggiornamento
Skill
AutoreNeeeophytee
Versione0.0.0
LicenzaNOASSERTION
CategoriaFlusso di lavoro
Formatiskill.md
PromptNon pubblicato
Compatibilità
Claude✓ Supportato
Cursor—
Copilot—
ChatGPT—
Gemini—
Descrizione

Stop paying for deep reasoning on easy turns by setting a modest default reasoning effort and escalating per task. Use when the user runs a reasoning model in an agent and the bill is dominated by output or thinking tokens, or asks about reasoning_effort, thinking budgets, or why a cheap model is still expensive to run.

Parole chiave
skillclaude

Nessuna copertura delle dipendenze

Questa voce non pubblica alcun pacchetto npm, quindi Forge non ha un albero delle dipendenze per essa. È una lacuna di copertura, non l'affermazione che non abbia dipendenze.