A Chinese design system for creating and reviewing web interfaces, with multiple design perspectives working together. It focuses on React and Tailwind-based projects.
Implement anticipatory UI — interfaces that react to pointer intent before the click. Three patterns: a proximity focus ring that warms as the cursor nears a field, a magnetic target that leans toward the cursor, and trajectory prediction that arms/prefetches the element the cursor is heading toward. Use this skill…
Turn a codebase directory and a business question into a single interactive HTML code map, or turn a described non-code business process into the same evidence-backed map. Use when the user asks to explain, map, or visualize code flows, architecture, modules, data models, or a business process.
Create and maintain evidence-based Product Requirements Documents (PRDs). Use when writing, reviewing, or revising product requirements, initiative scope, success measures, or product decisions before technical design and delivery planning.
Universal SSH multiplexing CLI for AI agents. Zero-overhead C daemon with ControlMaster connection reuse eliminates repeated authentication latency. Trigger: remote server management, batch ops, SSH connection acceleration, executing commands on remote servers, VPS administration, server health checks, multi-server…
★not rated 7 4mo agoA✓ AI review85 tokens
originalMIT
Use when builds data transformation flows on top of cocoindex — a Python framework with a Rust engine for ultra-performant, incremental data indexing (ETL, RAG ingestion, knowledge graphs, vector search). Covers the flow-building public API: FlowBuilder, DataScope, DataSlice, Flow, FlowLiveUpdater, sources, targets…
Use this skill to understand the Shipshape workflow, shared Articles of Agreement, and select the correct role skill: /captain, /qm, /crew, /boatswain, or /shipwright. Entry point when no role is active or the right role is unclear.
Use when optimizing or diagnosing GPU workload performance with CUDA, CUTLASS, Triton, PyTorch, vLLM or TensorRT-LLM; interpreting NCU, Nsys or PyTorch Profiler evidence; or preparing the workload and correctness checks for such optimization. General coding, skill maintenance and conceptual GPU questions do not…
Use the Google Workspace CLI to inspect schemas, authenticate safely, and run Google Workspace API commands. Use when the user wants to work with Drive, Gmail, Sheets, Docs, Calendar, Chat, Tasks, or other Google Workspace APIs through the gws command.
Design and create pitlane eval benchmarks that measure whether an AI coding skill or MCP server actually improves assistant performance. Use when the user wants to test a skill, evaluate an MCP server, create a pitlane eval YAML, benchmark an AI assistant, or compare baseline vs challenger configurations. Covers eval…
Create PowerPoint/PDF presentations where each slide is a complete AI-generated image with all text embedded. Supports multiple visual styles (corporate, minimalist, creative, kawaii, custom). Use when user wants fully-illustrated slides, visual-first decks, or AI-generated presentation images via x402 payments.
Design LLM applications using LangChain 1.x and LangGraph for agents, memory, and tool integration. Use when building LangChain applications, implementing AI agents, or creating complex LLM workflows.
Create or revise source-grounded lessons, exercises, learning pages, WeChat articles/drafts, and HTML slide decks. Use for teaching content, learning assets, official-account content, or PPT-style presentations.
Search Adobe Fonts (Typekit) families, create and manage web kits/projects, and return ready-to-use embed snippets plus CSS font-family values. Use when the user asks to find Adobe fonts, compare font options, set up Typekit for a website, add fonts to kits, publish kits, or generate copy/paste font embed metadata for…
Use when augmenting balanced trees or dynamic sets with maintained metadata, order-statistic trees, interval trees, rank/select queries, overlap search, red-black-tree augmentation theorems, or production choices around custom indexed structures.
Broke to Built AI runs 44 x402 services on Bankr Cloud. 44 of 44 answered HTTP 402 at their listed price on their most recent health check (oldest check in this file: 2026-09-15). A health check proves a route is live and what it charges. It says nothing about the quality of the output, and none of these services has…
Triage a Marker.io website-feedback backlog at scale. Use when asked to go through, categorize, prioritize, deduplicate, or make sense of many Marker.io issues at once. Splits content fixes from functional bugs, groups by page, rates criticality, flags duplicates and repeat reporters, surfaces quick wins, lists…
A strategy for extracting readable content from web pages, including pages that need JavaScript to load or resist automated access.
★not rated 7 4mo agoA84 tokens
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: