Guidance for distinctive, intentional UI design, typography, visual direction, and non-template-like product interfaces.

Reviews animation and motion code against a high craft bar derived from Emil Kowalski's design engineering philosophy. Default to flagging; approval is earned.

This skill encodes Emil Kowalski's philosophy on UI polish, component design, animation decisions, and the invisible details that make software feel great.

🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org

A set of agent skills that help improve different parts of a product, from animations and typography to layout and colors.

A full-lifecycle Claude Code skill for creating, compiling, reviewing, and polishing academic Beamer LaTeX presentations with quality scoring and pedagogical audits.

Agent skill to drive BaoCut macOS app for video transcription, subtitling, translation, and cutting via natural language.

An evidence-bound Codex skill for LLM internship resume polishing, JD tailoring, interview grilling, and project scouting.

Run a 5-dimension expert design review on any HTML artifact in the project — Philosophy / Visual hierarchy / Detail / Functionality / Innovation, each scored 0–10. Outputs a single self-contained HTML report with a radar chart, evidence-backed scores, and three lists: Keep / Fix / Quick-wins. Use when the brief asks for a "design review", "design critique", "5 维度评审", "design audit", or "what's wrong with my design".

Turn any domain folder of skills into a bounded agentic loop: compile a goal into a verifiable task plan, execute tasks with the domain's own tools, verify every task with machine-run checks, retry with caps, escalate to a human when budgets exhaust, and refuse to close until everything is verified or explicitly waived. Use when you want an agent or subagent to pick up a goal and drive it to a verified close across one of this repo's 18 domains ('run this goal through the engineering harness', 'set up an agentic loop for marketing work', 'make the finance domain self-verifying'). NOT for authoring Claude Code Workflow-tool .js scripts (workflow-builder), N-agent tournaments on one task (agenthub), single-file metric optimization (autoresearch-agent), or discovering published loop recipes (loop-library).

A design engineering system for AI coding agents to produce production-quality UI with craft-level standards.

A collection of 70 agent skills for frontend, motion, accessibility, QA, and handoff workflows, designed for Codex and compatible with other AI coding tools.