Aloha ⚜ retweeted
SAVE THIS: 4 GitHub repos trending this week.
1. Ponytail (~165K stars)
Makes your coding agent think like "the laziest senior dev in the room." Before writing code, it checks if the code needs to exist at all. Its own benchmark with Opus 5.5: about half the code, 41% less time.
github.com/DietrichGebert/po…
2. Matt Pocock's skills (~294K stars)
Real engineering skills for agents: TDD, code review, bug diagnosis, specs, tickets. One-line install for Claude Code, Codex, Copilot and more.
github.com/mattpocock/skills
3. ECC (~282K stars)
A full harness for coding agents: 71 agents, 311 skills, memory, hooks and security scanning. Best on Claude Code. There's a paid Pro tier, but the open-source version is free.
github.com/affaan-m/ECC
4. God's Eye View (~57K stars)
A 3D globe in your browser with live public data: flights, 838 satellites, ships, earthquakes and fires. Runs locally.
github.com/bilawalsidhu/gods…
Aloha ⚜ retweeted
this is the most DANGEROUS thing on internet today
REA (Reverse Engineer Anything) - this open source MCP lets your AI agent reverse engineer any app, down to the binary
i just reverse engineered TradingView, now I am using their premium indicators for FREE - software is cooked
here is how to use REA to reverse engineer TradingView:
1. point REA at TradingView's publicly observable interface and map every major feature, from chart interactions to indicators and alerts
2. trace how the interface behaves when you switch symbols, change timeframes, add indicators, draw levels, and update chart layouts
3. use REA's available MCP tools to investigate authorized software artifacts and trace application logic wherever the evidence allows
4. feed those findings into Claude Opus 5.5, which turns the investigation into a technical specification and an implementation plan
5. rebuild the charting engine independently, with real market data, candlesticks, technical indicators, drawing tools, and persistent watchlists
6. add a quant backtesting engine that tests strategies against historical data, accounting for fees, slippage, and drawdowns
7. test every component, compare its behavior against documented and observable results, fix failures, and keep iterating until the system actually works
8. you end up building your own TradingView-style quant research terminal from scratch, with source code you control and features you can keep extending
i won’t say anything more:
Aloha ⚜ retweeted
Agencies sell AI agents as a service. Meanwhile the code is sitting on GitHub for free
Ranked from good to the best one:
1. Describe a website or app and an agent builds it right on your machine. 21.6k stars
github.com/dyad-sh/dyad
2. Secure cloud sandboxes where your agent can run code without touching your machine. 13.4k stars
github.com/e2b-dev/E2B
3. A memory layer so your agent remembers users and past sessions. 66.8k stars
github.com/mem0ai/mem0
4. Build support bots, agents and RAG pipelines visually. 152k stars
github.com/langgenius/dify
5. An open source coding agent that writes, runs and fixes code on its own. 90.7k stars
github.com/All-Hands-AI/Open…
6. Agents that use the browser: click, fill forms, pull data. 117k stars
github.com/browser-use/brows…
7. A free Photoshop rewritten from scratch in Rust with Claude, part of a whole open source Adobe suite. 49.5k stars
github.com/storytold/photocr…
8. An MCP server that lets your agent reverse engineer any app, down to the binary. 130k stars
github.com/morluto/rea
Aloha ⚜ retweeted
33 SEO websites that are basically cheat codes 👇
1. search.google.com/search-con… - See exactly how Google sees your site
2. pagespeed.web.dev - Test Core Web Vitals and page speed
3. search.google.com/test/rich-… - Test structured data eligibility
4. developers.google.com/search - Google’s official SEO documentation
5. screamingfrog.co.uk - Crawl your entire website for technical issues
6. sitebulb.com - Visual technical SEO audits and crawl analysis
7. ahrefs.com - Backlinks, competitors, keywords, content gaps
8. semrush.com - SEO + PPC + competitor research
9. moz.com/link-explorer - Backlink research
10. keywords.google.com - Keyword Planner
11. trends.google.com - See search demand and seasonality
12. alsoasked.com - Find People Also Ask questions
13. keywordseverywhere.com - Keyword data directly in your browser
14. surferseo.com/keyword-surfer - Free keyword data inside Google
15. schema.org - Reference for structured data markup
16. validator.schema.org - Validate schema markup
17. webpagetest.org - Deep performance testing
18. gtmetrix.com - Speed and performance diagnostics
19. cruxvis.withgoogle.com - Real-world Chrome performance data
20. archive.org/web - See how competitor sites looked years ago
21. builtwith.com - See what technology a website uses
22. similarweb.com - Competitor traffic estimates
23. detailed.com/extension - Quick on-page SEO inspection
24. redirect-checker.org - Check redirect chains
25. httpstatus.io - Bulk status code checker
26. securityheaders.com - Check important HTTP headers
27. localfalcon.com - Map Pack geo-grid rank tracking
28. brightlocal.com - Local rankings, citations and reporting
29. gmbeverywhere.com - Inspect GBP categories and local competitors
30. pleper.com - GBP category and Local SEO tools
31. localviking.com - GBP and local rank workflows
32. moz.com/local - Listings management
33. answerthepublic.com - Discover questions around a topic
THE BEST AI AGENT IN 2026 USES 4 MODELS.
Not one.
Opus 5.5 for the hard thinking.
Sonnet 5.5 for the building.
Haiku 5.5 for the volume.
Jev for the yes or no decisions.
Picking which model does which job used to take an engineer.
Now Opus 5.5 does it for you.
It designs the agents, picks the models, writes the prompts and wires the workflow.
Copy the prompt below 👇
Aloha ⚜ retweeted
Turmeric without black pepper is useless. Spinach without fat won't absorb. Iron without vitamin C doesn't work. Calcium blocks iron absorption. Magnesium needs to be taken at night. Vitamin D needs K2 or it calcifies your arteries. Nutrient science is real. Supplement with intention or waste your money.
Aloha ⚜ retweeted
20 GitHub repos to turn Opus 5.5 into a full motion-design stack.
Pick the tools by layer: agent skills, animation, 3D, assets, sound and export.
1. Remotion — React → editable video
github.com/remotion-dev/remo…
2. Remotion Skills — official video workflows for Claude Code
github.com/remotion-dev/skil…
3. Motion Canvas — diagrams + explainers in TypeScript
github.com/motion-canvas/mot…
4. Motion AI Kit — Motion docs + guidance for Claude Code
github.com/motiondivision/ai…
5. Motion — animate UI layouts + gestures
github.com/motiondivision/mo…
6. GSAP — precise SVG, text and timeline animation
github.com/greensock/GSAP
7. Anime.js — SVG paths, text and interface animation
github.com/juliangarnier/ani…
8. GSAP Skills — teach Claude Code timelines + React cleanup
github.com/greensock/gsap-sk…
9. Rive Web — connect vector animations to app states
github.com/rive-app/rive-was…
10. dotLottie Web — play + control Lottie assets
github.com/LottieFiles/dotlo…
11. Three.js — 3D scenes, cameras and lighting
github.com/mrdoob/three.js
12. React Three Fiber — build 3D scenes in React
github.com/pmndrs/react-thre…
13. Drei — reusable 3D cameras, text and controls
github.com/pmndrs/drei
14. React Three Rapier — physics, collisions and joints
github.com/pmndrs/react-thre…
15. React Postprocessing — bloom, depth of field + finishing
github.com/pmndrs/react-post…
16. SVGO — clean SVGs before animation
github.com/svg/svgo
17. Satori — generate SVG title cards from JSX
github.com/vercel/satori
18. Howler.js — sound effects, fades and audio control
github.com/goldfire/howler.j…
19. Mediabunny — browser-based video encoding + conversion
github.com/Vanilagy/mediabun…
20. FFmpeg — encode, resize and inspect final exports
github.com/FFmpeg/FFmpeg
The loop:
brief → design → animate → build → sound → render → review → ship
Aloha ⚜ retweeted
This guy shows you in 22 minutes how to learn to create videos automatically with Claude Code
Aloha ⚜ retweeted
Stop wasting hours figuring out what to learn in AI.
Here’s one practical roadmap covering videos, GitHub repos, guides, books, papers and courses.
*VIDEOS*
1. LLM Introduction
youtube.com/watch?v=zjkBMF…
2. LLMs from Scratch
youtube.com/watch?v=9vM4p9…
3. Agentic AI Overview — Stanford
youtube.com/watch?v=kJLiOG…
4. Building & Evaluating Agents
youtube.com/watch?v=d5EltX…
5. Building Effective Agents
youtube.com/watch?v=D7_ipD…
6. Building Agents with MCP
youtube.com/watch?v=kQmXtr…
7. Building an Agent from Scratch
youtube.com/watch?v=xzXdLR…
8. Philo Agents
youtube.com/playlist?list=…
*GITHUB REPOS*
1. GenAI Agents
github.com/nirdiamant/Gen…
2. Microsoft AI Agents for Beginners
github.com/microsoft/ai-a…
3. Prompt Engineering Guide
github.com/dair-ai/Prompt…
4. Hands-On Large Language Models
github.com/HandsOnLLM/Han…
5. GenAI Agents
github.com/NirDiamant/Gen…
6. Made with ML
github.com/GokuMohandas/M…
7. Hands-On AI Engineering
github.com/Sumanth077/Han…
8. Awesome Generative AI Guide
github.com/aishwaryanr/aw…
9. Designing Machine Learning Systems
github.com/chiphuyen/dmls…
10. Machine Learning for Beginners
github.com/microsoft/ML-F…
11. LLM Course
github.com/mlabonne/llm-c…
*GUIDES*
1. Google’s Agent Whitepaper
kaggle.com/whitepaper-age…
2. Google’s Agent Companion
kaggle.com/whitepaper-age…
3. Anthropic: Building Effective Agents
anthropic.com/engineering/bu…
4. Claude Code Agentic Coding Practices
code.claude.com/docs/en/best……
5. OpenAI: Practical Guide to Building Agents
cdn.openai.com/business-guid……
*BOOKS*
1. Understanding Deep Learning
udlbook.github.io/udlbook/
2. Building an LLM from Scratch
manning.com/books/build-a-…
3. The LLM Engineering Handbook
oreilly.com/library/view/l…
4. AI Agents: The Definitive Guide
oreilly.com/library/view/a…
5. Building Applications with AI Agents
oreilly.com/library/view/b…
6. AI Agents with MCP
oreilly.com/library/view/a…
7. AI Engineering
oreilly.com/library/view/a…
*RESEARCH PAPERS*
1. ReAct
arxiv.org/abs/2210.03629
2. Generative Agents
arxiv.org/abs/2304.03442
3. Toolformer
proceedings.neurips.cc/paper……
4. Chain-of-Thought Prompting
arxiv.org/pdf/2201.11903
*COURSES*
1. Hugging Face Agent Course
huggingface.co/learn/agents-……
2. MCP with Anthropic
deeplearning.ai/courses/mcp-……
3. Building Vector Databases with Pinecone
deeplearning.ai/courses/buil……
4. Vector Databases: Embeddings to Apps
deeplearning.ai/courses/vect……
5. Agent Memory
deeplearning.ai/courses/llms……
No endless searching. No information overload.
Just a roadmap you can actually build from.
Save this and work through it consistently.
i can't comprehend why people run claude code on default settings
one settings change and every model gets its own job:
→ opus plans every task and advises when stuck
→ sonnet 5.5 writes the actual code
→ haiku handles every file search
→ a critic agent tries to break your diff before you merge
Opus thinks. The cheap models grind.
paste this into claude code 👇
Add this to ~/.claude/settings.json. Keep every hook, permission and plugin I already have. Then create the two agent files below and show me the diff.
```json
{
"model": "opusplan",
"advisorModel": "opus",
"effortLevel": "medium",
"modelSettings": {
"claude-opus-5-5": { "effortLevel": "high" },
"claude-sonnet-5-5": { "effortLevel": "medium" }
},
"env": {
"CLAUDE_CODE_SUBAGENT_MODEL": "haiku"
}
}
```
~/.claude/agents/scout.md
```
---
name: scout
description: finds code fast. returns file paths and line numbers only.
model: haiku
tools: Read, Grep, Glob
---
Locate exactly what was asked. Return file:line. No fixes. No opinions.
```
~/.claude/agents/critic.md
```
---
name: critic
description: reviews a diff or plan before any task is called done
model: opus
tools: Read, Grep, Bash
---
Assume this is broken. Find how it fails. One line per issue, worst first.
```
Aloha ⚜ retweeted
Stanford has a free 2.5-hour class explaining how ChatGPT and Claude actually work
The lecture breaks down:
- Tokenization
* Transformers & attention
* AI model training
* Next-token prediction
* Text generation
Aloha ⚜ retweeted
Agentic AI is the future.
If you want to become god-level with AI agents, save these 10 GitHub repos:
Aloha ⚜ retweeted
35 WEBSITES GOOGLE DOESN'T WANT YOU TO KNOW
1. Explee .com — sends cold emails on autopilot
explee.com
2. NoteGPT — turns docs into podcasts
notegpt.io
3. Napkin AI — turns text into diagrams
napkin.ai
4. Ideogram — generates text in images perfectly
ideogram.ai
5. Suno — makes full songs from a prompt
suno.com
6. HeyGen — clones your face into videos
heygen.com
7. Kling AI — best AI video generation
klingai.com
8. ElevenLabs — clone any voice instantly
elevenlabs.io
9. Gamma — AI presentations in seconds
gamma.app
10. Perplexity — AI search with real sources
perplexity.ai
11. Pika — animate any image into video
pika.art
12. Runway — cinematic AI video generation
runwayml.com
13. Cursor — AI code editor that builds for you
cursor.com
14. v0 — generate UI components with AI
v0.dev
15. Lovable — turn ideas into working apps
lovable.dev
16. Descript — edit video by editing text
descript.com
17. Opus Clip — auto cut long videos into shorts
opus.pro
18. Krea AI — real time AI image generation
krea.ai
19. Magnific — upscale any image with AI
magnific.ai
20. Viggle — make characters move realistically
viggle.ai
21. tl;dv — record and summarize any meeting
tldv.io
22. Fireflies — AI meeting notes automatically
fireflies.ai
23. Castmagic — turn audio into content pieces
castmagic.io
24. Replit — code and deploy from browser
replit.com
25. Leonardo AI — generate images for free
leonardo.ai
26. Synthesia — AI avatar videos no camera needed
synthesia.io
27. Fliki — turn text into videos with AI
fliki.ai
28. Photoroom — AI product photography
photoroom.com
29. Invideo AI — turn prompts into full videos
invideo.io
30. Consensus — search what science agrees on
consensus.app
31. SciSpace — understand any research paper
scispace.com
32. Tome — AI builds your pitch decks
tome.app
33. Beautiful AI — smart presentation design
beautiful.ai
34. Meshy — turn text into 3D models
meshy.ai
35. Vizcom — turn sketches into renders
vizcom.ai
The AI revolution isn't coming.
It already happened and you missed half of it.
Aloha ⚜ retweeted
This is an actual goldmine for every AI builder
400+ ready-made agents and skills for almost any job. From Anthropic, its engineers and the community.
github.com/msitarzewski/agen… (158k stars)
~170 agents organized like a company: engineering, design, marketing, sales, product, testing, security, support. Extra packs for finance, healthcare and game dev. Works with 15+ tools.
github.com/wshobson/agents (40k stars)
202 agents, 184 skills and 105 commands packed into 94 Claude Code plugins. Language experts, code review, debugging, infra, security, testing. Install only the plugins you need.
github.com/anthropics/knowle… (26k stars)
Anthropic’s own plugins built around jobs: sales, customer support, product management, marketing, legal, finance, data.
github.com/anthropics/claude… (18k stars)
Official agents you can deploy: a daily brief from Slack and GitHub, scheduled Sentry triage, Slack and Linear bots, a customer support agent, a financial data analyst.
github.com/addyosmani/agent-… (103k stars)
From Anthropic engineer. 25 skills covering the whole dev cycle: interview-me, spec writing, TDD, browser testing, security review, CI/CD.
I’d start with claude-quickstarts. Every agent there is a full working example you can run and take apart.
Aloha ⚜ retweeted
Paste this into Claude Code and your website turns into a 30-second launch video.
It runs on HyperFrames, the open-source tool HeyGen uses to turn HTML into video.
"Install HyperFrames (npx skills add heygen-com/hyperframes).
Read my site at [URL] and pull the headline, 3 key features, brand colors and logo.
Build a 30-second launch video in HTML:
1. 0 to 3s: logo reveal on the brand color
2. 3 to 8s: the headline in kinetic type, one word at a time
3. 8 to 23s: one scene per feature with real UI screenshots and smooth GSAP transitions
4. 23 to 30s: call to action and URL
Snappy motion, no stock footage, 1080x1920 for X and Reels.
Show me 3 still frames for approval, then render the MP4."
I'm genuinely shocked this is FREE
YOU CAN BUILD YOUR FIRST AI AGENT IN ONE AFTERNOON. FOR FREE.
My first one took me two weeks.
This guide gets you there in a few hours:
Step 1: Pick one boring task you repeat every week.
Step 2: Give the agent tools: read files, search, send a draft.
Step 3: Add a Jev decision layer, so the small calls (which tool, which file, done or not) cost a fraction of a cent.
Step 4: Put a human checkpoint before anything that sends, deletes or pays.
Step 5: Run it, watch it, tighten it.
One builder with this setup ships like a small team.
Full guide below. Bookmark it.
follow @cyrilXBT
Aloha ⚜ retweeted
Learn AI for free directly from top companies
𝟭 - 𝗔𝗻𝘁𝗵𝗿𝗼𝗽𝗶𝗰:
anthropic.skilljar.com
𝟮 - 𝗚𝗼𝗼𝗴𝗹𝗲:
grow.google/ai
𝟯 - 𝗠𝗲𝘁𝗮:
ai.meta.com/resources/
𝟰 - 𝗡𝗩𝗜𝗗𝗜𝗔:
developer.nvidia.com/cuda
𝟱 - 𝗠𝗶𝗰𝗿𝗼𝘀𝗼𝗳𝘁:
learn.microsoft.com/en-us/tr…
𝟲 - 𝗢𝗽𝗲𝗻𝗔𝗜:
academy.openai.com
𝟳 - 𝗜𝗕𝗠:
skillsbuild.org
𝟴 - 𝗔𝗪𝗦:
skillbuilder.aws
𝟵 - 𝗗𝗲𝗲𝗽𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴𝗔𝗜:
deeplearning.ai
𝟭𝟬 - 𝗛𝘂𝗴𝗴𝗶𝗻𝗴 𝗙𝗮𝗰𝗲:
huggingface.co/learn
❤️ Like
🔁 Retweet
🔖 Bookmark
Follow @lihazadn_Ai more AI Post
Aloha ⚜ retweeted
STOP WASTING HOURS TRYING TO FIGURE OUT WHAT TO LEARN IN AI.
I put together one practical roadmap with videos, GitHub repos, guides, books, research papers, and courses.
VIDEOS:
1. LLM Introduction — youtube.com/watch?v=zjkBMFhN…
2. LLMs from Scratch — youtube.com/watch?v=9vM4p9NN…
3. Agentic AI Overview (Stanford) — youtube.com/watch?v=kJLiOGle…
4. Building & Evaluating Agents — youtube.com/watch?v=d5EltXhb…
5. Building Effective Agents — youtube.com/watch?v=D7_ipDqh…
6. Building Agents with MCP — youtube.com/watch?v=kQmXtrmQ…
7. Building an Agent from Scratch — youtube.com/watch?v=xzXdLRUy…
8. Philo Agents — youtube.com/playlist?list=PL…
GITHUB REPOS:
1. GenAI Agents — github.com/nirdiamant/GenAI_…
2. Microsoft AI Agents for Beginners — github.com/microsoft/ai-agen…
3. Prompt Engineering Guide — github.com/dair-ai/Prompt-En…
4. Hands-On Large Language Models — github.com/HandsOnLLM/Hands-…
5. GenAI Agents — github.com/NirDiamant/GenAI_…
6. Made with ML — github.com/GokuMohandas/Made…
7. Hands-On AI Engineering — github.com/Sumanth077/Hands-…
8. Awesome Generative AI Guide — github.com/aishwaryanr/aweso…
9. Designing Machine Learning Systems — github.com/chiphuyen/dmls-bo…
10. Machine Learning for Beginners — github.com/microsoft/ML-For-…
11. LLM Course — github.com/mlabonne/llm-cour…
GUIDES:
1. Google's Agent Whitepaper — kaggle.com/whitepaper-agents
2. Google's Agent Companion — kaggle.com/whitepaper-agent-…
3. Building Effective Agents by Anthropic — anthropic.com/engineering/bu…
4. Claude Code Agentic Coding Practices — code.claude.com/docs/en/best…
5. OpenAI's Practical Guide to Building Agents — cdn.openai.com/business-guid…
BOOKS:
1. Understanding Deep Learning — udlbook.github.io/udlbook/
2. Building an LLM from Scratch — manning.com/books/build-a-la…
3. The LLM Engineering Handbook — oreilly.com/library/view/llm…
4. AI Agents: The Definitive Guide — oreilly.com/library/view/ai-…
5. Building Applications with AI Agents — oreilly.com/library/view/bui…
6. AI Agents with MCP — oreilly.com/library/view/ai-…
7. AI Engineering — oreilly.com/library/view/ai-…
RESEARCH PAPERS:
1. ReAct — arxiv.org/abs/2210.03629
2. Generative Agents — arxiv.org/abs/2304.03442
3. Toolformer — proceedings.neurips.cc/paper…
4. Chain-of-Thought Prompting — arxiv.org/pdf/2201.11903
COURSES:
1. Meta Data Analyst Professional Certificate: imp.i384100.net/rENKMG
2. Google Advanced Data Analytics Professional Certificate: imp.i384100.net/jR67bn
3. Microsoft Power BI Data Analyst Professional Certificate: imp.i384100.net/PzdQx6
4. Google Data Analytics Professional Certificate: imp.i384100.net/xJ6DQx
5. Introduction to Data Analytics: imp.i384100.net/5k0drn
6. Machine Learning Specialization: imp.i384100.net/k42K6M
7. IBM Deep Learning with PyTorch, Keras and Tensorflow Professional Certificate: imp.i384100.net/enZ0zg
8. Deep Learning Specialization: imp.i384100.net/qW6KMO
9. Crash Course on Python: imp.i384100.net/QYd9Dz
10. Python for Data Science, AI & Development: imp.i384100.net/9Vd6kQ
11. ChatGPT + Excel: AI-Enhanced Data Analysis & Insight Specialization: imp.i384100.net/rENKMB
12. Work Smarter with Microsoft Excel: imp.i384100.net/jR67ba
13. Microsoft Excel Professional Certificate: imp.i384100.net/PzdQxq
14. Excel Basics for Data Analysis: imp.i384100.net/5k0drD
15. SQL Foundations: imp.i384100.net/k42K6v
Repost so someone else can find this roadmap, and pls consider following @Mohiniuni for more content around AI, Beauty, and businesses.


























