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.
Use when the user wants to inspect arksim evaluation results, debug specific failures turn by turn, or compare two runs to measure improvement.
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.
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.
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.
Use when the user wants to launch the arksim web dashboard to browse evaluation results visually rather than in CLI output.
| name | draft-pr |
| description | Generate a PR title and description from your changes |
| disable-model-invocation | true |
| allowed-tools | Bash, Read, Grep, Glob |
Analyze commits and diff to produce a ready-to-use PR title and description.
Analyze commits and diff
git log --oneline main..HEAD
git diff --stat main..HEAD
git diff main..HEAD
Determine type and scope
Validate title
^(feat|fix|docs|chore|ci|build|refactor|test|perf|style|revert)(\([a-z][a-z0-9_-]*\))?!?: .+$Read and fill the PR template
Read .github/pull_request_template.md and fill in each section with real content from the commits and diff. Strip all HTML comments and placeholder text.
Validate description
Print the title and filled PR template body in raw markdown format, ready to copy:
Title: <type>(<scope>): <description>
<filled-out PR template in raw markdown>