Explore
15,439 skills indexed with the new KISS metadata standard.
Refactor HTML/TSX files to use existing UI components, DaisyUI classes, and semantic colors. Use when (1) refactoring React/TSX page components to use reusable UI components, (2) replacing raw HTML elements with component library equivalents, (3) converting primitive Tailwind colors to semantic DaisyUI colors, (4) extracting repeated styling patterns into components.
Smart PRD generator with TaskMaster integration. Detects existing PRDs and offers execute/update/replace options. Generates comprehensive technical PRDs optimized for task breakdown, validates with 13 automated checks, and optionally executes tasks autonomously with datetime tracking and rollback support. Use when user requests "PRD", "product requirements", or mentions task-driven development. Default: PRD generation + handoff to TaskMaster. Optional: autonomous execution with 4 modes.
Generate high-quality synthetic datasets using statistical samplers and Claude's native LLM capabilities. Use when users ask to create synthetic data, generate datasets, create fake/mock data, generate test data, training data, or any data generation task. Supports CSV, JSON, JSONL, Parquet output. Adapted from NVIDIA NeMo DataDesigner (Apache 2.0).
Memory preservation for Claude Code sessions. Use when approaching token limits, needing to /reset or /compact, switching between complex tasks, or preserving critical session state before context loss. Creates comprehensive memory dumps at /tmp/total-recall containing current state, decisions, artifacts, and next steps for seamless context restoration.
Use this skill when the user needs to analyze, clean, or prepare datasets. Helps with listing columns, detecting data types (text, categorical, ordinal, numeric), identifying data quality issues, and cleaning values that don't fit expected patterns. Invoke when users mention data cleaning, data quality, column analysis, type detection, or preparing datasets.
Detects and corrects Korean AI writing patterns to transform text into natural human writing. Based on scientific linguistic research (KatFishNet paper with 94.88% AUC accuracy). Analyzes 19 patterns including comma overuse, spacing rigidity, POS diversity, AI vocabulary overuse, and structural monotony. Use when humanizing Korean text from ChatGPT/Claude/Gemini or removing AI traces from Korean LLM output.
Interface with Zotero's MCP server to search and retrieve bibliographic data using advanced semantic search and multi-strategy approaches. Designed for output as a plain markdown formatted outline, suitable for pasting into Logseq. Also offers side-by-side translation of Chinese titles and abstracts for improved English language search within Logseq. Context-aware - uses agents in Claude Code, batched searches in Claude Desktop.
2. 算法 链表翻转 异或取数组中的不同数
When working with JSON data in LLM prompts (especially large arrays or tabular data), consider the token-efficient TOON (Token-Oriented Object Notation) format which reduces tokens by 30-70% while maintaining lossless JSON representation and structural validation. Use for reading/writing .toon files, converting JSON↔TOON, or optimizing structured data for LLM consumption with guardrails like [N] counts and {field} headers.
Use this skill when users want to generate images using OpenAI's image generation API (DALL-E or gpt-image-1), or extract text from images using OCR. Invoke when users request AI-generated images, artwork, logos, illustrations, visual content from text prompts, or need to extract text/data from images.
Domain registration and management via Namecheap API.
**Skills.sh** 是由 Vercel 开发的开放式 AI Agent 技能生态系统平台，旨在为各种 AI 代理提供可复用的能力增强模块。
Sample-specific guidance for AI agents.
Instructions for AI code agents (OpenAI Codex, Claude Code, etc.) working on this codebase.
GWAS result visualization scripts.
**Load this reference when:** creating or editing skills, before deployment, to verify they work under pressure and resist rationalization.
Main backend. Exposes all business logic via REST. Producer only (never consumes from RabbitMQ).
**IMPORTANT**: This project uses **trx** for ALL issue tracking. Do NOT use markdown TODOs, task lists, or other tracking methods.
This file gives AI coding agents the background needed to work on this codebase
> Parent rules: [`/workspace/backend/agents.md`](../agents.md)
We only care about the ACP backend and the code that compiles into the nori bin. We do not care about the default codex backend or the code that compiles into the codex bin. Make sure all changes and responses are aligned to this critical fact. For example, if I ask 'add notifications to the cli', y
Parallel agent orchestration using git worktrees for isolated branch work. Use when spawning multiple agents to work on separate Linear issues simultaneously. Prevents branch conflicts, dirty tree cross-contamination, and commit pollution.
This guide shows you how to create specialist agents for any domain. No subclassing, no boilerplate — just `Agent(name=..., system_prompt=..., tools=..., tool_map=...)`.
Analytics & Agents