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.
Quellsprache: Englisch
Diesen Prompt kopieren und in den verwendeten KI-Assistenten einfügen.
Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/arklexai/arksim.README des Repositorys wird geladen…
Es werden 9 von 9 gesammelten Skills angezeigt.
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.
Quellsprache: Englisch
Use when the user wants to inspect arksim evaluation results, debug specific failures turn by turn, or compare two runs to measure improvement.
Quellsprache: Englisch
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.
Quellsprache: Englisch
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.
Quellsprache: Englisch
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.
Quellsprache: Englisch
Use when the user wants to launch the arksim web dashboard to browse evaluation results visually rather than in CLI output.
Quellsprache: Englisch
Generate a PR title and description from your changes
Quellsprache: Englisch
Check your branch before opening a PR (lint, test, title validation)
Quellsprache: Englisch
Review a pull request against arksim project standards
Quellsprache: Englisch
Die README konnte nicht geladen werden. Die Skills des Repositorys lassen sich unten weiterhin ansehen.