Art & Design

使用模型原生视觉将中文书页、扫描页和截图逐页转写为可编辑文稿，默认不使用 OCR。

接口文档转字段映射（ERP/OpenAPI 一键结构化）：把 API 文档解析成字段名/类型/必填/端点，直接出映射。适合对接第三方、低代码搭建。

爬虫/自动化 防封指纹伪装（UA+分辨率池）：随机真实浏览器指纹（88+ UA、87 分辨率）降低风控识别。适合爬虫工程师、RPA 开发者、海外社媒多账号。

Evidence-driven Agent Skill for screening public Xiaohongshu rental listings.

App usage stats, clearer than built-in Screen Time. Local HTML reports for macOS and Windows.

Codex-native frontend skills, custom agents, profiles, and an evidence-backed evaluation harness for React, Next.js, Vite, and Astro.

Your Marketing Doctor: an open Agent Skill for DTC ecommerce diagnosis using first-party attribution, automatic routing, and actionable reports.

Three Agent Skills over one pluggable PTY + pyte core: drive TUIs, design terminal effects, and render cell-accurate UIs. pip install smartcli-toolkit

Custom Codex skills for PDF and Construct 3 workflows

Compact Rust agent CLI for local OpenAI-compatible models, with Docker isolation, sessions, skills, MCP, plan mode, sub-agents, and web search.

SkillForge is a workspace customization framework designed to build, manage, and orchestrate personalized AI Sub-Agents and modular skills. It serves as a foundation for generating platform-agnostic workflows.

MCP server for AlbumentationsX image augmentation workflows

Reusable Codex skills for decisions, writing, frontend design, and algorithmic art.

Simulate evidence-grounded timelines from a point of change, mapping causes, people, and branching futures with disciplined uncertainty.

Codex-first MCP that stops generic AI UI slop in Codex, Claude Code, and Cursor using real web/iOS UI references, design contracts, validation, audits, and critiques.

humanizer, but for code — an agent skill that removes AI-generated code slop: duplicated helpers, try-import fallbacks, broad excepts, speculative abstractions. Test-gated, behavior-preserving.

Let AI agents share your everyday, logged-in Chrome through a Skill + CLI — locally or across multiple machines.

Python toolkit, MCP server, and agent skills for reproducible, auditable clickstream and event log analytics. Helps AI agents, data scientists and analysts build, validate, and cross-check product analytics, quantitative UX, customer journeys, graph-based user flows, behavioral segmentation, A/B tests, process mining models, Markov chain simulation

Evidence-safe China market launch skill for English-language SaaS products

Queue research questions all day. Wake up to answers. Puts your idle Claude Code quota to work while you sleep.

Self-evolving skill packs that give Claude Code & Codex judgment, not knowledge — decidable rules, per-playbook regression quizzes for models, and a project harness generator. zh-TW canon + full EN mirror.

Turn agent sessions into illustrated, reproducible Word documentation with automatic screenshots and encoding-safe images.

Recently updated agent-skill-related GitHub repository: SemineChen/yueban-image-to-code.

Agentic tools for the Tableau workflow. Claude skills built around Tableau MCP to help practitioners design dashboards, author calculations, generate synthetic data, evaluate visualizations, document analytics assets, and improve governance. Built and maintained by Adam Mico. Independent community project, not affiliated with Salesforce.