Create custom subagents for specialized AI tasks. Use when you want to create a new type of subagent, set up task-specific agents, configure code reviewers, debuggers, or domain-specific assistants with custom prompts.
Debugging specialist for errors, test failures, and unexpected behavior. Use when encountering reproducible bugs; follow reproduction steps and remove instrumentation before finishing.
Convert 'Applied intelligently' Cursor rules (.cursor/rules/*.mdc) and slash commands (.cursor/commands/*.md) to Agent Skills format (.cursor/skills/). Use when you want to migrate rules or commands to skills, convert .mdc rules to SKILL.md format, or consolidate commands into the skills directory.
Adversarial multi-model code review — launch parallel readonly reviewers on different models, then synthesize consensus vs lone findings. Do not apply fixes unless the user asks.
Reproduce reported bugs before fixing. Provide evidence of reproduction and the fix; do not stop after repro to ask the user—continue to fix.
Guide users building apps, scripts, CI pipelines, or automations on top of the Cursor SDK - TypeScript (@cursor/sdk) or Python (cursor-sdk / cursor_sdk). Use when integrating Cursor agents programmatically; Agent.create, Agent.prompt, streaming, local vs cloud runtime, MCP, errors.
Runs the rest of a /shell request as a literal shell command. Use only when the user explicitly invokes /shell and wants the following text executed directly in the terminal.
Split current work into small reviewable PRs. Use when the user asks to split a chat, set of changes, branch, or PR.