🎯
Skills
Loading...
Showing 30 of 146048 results
A domain-specific skill from the Everything Claude Code performance system for energy procurement workflows, part of the operational domain skills collection within a comprehensive AI agent harness framework supporting multiple industry verticals.
Patterns for building MCP servers with the Node/TypeScript SDK, covering tool and resource registration, Zod validation, stdio vs Streamable HTTP transports, and prompt templates for AI assistant integration.
A UI/UX design intelligence skill for Claude Code covering planning, building, and reviewing UI code with 50+ styles, 21 color palettes, and accessibility-first principles.
A Claude Skills library for SEO and Generative Engine Optimization (GEO), organized around a Research → Build → Optimize → Monitor methodology framework.
Comprehensive Claude Code plugin system with 112 specialized AI agents, 16 workflow orchestrators, and 146 agent skills for production development.
A Claude Skills library for SEO and Generative Engine Optimization (GEO), organized around a Research → Build → Optimize → Monitor methodology framework.
Codified expertise for managing carrier portfolios including freight rate negotiation, RFP processes, carrier scorecarding, routing guide construction, and quarterly business reviews across truckload, LTL, intermodal, and brokerage.
Unified media generation via the fal.ai MCP — image (Nano Banana 2 and Pro), video (Seedance 1.0 Pro, Kling Video v3 Pro, Veo 3), text-to-speech (CSM-1B), and video-to-audio (ThinkSound) — exposing `search`, `find`, `generate`, `result`, `status`, `cancel`, `estimate_cost`, `models`, and `upload` tools.
Prepares, audits, and revises Nature-ready Data Availability statements, data repository plans, dataset citations, and FAIR metadata checklists for manuscripts. Supports Chinese-to-English translation for Chinese-speaking authors preparing Nature-family submissions.
Quick-reference cheat sheet for AI/ML CTF challenges covering model weight perturbation negation, model inversion, encoder collisions, LoRA adapter merging/exploitation, model extraction and membership inference, adversarial examples (FGSM/PGD/C&W), adversarial patches, data poisoning, and LLM attacks (prompt injection, jailbreaking, token smuggling, tool-use exploitation). Bundles ready-to-run inspection commands for `.pt`/`safetensors`/HuggingFace/LoRA models and points to detail files (`model-attacks.md`, `adversarial-ml.md`, `llm-attacks.md`) for each technique.
A curated collection of awesome LLM apps built with RAG, AI agents, multi-agent teams, MCP, and voice agents, using models from OpenAI, Anthropic, Google, xAI, and open-source providers.
Multi-platform content distribution across X, LinkedIn, Threads, and Bluesky that preserves the author's voice (optionally sourced from the `brand-voice` skill) and adapts a single source idea per platform constraint — while banning duplicate copy, fake founder-reflection posts, and filler CTAs like "What do you think?".
A comprehensive harness-native operator system for agentic AI work, providing production-ready skills, hooks, rules, MCP configurations, memory optimization, security scanning, and continuous learning across Claude Code, Codex, Cursor, and other AI agent harnesses.
Exposes React DevTools and the Next.js dev overlay as shell commands that AI agents can parse and act on. Agents can run commands like snapshot, click, and tree inspection against a long-lived browser daemon, enabling automated debugging of component trees, props, hooks, PPR shells, errors, network, and accessibility.
Comprehensive patterns for database access with JetBrains Exposed ORM in Kotlin, covering DSL queries, DAO entities, transactions, HikariCP connection pooling, Flyway migrations, and the repository pattern.
Comprehensive Playwright testing guides covering 70+ topics including E2E, API, component, visual, accessibility, and security testing, plus CLI automation with TypeScript and JavaScript examples.
Skill for interacting with ClawDirect, a directory of social web experiences for AI agents. Browse the directory, like entries, or add new agent-facing sites using ATXP authentication and MCP tool calls.
Lightweight CLI for running reproducible head-to-head comparisons of coding agents (Claude Code, Aider, Codex, etc.) on YAML-defined tasks, measuring pass rate, cost, time, and consistency. Use it to make data-backed agent selection decisions instead of relying on vibes.
Automates browser interactions via terminal using Playwright CLI, enabling web navigation, form filling, screenshots, and UI debugging.
Provides modern Perl 5.36+ idioms and best practices including subroutine signatures, strict pragmas, context sensitivity, and error handling patterns for building robust, maintainable Perl applications.
A comprehensive harness-native operator system for agentic AI work, providing production-ready skills, hooks, rules, MCP configurations, memory optimization, security scanning, and continuous learning across Claude Code, Codex, Cursor, and other AI agent harnesses.
A skill that enables conversion from PDF files to editable Word documents using the pdf2docx Python library, preserving layout, tables, images, and text formatting. Supports page-specific conversion, encrypted PDFs, and advanced layout tuning options.
Reviews code comprehensively, providing actionable feedback on quality, security, performance, and maintainability
Multi-agent orchestration using dmux (a tmux pane manager for AI agent harnesses) to run Claude Code, Codex, OpenCode, Cline, Gemini, and Qwen sessions in parallel and merge their output — with patterns for research+implement, multi-file features, test/fix loops, cross-harness tasks, and parallel code review.
Extracts text from images, scanned PDFs, and photographs using OCR with support for 100+ languages. Features table detection to CSV/JSON, structured output in Markdown/JSON/HTML, batch processing, confidence scoring, and quality assessment for OCR results.