hooks — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited hooks (Hook) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
<div align="center">
██╗ ██╗ ██╗ ██████╗ ███████╗ ██████╗ ██████╗ ██████╗ ██╗ ███╗ ██╗ ██████╗
██║ ██║ ██║ ██╔══██╗ ██╔════╝ ██╔════╝ ██╔═══██╗ ██╔══██╗ ██║ ████╗ ██║ ██╔════╝
██║ ██║ ██║ ██████╔╝ █████╗ ██║ ██║ ██║ ██║ ██║ ██║ ██╔██╗ ██║ ██║ ███╗
╚██╗ ██╔╝ ██║ ██╔══██╗ ██╔══╝ ██║ ██║ ██║ ██║ ██║ ██║ ██║╚██╗██║ ██║ ██║
╚████╔╝ ██║ ██████╔╝ ███████╗ ╚██████╗ ╚██████╔╝ ██████╔╝ ██║ ██║ ╚████║ ╚██████╔╝
╚═══╝ ╚═╝ ╚═════╝ ╚══════╝ ╚═════╝ ╚═════╝ ╚═════╝ ╚═╝ ╚═╝ ╚═══╝ ╚═════╝</div>
The most complete collection of battle-tested AI-assisted development resources — for Product Managers, Designers, and Developers who want to ship real products with AI.
What's inside: 247 agent skills (Cursor, Claude Code & Codex) · 8 slash commands · 21 coding rules · 123 Jupyter notebooks · 46 research papers (PDF, 9 themes) · 14 industry reports · 21 n8n workflow templates · 14 system prompts · 36 OpenClaw agents · 5,400+ OpenClaw skills indexed · 58 curated GitHub projects.
Whether you're a PM who wants to prototype faster, a Designer who wants to understand the code your AI is generating, or a Developer looking for the sharpest rules to ship with — this repo is built to be copied, forked, and used the same day.
Pick your path and start in under 5 minutes:
code-review, final-review, git-commit, security-audit)| Area | Entry point |
|---|---|
| Cursor, Claude & Codex | cursor-claude-codex/ · cursor-claude-codex/README.md · codex-profiles · Upstream catalog |
| Prompts | prompt-engineering/ · prompt-engineering/README.md |
| Learning | learning/ · learning/README.md |
| Reports | reports/ · reports/README.md |
| OpenClaw | openclaw/ · openclaw/README.md |
| Projects to watch | nice-projects/ · nice-projects/README.md |
| Research | research/ · research/README.md |
| Papers | papers/ · papers/README.md |
| n8n | n8n-templates/ |
| Topic | Location |
|---|---|
| Skills (brainstorming, plans, TDD, debugging, git worktrees, Vercel UI/React guidelines, etc.) | cursor-claude-codex/skills/ · cursor-claude-codex/skills/README.md |
| Tools (Codex multi-account CLI) | cursor-claude-codex/tools/ · codex-profiles |
| Slash commands — Cursor only (code-review, final-review, git-commit, etc.) | cursor-claude-codex/commands/ · cursor-claude-codex/commands/README.md |
| Product management (PRD, epics, tasks) | cursor-claude-codex/product-management/ · README |
| Coding rules (Python, TypeScript, FastAPI, Tailwind, …) | cursor-claude-codex/coding/ |
| Best practices (Karpathy guidelines, MCP, hooks, accessibility, …) | cursor-claude-codex/best-practices/ · karpathy-guidelines.md |
| Security | cursor-claude-codex/security/ |
| References (agentic patterns, …) | cursor-claude-codex/references/ · cursor-claude-codex/references/README.md |
Battle-tested prompts for Cursor, Claude, Grok, Kimi, n8n, Lovable, v0, and more — see prompt-engineering/README.md and prompt-engineering/prompts/.
Three freely-available textbooks that ground the notebooks and skills in this repo: Understanding Deep Learning (Prince), Mathematics for Computer Science (MIT 6.042J), and Algorithms for Decision Making (Stanford). See learning/README.md for what each is best for.
14 industry reports from McKinsey, Deloitte, KPMG, OpenAI, Anthropic, Air Street Capital, and others — useful for pitch decks, business cases, and agent metrics. See reports/README.md for a themed index.
36 agent projects catalogued (OpenClaw + 35 derivatives) and 5,400+ community skills indexed in 30 categories (local snapshots from machinae/awesome-claws and VoltAgent/awesome-openclaw-skills). Details: openclaw/README.md, openclaw/skills/README.md.
58 hand-picked open-source repos — tools, AI/ML, agent skills, and the upstream sources behind vendored hub content. See nice-projects/README.md and the full catalog at cursor-claude-codex/references/upstream-repos-catalog.md.
Workflow templates (AI assistants, messaging, sheets, scraping, etc.).
Educational notebooks and autonomous research setups. Full catalog and source links: research/README.md.
| Track | Folder | Notes |
|---|---|---|
| Reasoning LLM (book code) | research/reasoning-from-scratch/ | Build a Reasoning Model (From Scratch) |
| Minimal ChatGPT-style stack | research/nanochat/ | Karpathy nanochat |
| Autonomous nanochat experiments | research/autoresearch/ | README, Karpathy autoresearch |
| NLP with Transformers book | research/nlp-with-transformers/ | Classification, NER, generation, QA, … |
| Neural nets from scratch | research/nn-zero-to-hero/ | Karpathy course notebooks |
| Short ML examples | research/ML-Notebooks/ | Notebooks under notebooks/ |
| Understanding Deep Learning | research/understanding-deep-learning/ | Notebook list (Prince / UDL) |
Other items (e.g. DeepSeek OCR) are documented in research/README.md when present.
46 research papers (PDFs) in 9 thematic subfolders — from classic deep learning (AlexNet, DQN, Word2Vec) through the foundation-model era (Transformers, BERT, GPT-1/2/3, scaling laws, Chinchilla, RLHF, diffusion) to contemporary agent, harness, reliability, and ethics research. Full index: papers/README.md.
| Folder | Focus | PDFs |
|---|---|---|
| early-deep-learning/ | CNNs, RL, word embeddings (2012–2013) | 3 |
| foundation-models/ | Transformers, BERT, GPT, scaling laws | 7 |
| alignment-and-post-training/ | RLHF / InstructGPT | 1 |
| generative-models/ | Diffusion models | 1 |
| agents-and-engineering/ | Agents, harnesses, code evaluation | 13 |
| reliability-and-reasoning/ | Hallucinations, reasoning, memory | 6 |
| models-and-training/ | World models, fine-tuning, DeepSeek | 4 |
| ethics-risks-and-society/ | Risks, work, autonomy | 7 |
| perspectives-and-futures/ | Long-term AI visions | 4 |
Includes 12 foundational PDFs added to the repo (early DL through alignment and diffusion). Code-LLM papers (AlphaCode, StarCoder, DeepSeek-Coder, …) are external links in papers/README.md.
Counts verified against the repo tree (2026-06):
| Resource | Count | Entry point |
|---|---|---|
| Agent skills (Cursor / Claude / Codex) | 247 | cursor-claude-codex/skills/README.md |
| Cursor slash commands | 8 | cursor-claude-codex/commands/ |
| Coding & stack rules | 21 | cursor-claude-codex/coding/ |
| Upstream sources integrated | 18 | cursor-claude-codex/README.md |
| OpenClaw agents catalogued | 36 | openclaw/README.md |
| OpenClaw skills indexed (snapshot) | 5,400+ | openclaw/skills/README.md |
| GitHub projects to watch | 58 | nice-projects/README.md |
| Jupyter notebooks | 123 | research/README.md |
| Research papers (PDF, 9 themes) | 46 | papers/README.md |
| Industry reports (PDF) | 14 | reports/README.md |
| n8n workflow templates | 21 | n8n-templates/ |
| System prompt snapshots | 14 | prompt-engineering/prompts/ |
This repository is maintained by Adrianno, a Staff Product Manager at Pipefy, diving into the magic behind LLMs.
You can find more about me on GitHub and LinkedIn. Feel free to connect with me, I'm always open to discussing AI, product management and building cool things together!
This isn't just another collection of AI tools. We focus on:
git checkout -b feature/amazing-feature)git push origin feature/amazing-feature)Full guidelines: CONTRIBUTING.md.
This project is licensed under the MIT License — see LICENSE.
Ready to level up? Start with cursor-claude-codex/README.md, openclaw/README.md, nice-projects/README.md, or prompt-engineering/README.md. The best way to learn is by doing.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.