My Python scripts to make high-quality figures for publications in top AI conferences and journals.
Light — 全流程科研技能包：28 个技能覆盖文献调研到投稿全流程，配套 9 个可核查知识库。适配主流 AI 编程客户端。
Claude Code / Codex skill: generate a lean, high-signal CLAUDE.md from scratch via repo scan + focused user interview.
Claude Code skill — generate cross-client HTML email with MJML. Outlook-safe, Gmail-optimized, WCAG 2.1 AA accessible.
A personal learning environment that helps you find your unknown unknowns by grilling you against the consensus research on a particular topic or question.
Improve scientific collaboration in AI-assisted research. Citation validation, claim verification, cross-file consistency.
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.
12 codex-grade PM skills (1,000–1,300 lines each) for senior PMs, founders, and AI agents. AGENTS.md, MCP server, plugin marketplaces.
ExoBrain CLI - atomic reasoning engine for agents
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
Community skills for Claude Code: token optimization, productivity workflows, and development best practices. All skills tested with TDD methodology (RED-GREEN-REFACTOR). Features rescue-tokens skill: 90% verbosity reduction, eliminates rate limits through 9 optimization patterns.
A modular collection of AI skills for academic research, writing, citation normalization, and experimental documentation (UA/EN).
🧠 Modular skills for autonomous AI agents. Production-ready Docker & Kubernetes tooling with built-in validators. Install once, use everywhere.
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.
AI-assisted development toolkit for GeneXus 18 — works with Claude Code, ChatGPT, Copilot and any GeneXus compiler
Skill to generate a LLMs.txt for your website
Human system for learning complex subjects based on superior intelligence agents
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."