Agent skill

tuning/parameter-optimizer

Optimize Ollama PARAMETER values (temperature, num_ctx, top_k, top_p, repeat_penalty, stop sequences) per task. Use to translate tuning directives into runtime presets.

View SKILL.md on GitHub Repository
Stars 163
Forks 31

Install this agent skill to your Project

npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/productivity/tuningparameter-optimizer

SKILL.md

Parameter Optimizer

Capabilities

  • set_cognitive_temperature: adjust creativity vs. determinism.
  • define_context_window: set num_ctx based on doc size/task.
  • configure_stop_sequences: define stop tokens to bound outputs.
  • penalize_repetition: adjust repeat_penalty to avoid loops.

Dependencies

  • embedding-repair (diag logging)
  • reliability-budget (optional SLO tuning)

Outputs

  • parameter preset dict for Ollama run/create.

Didn't find tool you were looking for?

Be as detailed as possible for better results