Shape a complex idea, workflow, design, or report on work around the judgment a person needs to make. Use when summarizing, reporting on, or explaining complex work to someone who must judge or act on it, or when an explanation obscures its point or makes the…
Find and carry through worthwhile code simplifications across recent edits, named files, or a subsystem. Use for a collapse pass, a refactoring pass, another simplification pass, "simplify this", clean up code, or a hunt for indirection and dead abstractions.…
Apply Epicenter’s Svelte 5 patterns for runes, components, lifecycles, and workspace-backed state. Use when editing `.svelte`, `.svelte.ts`, or Svelte UI state.
Independently pursue the strongest greenfield design, challenge the underlying model, and find concrete deletion prizes. Use when asking for an adversarial review, an independent architecture review, or an adversarial checkpoint on a plan or cumulative…
Improve an interactive product through repeated computer-use simulations, bounded Claude implementation, verification, and reflection to find opportunities to collapse complexity. Use when asked to keep exercising and improving a UI across implementation…
Assign Claude Code a read-only investigation, recommendation, or finished text draft. Use when asked to consult Claude or when a design-review workflow includes Claude. Completed edits and executable experiments belong to delegate-claude.
Delegate a bounded implementation, prototype, benchmark, or file artifact to Claude Code, then verify and integrate its completed work. Use when the user explicitly authorizes Claude to own execution. Read-only advice belongs to consult-claude.
Write and maintain repository guidance across AGENTS.md, CLAUDE.md, and .agents/skills. Use when creating or editing skills, deciding where instructions belong, or diagnosing instruction sprawl and skill selection. Do not use merely because another skill is…