Menu
Review changed code for reuse, quality, and efficiency, then fix issues found. Use after implementing a feature or bug fix.
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
Control Herdr, a terminal multiplexer for coding agents. Use only when the user explicitly mentions Herdr or asks to use Herdr to inspect or control panes, tabs, workspaces, terminals, commands, or communication with another agent. Do not use merely because a task could benefit from a background terminal, delegation, or parallel work. Requires HERDR_ENV=1.
Compact the current conversation into a handoff document for another agent to pick up.
Use when the user says "tuicr review", "/tuicr", "open tuicr", or asks to review local changes in tuicr. Launch tuicr in tmux, then use tuicr's review CLI to read or add comments in TUI review sessions.
Investigate aube package-manager trust, provenance, advisory, or install failures before adding bypasses or package exceptions. Use when `aube install`, `aube add`, `aube audit`, or `mise install` with `npm.package_manager = "aube"` fails on trust policy, provenance, advisories, lifecycle scripts, low downloads, lockfile drift, or another supply-chain gate; also use before adding `trustPolicyExclude`, turning `trustPolicy` off, allowing package builds, or accepting npm packages installed through mise.
Always use this skill for PR creation. Use whenever the user asks to open, create, draft, prepare, or submit a pull request, unless they explicitly ask for raw CLI/API commands instead.
Attach an issue or attach a ticket by creating a Platform Linear issue for a PDQ PR or unpushed branch, renaming the branch when needed, updating the PR title, and rerunning the ticketing check.
| name | simplify |
| description | Review changed code for reuse, quality, and efficiency, then fix issues found. Use after implementing a feature or bug fix. |
| argument-hint | [focus area or concern] |
You are performing a post-change cleanup pass focused on code reuse, code quality, and efficiency.
If the user provided arguments, treat them as extra review focus:
$ARGUMENTS
Run git diff (or git diff HEAD if there are staged changes) to see what changed. If there are no git changes, review the most recently modified files that the user mentioned or that you edited earlier in this conversation.
Use the Task tool to launch all three agents concurrently in a single message. Pass each agent the full diff so it has complete context.
Check for:
Check for:
Check for:
Wait for all three agents to complete. Aggregate findings and fix each valid issue directly.
If a finding is a false positive or not worth addressing, note it and move on. Do not argue with the finding.
If you made code changes, run the project's relevant tests after applying fixes. Prefer targeted tests first, then broader test suites when appropriate.
When done, briefly summarize what was fixed, or confirm the code was already clean.
