Art & Design

Find which segment of your VPS/proxy chain is broken, without the agent disconnecting itself. Xray, 3x-ui, Reality, Hysteria2. Python stdlib only.

VMware vSphere storage management: datastores, iSCSI, vSAN. Domain-focused MCP skill with 11 tools.

A Codex and ChatGPT Skill that helps agents avoid scope creep and overengineering—finish the ask, prove it works, and keep software architecture clear.

HEDGEHOG codes Cleaner, Faster and with Fewer Tokens. Hedgehog's AI-driven development builds a task dependency graph from your spec-driven, BMAD-METHOD plan, so Claude Code, Cursor & Gemini CLI stay locked to it. A CLI-enforced state machine for agentic coding. Now builds DeepSeek DSH Plugins. DeepSeek Harness、DSH 插件、AI 编程、BMAD 方法

Mini Program Engineering Skill Suite is an Agent Skill suite for evidence‑first mini‑program development. It helps agents bring WeChat or other mini‑program projects from vague intent to reliable engineering work: project intake, product specification, architecture, implementation, UI & device adaptation, debugging, verification, release readiness.

Use live AI Open Source Radar evidence to browse, discover, verify, compare and select open-source AI projects or plan candidate stacks. Use for Radar rankings and collections, project or license checks, alternatives, technology selection, stack planning, or the Radar Skills library; do not use for general AI news or closed-source product research.

Find and compare current creator or editorial topic candidates with AI Workstation Global Topic Radar, or build a research-ready brief for one supplied current topic. Use when the user needs a live-topic choice, a brief grounded in a current Radar card or a supplied topic name resolved against current Radar, or both in one workflow. Do not use for ordinary news or factual lookup, translation, rewriting, summarization, generic titles or ideas, platform-style advice, or complete supplied material that needs no current-topic decision.

>-

Agent skill from Spotfin/Ballast

The UX DeCode — 13 operational HCI principles as a Claude Skill. Evaluate and design interfaces with pass/fail criteria instead of opinions.

Linux setup, automation, MCP server, and Codex skill for VSDinside and Mirabox M18 Stream Docks

Codex skills for debranded visual DNA, style calibration, and deterministic multi-brand illustration overlays

Evidence-tiered UX auditing as a Claude skill: human-locked gates, preregistered thresholds, app_type-gated metrics and an append-only registry. Sibling of Mizan, Kiyas and Iskele. Bilingual TR/EN.

Recently updated agent-skill-related GitHub repository: TheonePro7/design-agent-skill.

Cross-platform Codex Skill for architecture, verification, product identity, privacy, release design, and publication.

An evidence-driven Codex skill for consistent live-action AI filmmaking—from clean identity and spatial anchors to cinematic shot design and Higgsfield-ready production packages.

A Codex skill for converting diagram images to draw.io and auditing or repairing embedded icons.

A lightweight, DSL-driven AI agent for file operations, code modification, and command execution — designed for web and client-side AI assistants.

VS Code marketplace UI for grim — the OCI package manager for AI artifacts (skills, rules, agents, MCP servers, bundles).

Easy WebBridge: open multi-browser bridge and Agent Skill for Codex, Claude Code and other AI agents.

Agent Skill for safely setting up Kiro Crew teams, GitHub issue automation, and service operations

Claude skill - strict Conventional Commits + Gitmoji commit messages

Visual HTML explainers and browsable notebooks for Codex.

CLI for Walmart Connect advertising support cases — read, answer, and file them without a browser