Skills

A skill from the Awesome GitHub Copilot collection that provides Copilot Spaces functionality. Part of a community-curated repository of custom agents, instructions, skills, hooks, workflows, and plugins to enhance the GitHub Copilot experience.

An official Starchild skill focused on coding assistance, providing AI agents with structured guidance for software development tasks within the Starchild agent ecosystem.

A web fiction writing skill that performs multi-perspective story review using 4-agent adversarial review with scoring standards from platforms like Tomato Novel, Qidian, and Zhihu.

Transforms data into visual charts by intelligently selecting from 26 chart types including time series, comparisons, maps, hierarchies, and specialized visualizations. Handles chart selection, parameter extraction, and image generation using JavaScript scripts with Node.js 18+.

Agent skill for viewing DeFi positions and holdings overview across protocols and chains via the OKX OnchainOS platform.

Expert guide for interpreting and fixing n8n validation errors, covering error severity levels (errors, warnings, suggestions), false positives, operator structure issues, and the iterative validation loop process.

Systematically refines UI design by applying principles of hierarchy, spacing, and visual clarity to create more intuitive and professional interfaces.

A curated collection of awesome LLM applications with skills for building AI-powered apps, covering RAG, agents, and various use cases.

Three-mode design system tool for Claude Code: **Generate** (scan CSS/Tailwind/styled-components, propose design tokens, emit `DESIGN.md` + `design-tokens.json` + interactive HTML preview), **Audit** (score UI 0-10 across colour, typography, spacing, components, dark mode, a11y, etc. with file:line fixes), and **AI Slop Detection** (catch generic gradients, glass morphism, purple-blue defaults, gratuitous animation). Use to start a new design system, audit existing styling, or review styling-touching PRs.

Fetches daily stock data for specified tickers, calculates multiple technical indicators, and generates a CSV with buy/sell recommendations and pattern analysis.

from lijigang/ljg-skills

A comprehensive performance optimization system for AI agent harnesses, providing production-ready skills, hooks, rules, MCP configurations, and development patterns evolved over months of intensive daily use across Claude Code, Codex, Cursor, and other AI coding tools.

An official Starchild skill for managing wallet policies in AI agent interactions. Part of the Starchild official skills collection, installable via npx skills and compatible with the Starchild agent framework.

Agent skill for DeFi product discovery, deposits, withdrawals, and reward claiming across protocols like Aave, Lido, PancakeSwap, Kamino, and NAVI via OKX OnchainOS.

OpenCLI's adapter-creation skill — runs the full browser exploration workflow (`explore` → `synthesize` → `generate`), the 5-tier authentication strategy decision tree, and debugging guide so AI agents can build new OpenCLI adapters for any website.

A collection of 65 Claude Code skills and 9 workflows with progressive disclosure, covering full-stack development including context engineering and Atlassian integration.

A skill from ECC (Everything Claude Code) that distills and optimizes agent rules for agentic workflows. Part of the harness-native operator system featuring skills, instincts, memory optimization, and security scanning across multiple AI agent harnesses.

Evolves AI agents by autonomously analyzing runtime history, identifying improvements, and applying protocol-constrained code updates.

A Trail of Bits plugin that performs systematic false positive verification for security bug analysis, using mandatory gate reviews to ensure only valid security findings are reported.

Official Figma skill that generates code from selected Figma frames, providing design information and context to AI agents via the Figma MCP server.

Transforms AI-generated text into natural, human-sounding writing while preserving meaning and intent.

Runs four-phase automated browser QA on a deployed URL via a browser MCP (claude-in-chrome, Playwright, or Puppeteer): smoke test (console errors, network, Core Web Vitals), interaction test (nav links, form valid/invalid states, auth flow, critical journeys), visual regression at 375/768/1440px with dark mode, and accessibility (axe-core, keyboard nav, screen reader landmarks). Outputs a structured QA report with a SHIP/SHIP WITH FIXES/BLOCK verdict.

Agentic actions auditor skill from Trail of Bits for auditing AI agent actions, ensuring safety and detecting potentially harmful behaviors.

A curated collection of awesome LLM applications with skills for building AI-powered apps, covering RAG, agents, and various use cases.

A skill from the Awesome GitHub Copilot collection that integrates FlowStudio and Power Automate as an MCP server for Copilot. Part of a community-curated repository of agents, skills, workflows, and plugins for enhancing GitHub Copilot.

A curated collection of awesome LLM applications with skills for building AI-powered apps, covering RAG, agents, and various use cases.

An official Notion agent skill that enables installing and using the Notion CLI (ntn) for workers, public API requests, and file uploads. Part of the makenotion/skills collection built for use with the skills CLI.

A persistent memory compression system built for Claude Code that enables context retention across sessions. Provides intelligent memory management with compression, allowing Claude Code to maintain knowledge of projects and conversations beyond the default context window.

Provides expert-level FastAPI development guidance and patterns, from a collection of 65 skills and 9 workflows built for full-stack developers.

Best practices skill for Node.js development by Matteo Collina. Part of a curated collection of AI-assisted development skills that includes expertise in Fastify, TypeScript, OAuth, Git/GitHub workflows, and more.