Quality

Refactor performs intelligent, deterministic refactoring with codebase awareness, mapping code, assessing risk, planning, and verifying each change. Use it to safely restructure files, modules, or projects by triggering /refactor and specifying a target, scope, and risk strategy.

Remove AI Slops cleans AI-generated code smells from branch changes or explicit file lists, locks behavior with regression tests first, runs categorized cleanup via parallel agents, and verifies with quality gates. Use it when asked to remove slop or clean AI-generated patterns from recent changes.

Review Work orchestrates a post-implementation review by launching five parallel sub-agents for goal verification, code quality, security, QA execution, and context mining; all must pass before a PR handoff. Use it when you need to review completed work.

Ultrawork activates a rigorous, outcome-first coding workflow when a Codex prompt contains 'ultrawork' or 'ulw', requiring tier triage, RED-to-GREEN evidence, and real-surface manual QA through HTTP, terminal, browser, or computer-use channels before work is declared done.

Implementation Validator checks whether an implementation matches its stated goal and returns a structured pass/warn/fail verdict with actionable issues. Use it when you need a second opinion on your own output or when a user asks to review an implementation.

Reproduce LinkedIn Issue runs the failing MCP tool call against the real authenticated LinkedIn session on the current branch and captures concrete evidence — output JSON, error message, partial state — then maps it back to the scraper code path. Use when asked to reproduce, investigate, or verify an issue number locally.

Triage Issues and PRs scans all open issues and pull requests in a repository and ranks them by urgency, implementation quality, and contributor track record to help a maintainer decide what to tackle next. Use it when asking what to fix first, which PRs are production-ready, or to triage a backlog.

Triage PR Reviews fetches all review comments on a pull request, verifies each finding against the actual code, fixes valid issues, replies on each thread, and resolves them.

Verify PR Fix checks out a candidate pull request locally, restarts the MCP server on that branch, re-runs the exact MCP tool call that previously failed, diffs outputs against a saved baseline, and audits the fix for locale-independence, DOM-stability, and scope. Use when asked to verify a PR fixes a reproduced issue.

Complex Test validates directory-based skill discovery (the */SKILL.md pattern) for smoke testing.

Evaluate Presets runs shell scripts to test Ralph's hat collection presets, validating configurations and auditing the preset library for bugs and UX issues.

Review PR runs the ralph.reviewer.yml orchestration loop against a pull request, checking out the PR in an isolated worktree, running tests, reviewing the diff, and producing a structured report. Use it when asked to review a PR or a GitHub pull request URL.