hill-climb

SKILLWorkflowcommunauté
v0.0.0skillberry-aiApache-2.0Mis à jour il y a 1 moisSource →

Runs a global hill-climb optimization loop where the parent is always the current best candidate and the val significance gate decides acceptance. Use as the algorithm for most runs. Pick how each iteration's reflection is focused with --focus all (whole train set), cyclic (one task at a time), or h

Community-submitted skill. Not yet reviewed by the Forge team. Full prompt content may not be available.Request review →
37Étoiles du dépôt
1Clients
1Formats
il y a 1 moisDernière mise à jour
Skill
Auteurskillberry-ai
Version0.0.0
LicenceApache-2.0
CatégorieWorkflow
Formatsskill.md
PromptNon publié
Compatibilité
Claude✓ Pris en charge
Cursor—
Copilot—
ChatGPT—
Gemini—
À propos

Runs a global hill-climb optimization loop where the parent is always the current best candidate and the val significance gate decides acceptance. Use as the algorithm for most runs. Pick how each iteration's reflection is focused with --focus all (whole train set), cyclic (one task at a time), or hardest-first (lowest-scoring tasks first). Replaces the former all-at-once, cyclic, and hardest-firs

Mots-clés
skillclaude

Aucune couverture des dépendances

Cette entrée ne publie aucun paquet npm : Forge n'a donc pas d'arbre de dépendances pour elle. C'est une lacune de couverture — pas une affirmation qu'elle n'a aucune dépendance.