Menü
Recommend the best model tier (haiku/sonnet/opus) for the current task by complexity and budget.
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Basierend auf der SOC-Berufsklassifikation
Scan installed skills to extract cross-cutting principles and distill them into rules — append, revise, or create new rule files.
Audit all installed OpenClaw skills for quality: content overlap, freshness, and uniqueness. Supports Quick Scan (changed only) and Full Stocktake modes.
Cluster MEMORY.md entries by theme and optionally generate SKILL.md drafts.
Export MEMORY.md to a timestamped markdown file for sharing or backup.
Import memory entries from a markdown export file, merging with MEMORY.md without duplicating.
Show current workspace memory: MEMORY.md contents, pending recalls, and index status.
| name | cmd_model_route |
| description | Recommend the best model tier (haiku/sonnet/opus) for the current task by complexity and budget. |
| user-invocable | true |
| origin | openclaw-mas |
| argument-hint | <project-path> <task> |
The first argument is the project path. Before doing anything else:
Recommend the best model tier for the current task by complexity and budget.
/model-route [task-description] [--budget low|med|high]
haiku: deterministic, low-risk mechanical changessonnet: default for implementation and refactorsopus: architecture, deep review, ambiguous requirements$ARGUMENTS:
[task-description] optional free-text--budget low|med|high optional