Menu
Split current work into small reviewable PRs. Use when the user asks to split a chat, set of changes, branch, or PR.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
| name | split-to-prs |
| description | Split current work into small reviewable PRs. Use when the user asks to split a chat, set of changes, branch, or PR. |
| disable-model-invocation | true |
Turn one pile of work into a few small PRs.
reset --hard, clean -fdx, branch
deletion, force-push, history rewrite) without explicit approval.main, so do not assume there is already a safe branch.git add . / git add -A.Compare the current work to the repo's default branch, including committed and uncommitted changes. Summarize the real slices you see, and use the chat history to recover intent.
Before proposing slices, find ownership signals for the touched paths (CODEOWNERS, nested
ownership files, tools/ownership/PRODUCTOWNERS, or repo equivalents) and use them to identify
natural reviewer boundaries.
Use judgment on detail. Usually PR titles are enough. Add a one-line scope note only when a title is unclear. Show a Mermaid diagram when there are multiple slices.
Optimize for reviewer-aligned PRs with minimal unrelated diff: split independent owners or concerns, keep tightly coupled changes together, and when stacking is necessary, order foundations before consumers.
Ask for approval before starting.
If there is uncommitted work, save a recoverable snapshot without changing the working tree:
SHA=$(git stash create "pre-split")
if [ -n "$SHA" ]; then
git update-ref "refs/backup/pre-split-$(date +%s)" "$SHA"
fi
For each approved slice, create a branch from the right base, stage and commit only the planned files or hunks, then push and open the PR.
Keep it short: PR titles and URLs, plus anything left on the starting branch or working tree. Do not delete the backup ref or original branch unless the user asks.
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.