My Python scripts to make high-quality figures for publications in top AI conferences and journals.
Claude Code skill — generate cross-client HTML email with MJML. Outlook-safe, Gmail-optimized, WCAG 2.1 AA accessible.
Improve scientific collaboration in AI-assisted research. Citation validation, claim verification, cross-file consistency.
A personal learning environment that helps you find your unknown unknowns by grilling you against the consensus research on a particular topic or question.
Searchable Markdown KB built for AI workflows. Hybrid search, typed relations, wiki links, graph views. Token-efficient CLI for agents, static publishing for humans.
A community-driven library of reusable AI agent skills for Claude Code, Cursor, Codex, Cline, and more.
Automated end-to-end testing for AI agent skills(agentskills.io). Launches Claude Code and Cursor as subprocesses, runs scenarios in real workspaces, and asserts what the model actually does.
A modular collection of AI skills for academic research, writing, citation normalization, and experimental documentation (UA/EN).
12 codex-grade PM skills (1,000–1,300 lines each) for senior PMs, founders, and AI agents. AGENTS.md, MCP server, plugin marketplaces.
A curated collection of AI coding skills for elite-level fullstack web/mobile engineering and MQL5 Expert Advisor trading systems — compatible with Claude Code, ChatGPT, Gemini, and other high-performing LLMs
🧠 Modular skills for autonomous AI agents. Production-ready Docker & Kubernetes tooling with built-in validators. Install once, use everywhere.
Skill to generate a LLMs.txt for your website
an agentic skills framework that equips any LLM coding agent (Cursor, Claude Code, Codex, OpenCode) with hardened markdown processing superpowers — auto wiki-linking, concept extraction, mermaid/LaTeX healing, web research, and knowledge graph construction.
Paste a mean message, pick a tier (soft/medium/heavy/trainwreck), get one clever sentence back. A free, open-source Claude Code skill.
Cairo and Starknet security skills for AI agents. 7 modules, 24 audits, 217 findings.
Claude SKILLs to imitate Amp's /handoff command
ADA is a lightweight, provider-agnostic framework for building AI agents with customizable skills, persistent memory, knowledge RAG, and personas. Designed for simplicity and extensibility, ADA allows you to create agents that learn, remember, and act in local environments.
LLM agent skills for software architecture analysis and review. This repository equips AI agents with reusable capabilities to evaluate system design, review architecture decisions, identify risks, analyze trade-offs, and recommend improvements for scalable, reliable, and maintainable systems.
A Claude Code plugin marketplace with skills for software development, project management, data research, and team workflows.
agent-skills
Add a description, image, and links to the llm-skills topic page so that developers can more easily learn about it.
To associate your repository with the llm-skills topic, visit your repo's landing page and select "manage topics."