Latest Entries
π
Facilitator Guide: Who Did the Learning?
π
Who Did the Learning? An AI Ethics Policy Lab
Stanford CS329A β Self-Improving AI Agents: Public Lecture Learning Path
Engineering Agent Improvement Loops - From Self-Critique to Verified Revision
Stanford CS329A Part 9 β Future Research Areas
Stanford CS329A Part 8 β Agentic Evaluations and Long-Horizon Tasks
Stanford CS329A Part 7 β Self-Improvement and Deep Research Agents
Stanford CS329A Part 6 β Train-Time Scaling and Scaling RL
Stanford CS329A Part 5 β Planning and Multi-Step Reasoning
Stanford CS329A Part 4 β Learning from Feedback with Tools and Code
Popular
Harness Engineering β The Real Bottleneck Isn't the Model
Karpathy Skills β Four Rules That Fix LLM Coding's Worst Habits
Cross-Model Code Review β Why Claude Can't Catch Its Own Bugs
AI-Assisted Research Workflow: Formulate β Find β Judge β Verify β Execute β Monitor β Record
Building a Personal Knowledge Base β The LearnAI Workflow Guide
Karpathy's LLM Knowledge Bases β Building a Personal Wiki with AI
Socratic Prompting β Ask Questions, Don't Give Instructions
7 Framework Prompts That Turn Claude into a Thinking Partner
OpenMAIC: Tsinghua's Multi-Agent AI Classroom
Codex + Claude Code for Research β A Practical Tutorial
TensorTonic β Learn Machine Learning by Implementing 200+ Algorithms from Scratch
Using /goal for Wiki Management β Spec-Driven Autonomous Wiki Sessions
Claude Code Engineering
Harness / Loop / Graph Engineering β Environment, Feedback, Flow
claude-tap β Local Trace Viewer for AI Coding Agents
Claude Code Token Guard β Audit Unattended Token Burn
project-spec-interviewer-skill β Interactive Terminal Interview That Writes Your spec.md
Using /goal for Wiki Management β Spec-Driven Autonomous Wiki Sessions
Codex-Maxxing β Jason Liu's Power User Workflow for OpenAI's Codex Agent
AI Coding Reliability β Implementation Notes Habit + 12 Engineering Rules
/goal δ½Ώη¨ζε β The Visual Playbook for Claude Code's Persistent Goal Mechanism
Beyond /goal β The Orchestrator + Headless Pattern for Long-Running Claude Sessions
Agents Need Control Flow β Brian's Case for Code Over Prompts
The Unreasonable Effectiveness of HTML β Thariq's Case for Output Format Engineering
Building /review-wiki β A Batch AI Quality Pipeline from Scratch
Karpathy Skills β Four Rules That Fix LLM Coding's Worst Habits
Claude Code from Source β The Architecture Book That Treats Claude Code Like an OS
Don't Make Too Many Decisions for AI β Anthropic's 3 Core Development Philosophies
Claude Code Source Analysis β What Makes It Work & How to Actually Learn From It
CC Unpacked β Visual Guide to Claude Code's Internals
Claude Code Cheat Sheet, Everything-Claude-Code & Claude How-To β Complete Reference Kit
The Five Levels of Claude Code β From Prompting to Orchestration
Harness Engineering β The Real Bottleneck Isn't the Model
Claude Code Tips & Context Engineering β From 45 Tips to Six-Layer Architecture
Claude Code Context Management & CLAUDE.md β From Pitfalls to Infrastructure
Claude Code: Isolate Heavy Tasks with context: fork
Claude Code: Agent Teams vs Subagents
Claude Code Workflows
Claude Drafts, Codex Gates β An Interleaved Two-Model Review Loop for Hard Work
gnhf β Good Night, Have Fun: Run AI Agents While You Sleep
SpecOps β Spec-Driven Development with AI Coding Agents
Codex + Claude Code for Research β A Practical Tutorial
Cross-Model Code Review β Why Claude Can't Catch Its Own Bugs
Claude Code as Research Infrastructure β From Chatbot to AI Research Team
Claude Code /loop: Scheduled Prompts on Autopilot
Obsidian CLI + Claude Code: Your Second Brain as Context
Claude Code Git Worktree: Parallel Agents Without Conflicts
Agent Setup & Migration
Skills & Plugins
From /grill-me to Review β A Slide-Based AI Development Workflow
Codex Skill Watchlist β Media Generation and UI Quality
π§
leader β Turn Vague Ideas Into /goal-Ready Agent Task Briefs
SkillsMP β Map the Agent Skills Ecosystem Before You Install
Ponytail β The Anti-Overengineering Skill for Coding Agents
OpenWorker β Local-First Desktop Agents That Deliver Finished Work
/last30days β Recent-Signal Research Skill for Agents
Graphify β Multimodal Tool Memory for AI Coding Agents
book-to-skill β Turn Technical Books Into Agent Skills
Cybersecurity Skills for AI Agents β A Structured Security Skill Library
Personal AI Skill Cheat Sheet β When to Use Each Skill
notebooklm-py β Unofficial Python API for Google NotebookLM Automation
MATLAB MCP β Connect Claude Code to Your Local MATLAB Environment
ImageLens β Chrome Extension That Extracts AI-Editable Prompts from Any Web Image
html-anything β Claude Outputs Any Document Type as a Self-Contained HTML File, Zero Config
Paper-Code Joint Analysis & Contract-Driven Skill Design
codegraph β Local Code Knowledge Graph for AI Coding Agents
grill-me β When AI Interviews You Before Writing Code
How Anthropic Uses Skills β Thariq's 9-Category Framework & the Gotchas Pattern
open-slide β The Slide Framework Built for AI Coding Agents
Matt Pocock's Skills β Claude Code for Real Engineers
Browser-Use β Make Any Website Accessible to AI Agents
Yao Bayesian Decision Skill β Structured Decision-Making for Claude Code
Godogen β Prompt-to-Game Pipeline for Godot, Bevy, and Babylon.js
Caveman β Token Compression for AI Coding Agents
Agents with Taste β Encoding Design Judgment as Skill Files
Addy Osmani's agent-skills β Senior Engineering Practices as SKILL.md Files
kepano/obsidian-skills β Agent Skills That Let AI Edit Your Vault
HTML PPT Studio β AI-Powered Presentation Skill for Claude Code
Obsidian Web Clipper β AI-Powered Web Capture That Actually Organizes Itself
Make Slides: AI-Powered Interactive Teaching Slides
ui.sh β Tailwind Creator's Design Toolkit for AI Coding Agents
Taste Skill β Teaching AI Agents Design Taste for Frontend Code
Markdown Viewer Skills β 9,500 Icons and 14 Diagram Types for AI Agents
Fireworks Tech Graph β Natural Language to Architecture Diagrams in Claude Code
Code Review Graph β Turn Your Codebase Into a Knowledge Graph, Cut Tokens 8x
Paper2Code: Turn ArXiv Papers into Citation-Anchored Code
AI Website Cloner β Reverse-Engineer Any Site Into Clean Next.js Code
Supermemory β The Memory API That Makes AI Actually Remember You
Pretext & Refero β Tools to Fix AI's Frontend Problem
oh-my-claudecode β Multi-AI Orchestration Plugin for Claude Code
Unsloth Studio β Train and Run LLMs Locally with 70% Less Memory
Understand Anything β Turn Codebases Into Interactive Knowledge Graphs
PUA Skill β Force Your AI to Stop Being Lazy and Actually Debug
Prompt Master β Write Accurate Prompts for Any AI Tool, Zero Waste
Posterskill β AI-Generated Academic Conference Posters from Your Paper
Gstack β Garry Tan's AI Software Factory for Claude Code
alphaXiv MCP β Semantic ArXiv Search Directly in Claude Code
mdpdf: Markdown to PDF with Claude Code
Non-Coding Skills for Claude Code β Automating Business & Life
Build Interactive Diagram Tools with Claude
Ralph: Autonomous Development Loop for Claude Code
Beads: Graph-Based Memory for AI Coding Agents
AI for Research
π
You Point, I Learn β Medical Segmentation Models That Adapt from User Clicks
ResearchArena β Why Agent-Written Papers Still Need Artifact-Aware Review
Research Skills Starter Pack β Install and Use Academic AI Skills Without the Hype
GPT-Red β Automated Red Teaming Through Self-Play
CARE β Evidence-Grounded Agentic Medical Reasoning
AI in Science β More Individual Impact, Narrower Collective Focus
π€
Quality-First Research Partnership: A Claude + Codex Working Agreement
PaperSpine β Motivation-Driven Paper Writing Skill Suite for Codex and Claude Code
Nature Skills β Academic Writing and Research Skill Bundle for Codex and Claude Code
Awesome-Auto-Research-Tools β A Curated Map of Automated-Science Projects
academic-research-skills β Imbad0202's 4-Skill Claude Code Pipeline for Academic Research
Towards a Medical AI Scientist β Full Auto Clinical Research from Idea to Paper
Dexter β Autonomous AI Agent for Deep Financial Research
GBrain β Garry Tan's Persistent Agent Memory System
AI Research Tools Landscape: FARS vs AutoResearch vs ARIS vs Elicit
AI-Assisted Research Workflow: Formulate β Find β Judge β Verify β Execute β Monitor β Record
Building a Research KB β Zotero + Obsidian + Claude Code
Anthropic's Automated Alignment Researchers β Claude Beats Humans 4x at AI Safety Research
MetaGPT β The AI Software Company That Runs on One Prompt
Meta Harness β The Agent That Optimizes Its Own Scaffolding (Stanford/MIT)
Hermes Agent β The Self-Improving AI Agent That Learns From Experience
Anthropic Managed Agents β Decoupling the Brain from the Hands
AI Quant Tools β Kronos and Midas for Financial Market Research
How AI Agents Cheat Benchmarks β Berkeley's Wake-Up Call
TurboQuant β Former Google Engineer Reverse-Engineers Google's Algorithm in 36 Hours with Claude
Karpathy's LLM Knowledge Bases β Building a Personal Wiki with AI
AI Agents for Academic Research & Writing β From KatmerCode to the Nature Playbook
Feynman AI Research Agent & Claude as Lab Partner β Promise and Pitfalls
litellm Supply Chain Attack: How a Poisoned PyPI Package Nearly Compromised the AI Ecosystem
Claude-Prism β Local-First Academic Writing Workspace with AI
Autoresearch: 100 Autonomous ML Experiments Overnight
AI for Teaching
π
Facilitator Guide: Who Did the Learning?
π
Who Did the Learning? An AI Ethics Policy Lab
π
Build a Verifiable Agent Loop - Six-Question Learning Lab
AI Ethics in College: Stop Asking "Did Students Use AI?" Ask Whether They Learned
AI Ethics β From Principles to Power Structures
CS329A Agent-System Literacy β The Next Layer of AI Education
AI Infrastructure Literacy β The Missing Bridge to Agentic Building
AI Education Search-Space Design β Make Students Wider Before Faster
π
LearnVector β Andrew Ng's AI-Native Learning Bet and the Cognitive-Offloading Problem
U.S. AI in Education Priority β What the 2026 Federal Register Notice Means
AI+Education Career Path β Learning Science, Data, and Teaching Tools
Build a Free Online Survey with GitHub Pages + Google Sheets
Anti-AI Exam Designer β A Claude Code Skill for AI-Resistant Exams
Independent Thinking in the Age of AI β Visual PKM and 4D Knowledge
What Researchers Should (and Shouldn't) Use LLMs For
Socratic Prompting β Ask Questions, Don't Give Instructions
claude.nagdy.me β Learn Claude Code by Doing, Not Reading
OpenMAIC: Tsinghua's Multi-Agent AI Classroom
AI Brain Fry β Why Deeper AI Use Makes You Less Productive, Not More
AI Mastery Games β Teaching AI Literacy Through Interactive Games
AI in Education β Teacher's Factory, Not Student's Cheat Tool
MIT Professor's NotebookLM Grading System β 47 Essays in 12 Minutes
Frustration Shifts Upward β How AI Coding Changes What's Hard
Learning in the AI Era: Amplify Your Thinking, Don't Outsource It
AI Fluency Index: Why Your Best Prompts Might Lead to Your Worst Work
Create Custom Course Materials with Claude
Turn Claude Code into Claude Teacher
Learning Resources
Stanford CS329A β Self-Improving AI Agents: Public Lecture Learning Path
Stanford CS329A Part 9 β Future Research Areas
Stanford CS329A Part 8 β Agentic Evaluations and Long-Horizon Tasks
Stanford CS329A Part 7 β Self-Improvement and Deep Research Agents
Stanford CS329A Part 6 β Train-Time Scaling and Scaling RL
Stanford CS329A Part 5 β Planning and Multi-Step Reasoning
Stanford CS329A Part 4 β Learning from Feedback with Tools and Code
Stanford CS329A Part 3 β Robust Verification
Stanford CS329A Part 1 β From Scaling to Self-Improving Agents
Stanford CS329A Part 2 β Test-Time Compute Scaling
π§
LangGraph Stateful Business Workflows β Three Recipes from arXiv 2607.19297
DeepLearning.AI AI for Medicine β Practical Medical ML Course Path for Students
Graph Engineering β From Prompting AI to Managing AI Workflows
π
3Blue1Brown Neural Networks β Visual Foundations for ML, LLMs, and Diffusion
Socratopia AI Science I β Learning Neural Networks Through Socratic Dialogue
Project N.O.M.A.D. β Offline Knowledge and AI Education Server
CMU 11-768 AI Agents β A Course Map for Agent Engineering
AI Agent Book β Agent = Model + Context + Tools
Agent AI Survey β Multimodal and Embodied Agents Beyond Chatbots
Start Here β AI Agents & Claude Code for Beginners
All Agentic Architectures β 17+ Runnable Jupyter Notebook Implementations
12-Factor Agents β Engineering Principles for Production AI
Vibe Coding ζ°ζζε β The Open-Source Primer for Non-Technical AI-Assisted Development
How to Train Your GPT β From-Scratch LLM Textbook with 12 Chapters and 28 Explainers
ML HW-SW Codesign / Efficient AI β 13 Free Lecture Pages on ML-Hardware-Software Co-Design
MIT 6.5940 β Song Han's TinyML & Efficient Deep Learning Course
Codex Orange Book β θ±ε's Bilingual Codex Reference
What is Agentic Engineering? A Teaching Primer
Claude Code 101 β Anthropic's Official Onboarding Course
Case Study: Building a 3D Specimen Viewer from Scratch β Every Prompt I Used, in Order
Building CAS-Style 3D Knowledge Visualizations β From a PDF to a Deployed Specimen Viewer
AI Agent Primer β The Vocabulary Ladder and 18-Step Workflow
Stanford CS336 β Language Modeling from Scratch: The Complete Free LLM Curriculum
AI Engineering from Scratch β Rohit Ghumare's 416-Lesson Math-to-MCP Curriculum
7 Agent Architectures β From Single Agent to Enterprise Graph Workflows
TimesFM 2.5 β Google's Zero-Shot Time Series Forecasting
Mathematical Foundations of Reinforcement Learning β Free Textbook by Shiyu Zhao
Agentic AI Engineer Roadmap 2026 β Eight Pillars from Prompt to Production
MuJing (εΉε’) β Learn English Vocabulary Through Movies and Real Context
Building a Personal Knowledge Base β The LearnAI Workflow Guide
Karpathy's MicroGPT β A Complete GPT in 200 Lines of Pure Python
A Lawyer Beat 500 Developers β Problem Definition Is the New Coding
TensorTonic β Learn Machine Learning by Implementing 200+ Algorithms from Scratch
LLM Architecture Gallery β Visual Reference for Every Major Model
Five Questions for Critical Paper Reading β The Cambridge Method with Claude
Five Core Learning Prompts β From Memorization to Mastery
Claude Certified Architect β Anthropic's First Official AI Certification
Anthropic Academy β 13 Free AI Courses with Certificates
Pull Requests (PR): What They Are and How to Use Them in Claude Code
Prompting & Writing
π
Editing AI-Sounding Writing: Which Skill Should You Use?
Killing AI Slop: avoid-ai-writing + stop-slop
Anti-Sycophancy Prompt β Stop AI from Flattering You, Get Accurate Answers
7 Framework Prompts That Turn Claude into a Thinking Partner
Three Hidden Instructions That Stop Claude from Hallucinating
Creative & Media
Slide Image to Editable PPTX β Tested Agent Workflow for Rebuilding Slide Screenshots
html-video β Video-as-Code for Agentic Media Workflows
video-use β Editing Video by Reading Transcripts, Not Dumping Frames
Teaching Videos with Manim + Remotion β Two Engines for Code-Driven Explainers
Remotion Case Study β Animating "Adding Elements to an Array"
baoyu-comic β Turn Any Knowledge Into a Manga
AI Slide Generation with Claude Code β Tool Comparison & Guide
image-blaster β Turn a Single Photo into a 3D Environment + Audio + Mesh in One Pipeline
Awesome GPT Image 2 Prompt Library β 7,000+ Prompts with Live Preview for 16 Scenarios
GPT Image 2 ζ°΄ε’¨ι£ Slide Prompt β Structured Template for Ink-Wash Style Slides
InfiniteTalk β Unlimited-Length AI Talking Videos from a Single Photo
Toonflow β The AI Factory That Turns Novels Into Short Dramas
WebNovel Writer β How AI Writes 2M+ Word Novels Without Forgetting
Industry & Trends
Why I Don't Vibe Code β Jacob Harr's Defense of Friction and Essential Complexity
Forward Deployed Engineer β AIζΆδ»£ηζ°ε²δ½: On-Site Coder, Architect, and Consultant in One
10 Lessons for Agentic Coding β What Should We Do When Code Is Cheap?
Career-Ops β The AI Job Search System That Landed a Head of Applied AI Role