arklexai/arksim

arksim-evaluate

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.

原文语言：英语

arksim-results

Use when the user wants to inspect arksim evaluation results, debug specific failures turn by turn, or compare two runs to measure improvement.

原文语言：英语

arksim-scenarios

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.

原文语言：英语

arksim-simulate

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.

原文语言：英语

arksim-test

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.

原文语言：英语

arksim-ui

Use when the user wants to launch the arksim web dashboard to browse evaluation results visually rather than in CLI output.

原文语言：英语

draft-pr

Generate a PR title and description from your changes

原文语言：英语

pre-review

Check your branch before opening a PR (lint, test, title validation)

原文语言：英语

review-pr

Review a pull request against arksim project standards

原文语言：英语