Before After — AI skill for Claude Code
Before/after comparison — show exactly how AI-generated slop transforms into production-quality UI.
How to install Before After
Installs to ~/.claude/skills/phazurlabs-sumi-before-after/SKILL.md
mkdir -p ~/.claude/skills/phazurlabs-sumi-before-after && curl -fsSL https://raw.githubusercontent.com/phazurlabs/sumi/HEAD/commands/before-after.md -o ~/.claude/skills/phazurlabs-sumi-before-after/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Before After does
name: before-after description: "Before/after comparison — show exactly how AI-generated slop transforms into production-quality UI. Visual proof of every design improvement." argument-hint: "[file or component to compare]"
Before / After — Transformation Proof
Before running
This command needs a file or component to compare.
If the user invoked it with nothing and no target is evident from the conversation or open files, ask for it in one plain-language question and stop. Do no
Alternatives in AI
- Model Update — 增量更新财务模型 — 用新财报/新指引/修正假设重算 DCF 内在价值、Comps 隐含价、投资逻辑与目标价,输出 before→after delta 6.6k ★
- Golutra — Multi-agent AI orchestration platform for automation, workflows, and developer tools 3.8k ★
- Sentrux — Real-time architectural sensor that helps AI agents close the feedback loop, enabling recursive self-improveme 2.9k ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Slop Cop
Detect AI-generated language patterns in your codebase with this Claude Code skill to ensure human-quality pro
Sth Blueprint
Open or refresh your AI skills organization chart. First run auto-scans your project and sets up ./skills-dash
PDF Proof
Trust, but check. A Claude skill that turns AI answers into visual proof — highlighted screenshots and confide
Contextkit
by Cihat Gündüz - A systematic development framework that transforms Claude Code into a proactive development
Prompt To Session
A proof of concept for prompt-driven DAW automation using ChatGPT, Claude Cowork, Codex, and Ableton Live 12 L
AI Engineer Review
Get a brutally honest review of your project from the perspective of a principal AI engineer. Covers architect
Related Agents
Asset QA Validator
Use this agent when validating a kie.ai-generated image for a short video, before it goes into composition. It
Plantuml Visual QA
Visual quality assurance agent for plantuml-js. Use when asked to check rendering accuracy, compare output aga
Codecrusher
Senior Developer & Implementation Expert who transforms architectural plans into high-quality, production-read