con un clic
algorithm-selection
// Use this when the user needs to choose between multiple ML routes after survey but before committing to implementation. Compares candidate approaches, selects one, records rejected routes, and keeps a fallback.
// Use this when the user needs to choose between multiple ML routes after survey but before committing to implementation. Compares candidate approaches, selects one, records rejected routes, and keeps a fallback.
| name | algorithm-selection |
| description | Use this when the user needs to choose between multiple ML routes after survey but before committing to implementation. Compares candidate approaches, selects one, records rejected routes, and keeps a fallback. |
| metadata | {"openclaw":{"emoji":"🧭"}} |
Don't ask permission. Just do it.
Use this skill after /research-survey when there are several plausible ML approaches and the project needs a deliberate route choice instead of jumping straight into implementation.
Outputs go to the workspace root.
survey_res.md already existsSOUL.mdsurvey_res.mdknowledge/paper_*.md when availableIf survey_res.md is missing, stop and say: Run /research-survey first to complete the deep analysis.
selection_res.mdRead:
SOUL.mdsurvey_res.mdknowledge/paper_*.mdExtract:
Create 2-3 realistic candidate routes only. For each route, record:
Use references/candidate-template.md.
Choose:
Chosen RouteRejected RoutesFallback RouteThe fallback should be the route most likely to work if the chosen route underperforms or proves too expensive to implement.
selection_res.mdUse references/selection-template.md.
The final output must include:
SOUL.md.