Menú
SkillsMP ha recopilado 9 skills de arklexai/arksim. Abre una skill para revisar su origen y sus detalles.
Mostrando 9 de 9 skills recopiladas.
Use when the user wants to re-evaluate a previous arksim simulation with different metrics, thresholds, or judge model without re-running the agent. Cheaper than re-simulating.
Idioma del texto original: inglés
Use when the user wants to inspect arksim evaluation results, debug specific failures turn by turn, or compare two runs to measure improvement.
Idioma del texto original: inglés
Use when the user wants to generate, edit, or extend arksim test scenarios. Reads the agent's source code to derive realistic scenarios; can build regression scenarios from past failures.
Idioma del texto original: inglés
Use when the user wants to simulate multi-turn conversations against an AI agent. Alias for the arksim-test skill; the canonical flow lives there.
Idioma del texto original: inglés
Use when the user wants to test, simulate, or evaluate an AI agent against multi-turn scenarios (also exposed as the arksim-simulate alias). Discovers the agent, generates scenarios, runs simulation and evaluation, surfaces failures.
Idioma del texto original: inglés
Use when the user wants to launch the arksim web dashboard to browse evaluation results visually rather than in CLI output.
Idioma del texto original: inglés
Generate a PR title and description from your changes
Idioma del texto original: inglés
Check your branch before opening a PR (lint, test, title validation)
Idioma del texto original: inglés
Review a pull request against arksim project standards
Idioma del texto original: inglés