Launches a built app and verifies it against the spec using browser/electron automation. Includes fix loop. Use after implementation to verify the app works as specified.
Generate multi-CLI distribution packages from the Claude Code plugin. Converts skills, agents, and hooks for Gemini CLI, OpenCode, and Codex CLI under dist/.
Iteratively optimizes prompts for token efficiency by maximizing information density - reduces verbosity, removes redundancy, tightens phrasing while preserving semantic content.
Walk through a PR or large diff together — your own or someone else''s — one sub-changeset at a time and one review topic at a time within it.
Manifest builder. Plan work, scope tasks, spec out requirements, break down complex tasks before implementation.
Iteratively auto-optimize a prompt until no issues remain. Uses prompt-reviewer in a loop, asks user for ambiguities, applies fixes via prompt-engineering skill.
Figure things out together — any topic, problem, or idea. Collaborative thinking partner that investigates before claiming, builds shared truth through evidence not inference.
Compresses prompts/skills into minimal goal-focused instructions. Trusts the model, drops what it already knows, maximizes action space.
Analyzes the current project structure and tech stack. Use when asked to explore, understand, or summarize a project.
Sync the prompt-engineering plugin from a local clone of claude-code-plugins into .claude/ so the repo is self-contained for isolated/web environments.
Harden /define task guidance files for one-shot quality. Iterates: orthogonality gap analysis, user-approved additions, prompt review, fix, converge.
Use when stuck in circles and want to hand off to another agent (Codex CLI) with full context