Rework a change as if the intended UX and architecture had existed from day one — deleting compatibility cruft, dead branches, and accidental complexity instead of patching around them. Use when refactoring, cleaning up after a feature lands, removing flags, collapsing legacy paths, or when the user says the code "should look like X from scratch".
The English summary is being prepared. Showing the original description.
See how to installReview the instructions the agent will receive before you install.
Reshape the change from the intended end state, not from the historical path that produced the current patch. The goal is the code that should exist now, not the smallest diff from what's there.
Name the end state. In one or two sentences, describe the product surface and architecture as if you were building it today.
Find real callers before preserving anything. Grep for actual usage of each mode, prop, wrapper, route alias, or fallback. If nothing references it, delete it — do not "improve" it.
Reshape around the final surface. Prefer one clear component or flow over mode flags. Split only when there is an obvious boundary: state, layout, controls, or domain commands.
Move shared rules to one place. Feature flags, permissions, route gating, URL state, and command naming must not be duplicated across pages or buried inside view components.
Verify the intended flow. Test the new behavior and the assumptions you deleted — anything that touched navigation, permissions, or persisted state.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression.
The English summary is being prepared. Showing the original description.
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
The English summary is being prepared. Showing the original description.
Find deepening opportunities in a codebase, informed by the project's own domain language and prior design decisions. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.
The English summary is being prepared. Showing the original description.
Resolve a verified cluster of Rembric issues from causal root to evidence-gated closure. Use after systemic triage identifies a shared root, or when the user asks to attack issues at the root, create a mechanism map, plan a deletion-first fix, or close a fixed/stale issue cluster. Use `diagnose` for a single defect whose reproduction is not yet established.
The English summary is being prepared. Showing the original description.
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
The English summary is being prepared. Showing the original description.
Migrates React projects and components from Radix UI to Base UI. Use when asked to migrate from radix, move to base-ui, convert radix primitives, or switch a shadcn project's base library. Handles single components ("migrate accordion") and whole projects.
The English summary is being prepared. Showing the original description.