Agent skill
model-selection-orchestrator
Select the best local Ollama model for a task and emit tuning presets. Use when choosing between reasoning, creative, fast, vision, synthesis, or pre-AGI modes based on available local models.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/data/model-selection-orchestrator
SKILL.md
Model Selection Orchestrator
Choose an Ollama model based on task intent and emit a consistent tuning preset.
Workflow
- List local models with
ollama list. - Map the task to a preference list and pick the first available model.
- Emit a recommended model, a backup, and a tuning preset.
- Fall back to the fastest available model when none match.
Scripts
- Run: python skills/tuning/model-selection-orchestrator/scripts/recommend_model.py --task reasoning
References
- references/presets.json
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
majiayu000/claude-skill-registry
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
majiayu000/claude-skill-registry
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
majiayu000/claude-skill-registry
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?