Art & Design

A Claude Code skill for the moment your brain stops. /huh makes the agent stop, find the context you never saw, and explain itself like a person.

Audience-aware, repository-grounded README generation for agents (inspect + evidence + lint)

For almost any idea, someone has already built a version of it. Checks what have been built, before your AI agent starts building.

Build guided interactive HTML demos with your coding agent.

Agent skill and user docs for exray — an agent-native MCP web-scraping runtime. Service is hosted at mcp.exray.dev; nothing here to run.

Decide where to go before building the itinerary. A Codex / Claude Code travel skill that hard-filters destinations before it scores them, verifies every fare, timetable and entry rule against a live source, and ships a self-contained booking-ready HTML plan — per-segment maps, sourced per-person budget, all data local.

Agent skill: name files/projects by surveying local repo structure

Agent skills I actually use — deslop, swiftui, and more to come

Agent skills for Codex/Claude to set up automations that send iPhone Live Activity, widget, notification, and Control Widget updates to your iPhone.

Suit up. Build anything. A drop-in engineering organization for Claude Code — deep idea interrogation, TDD sprints, enforced quality gates. 43 skills · 8 agents · 13 hooks.

AI Corner Store 🏪 — a small, curated shop of AI skills, plugins, and bundles for Claude. One folder per release, each installable on its own. Now stocking: organisational-dysfunction (61 dysfunctions via open sociotechnical systems theory).

Strip the markers that make text read as machine-generated. Ordered by measured frequency in agent-written prose: formatting first, paste-era artifacts last. Sources cited, unsourced claims labelled.

Optimize any AI agent’s skills, tools/MCP, and prompts against your own evals.

Vibe code with pi in a lightweight, real IDE - The Vibe You Need

AI agent skill for end-to-end hotel search and booking—compare live rates across leading OTAs and hotel suppliers, verify availability, book stays, and manage reservations, cancellations, and payments via the TourMind API.

A low-token visual evidence compiler for text-only coding agents. Convert images into compact Visual Evidence Packets (VEP) for DeepSeek, Codex, Claude Code, and other text-only models.

Evaluate a RAG system or AI-agent release against an accepted baseline, diagnose regressions, and produce explainable PASS, WARN, or BLOCK evidence. Use for candidate traces, RAG evaluation scenarios, model or prompt changes, release gates, citation regressions, abstention checks, and pre-release AI quality reviews.

Compose, arrange, revise, validate, compare, inspect, and export original multi-track music as Standard MIDI with Codex and BeatFlow's style-neutral Python DSL. Use for translating a musical brief into coordinated instrumental roles, writing complete songs in any genre, diagnosing rhythm or phrasing problems, or working with BeatFlow Composition 1.1 and MIDI files.

A fail-closed agent skill for generating and verifying WCAG 2.2 high-contrast Figma token modes from explicit semantic foreground/background pairs.

Archive single or batch Xiaohongshu notes to Markdown with metadata, images, tags, resume support, and reports.

Codex skill for exporting public WeChat articles to Markdown, sanitized offline HTML, and local images.

Codex skill for requirement discovery, evidence-based solution design, Mermaid diagrams, and verified formal PDF delivery.

Codex skill for converting runnable mobile HTML prototypes into native iOS interfaces with SwiftUI or UIKit, including component mapping, navigation, Auto Layout, simulator screenshots, and visual validation.

A Codex skill for review ui design.