Loading video...

Video Failed to Load

Go Home

Want to give your agent quality checks? Chrome's DevTools MCP now includes: ⚡️ Performance checks via Lighthouse 📈 Memory leak detection Skill 🦻 Accessibility debugging Skill 🎨 LCP optimization Skill and an experimental new CLI 👀

addyosmani's profile picture

Addy Osmani

409,217 subscribers

130,532 views • 4 months ago •via X (Twitter)

Science & Technology
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

That’s a wrap on Developer Week! 🎬 We shipped the Stitch MCP Server (easier auth next week), the Gemini CLI Extension, and Agent Skills. Why? To enable workflows like this. 👇 Watch the Gemini CLI orchestrate a self-building, self-ideating loop by using a new Stitch skill (stitch-loop). It connects the Stitch MCP and the Chrome DevTools MCP to design, build, and iterate all on its own. More details in 🧵 Thanks for an amazing week. Happy building! 🛠️
0:11

That’s a wrap on Developer Week! 🎬 We shipped the Stitch MCP Server (easier auth next week), the Gemini CLI Extension, and Agent Skills. Why? To enable workflows like this. 👇 Watch the Gemini CLI orchestrate a self-building, self-ideating loop by using a new Stitch skill (stitch-loop). It connects the Stitch MCP and the Chrome DevTools MCP to design, build, and iterate all on its own. More details in 🧵 Thanks for an amazing week. Happy building! 🛠️

Stitch by Google

55,940 views • 7 months ago

Excited to announce AI Research Skills - an open-source library of 82 specialized skills for AI coding tools. One command gives your agent expert knowledge in: → Model training & fine-tuning (TRL, Unsloth ...) → Distributed systems (DeepSpeed, FSDP ...) → Inference optimization (vLLM, TensorRT ...) → Agent building ? (Langchain, AutoGPT ...) Works with Claude Code, Cursor, Gemini CLI, Windsurf, and Codex with one click interactive installation @ npx orchestra-research/ai-research-skills If you found the ML paper writing skill useful, check out the comprehensive collection
0:15

Excited to announce AI Research Skills - an open-source library of 82 specialized skills for AI coding tools. One command gives your agent expert knowledge in: → Model training & fine-tuning (TRL, Unsloth ...) → Distributed systems (DeepSpeed, FSDP ...) → Inference optimization (vLLM, TensorRT ...) → Agent building ? (Langchain, AutoGPT ...) Works with Claude Code, Cursor, Gemini CLI, Windsurf, and Codex with one click interactive installation @ npx orchestra-research/ai-research-skills If you found the ML paper writing skill useful, check out the comprehensive collection

Zechen Zhang

75,583 views • 7 months ago

We are entering an extremely exciting era for open-weight models. Kimi K2.6 now feels like a top agentic model. I took it for a spin via Fireworks AI fast inference APIs. Kimi K2.6 has impressive agentic capabilities, design skills, and the ability to synthesize large amounts of information. I built a little Skill that produces survey papers on any AI research topic you want. (see example in the clip) You can use the skill to tell your agent to generate a survey on whatever topic and watch it go to work. The artifact was fully generated by Kimi.ai's Kimi K2.6. It's cheap and fast. Next step for me is to explore ways to continue integrating the capabilities of these models on use cases like automating my LLM knowledge bases and augmenting my agent memory capabilities. Stay tuned for more.
0:19

We are entering an extremely exciting era for open-weight models. Kimi K2.6 now feels like a top agentic model. I took it for a spin via Fireworks AI fast inference APIs. Kimi K2.6 has impressive agentic capabilities, design skills, and the ability to synthesize large amounts of information. I built a little Skill that produces survey papers on any AI research topic you want. (see example in the clip) You can use the skill to tell your agent to generate a survey on whatever topic and watch it go to work. The artifact was fully generated by Kimi.ai's Kimi K2.6. It's cheap and fast. Next step for me is to explore ways to continue integrating the capabilities of these models on use cases like automating my LLM knowledge bases and augmenting my agent memory capabilities. Stay tuned for more.

elvis

47,678 views • 4 months ago

Sharing my new skill! It keeps track of high-signal X accounts for top AI news, papers, projects, etc. Total gamechanger for me. Built with X MCP tools. Give your agent the skill and tell it to generate the artifact with top stories. Works for Codex, Claude, Hermes, OpenClaw, or whatever you use. 3 steps: 1. Set up X MCP - X API: 2. Install skill here: 3. Run prompt: "Use the x-agent-intelligence skill to build a self-contained local feed from my X MCP connection; ask for my source handles if needed, save feed.html, and validate it." It should generate a nice, beautiful HTML artifact like the one shown in the clip. You can tune it however you want. You can then set a schedule/automation to do this daily or whatever cadence you prefer. I have it every 4 hours. You will need to curate the X accounts yourself, but I have shared a few good ones under the assets. You can ask your agent to tune it to however you like. I have also shared my personal feed with our community here: I understand if it gets tricky to set up. Please reach out to me in the community forum. I plan to do a little tutorial or live session soon to help others reproduce the process. You can also store the feed as a wiki, as I have in my own implementation, but that's optional. If you encounter any issues or have ideas on how to improve it, please open a PR.
0:10

Sharing my new skill! It keeps track of high-signal X accounts for top AI news, papers, projects, etc. Total gamechanger for me. Built with X MCP tools. Give your agent the skill and tell it to generate the artifact with top stories. Works for Codex, Claude, Hermes, OpenClaw, or whatever you use. 3 steps: 1. Set up X MCP - X API: 2. Install skill here: 3. Run prompt: "Use the x-agent-intelligence skill to build a self-contained local feed from my X MCP connection; ask for my source handles if needed, save feed.html, and validate it." It should generate a nice, beautiful HTML artifact like the one shown in the clip. You can tune it however you want. You can then set a schedule/automation to do this daily or whatever cadence you prefer. I have it every 4 hours. You will need to curate the X accounts yourself, but I have shared a few good ones under the assets. You can ask your agent to tune it to however you like. I have also shared my personal feed with our community here: I understand if it gets tricky to set up. Please reach out to me in the community forum. I plan to do a little tutorial or live session soon to help others reproduce the process. You can also store the feed as a wiki, as I have in my own implementation, but that's optional. If you encounter any issues or have ideas on how to improve it, please open a PR.

elvis

72,234 views • 1 month ago

NEW HTML VIDEO SKILL: Claude can now make photo-grid promo video ads like these. These are very popular offer-style ads that work well for bottom-of-funnel conversions. Brands will often run these when they're doing seasonal sales, for example. It's pure HTML, so it's very cheap to make because there's no video generation cost. You can create dozens of variants very fast and then test them in Meta. All you have to do is install the skills and give Claude your brand website. This skill is insane - it'll make the entire Ad and give you a link where you can download the mp4 file. > If you want more variants, just mention in the prompt > If you have a specific concept in mind, just mention in the prompt > If you want any edits on the generated ad, just mention in the prompt Comment Goose and I'll DM you the skill (must be following so I can DM you)
0:19

NEW HTML VIDEO SKILL: Claude can now make photo-grid promo video ads like these. These are very popular offer-style ads that work well for bottom-of-funnel conversions. Brands will often run these when they're doing seasonal sales, for example. It's pure HTML, so it's very cheap to make because there's no video generation cost. You can create dozens of variants very fast and then test them in Meta. All you have to do is install the skills and give Claude your brand website. This skill is insane - it'll make the entire Ad and give you a link where you can download the mp4 file. > If you want more variants, just mention in the prompt > If you have a specific concept in mind, just mention in the prompt > If you want any edits on the generated ad, just mention in the prompt Comment Goose and I'll DM you the skill (must be following so I can DM you)

Shiv

92,070 views • 1 month ago

How to build a viral Web3 app in an afternoon using the ChainGPT AI skill for Claude Code. No coding experience required. I built Roast My Wallet. Paste any Ethereum wallet address, get a savage AI-generated roast of your trading history, a Degen Score out of 100, an on-chain report card, and three AI-generated NFT portraits. Here's exactly how it came together. Setup (3 minutes): 🔸Install Claude Code at 🔸Run /plugin install ChainGPT-org/chaingpt-claude-skill 🔸Get an API key at 🔸Type /chaingpt and describe what you want to build What the skill actually does: The ChainGPT skill doesn't just give you starter code. It knows the entire API. Every endpoint, every parameter, every credit cost, every error code. When I asked it to build the roast feature, it knew to call the LLM endpoint, how to stream the response back to the browser in real time, and how to handle errors automatically. I didn't look up a single thing. How it works under the hood: 1. Pulls real ETH balance and transaction count from the Ethereum blockchain 2. Feeds those numbers into ChainGPT's LLM and streams the roast back live 3. Calculates a Degen Score from your tx count vs balance ratio 4. Generates a report card with letter grades across Trading, Patience, Risk, Diamond Hands, and NGMI 5. Uses the roast text to generate three custom NFT portraits in parallel via VeloGen 6. Packages everything into a downloadable PNG card ready to post 7. Every feature came from describing what I wanted: 8. "Make the API key server-side." Done. 9. "Add an animated arc gauge for the degen score." Done. 10. "Generate NFT portraits using the roast text as context." Done. I never wrote a function or debugged an API response. I described outcomes. The ChainGPT skill handled the rest. If you can describe what you want to build, you can build it. Get your API key. Install the skill. /plugin install ChainGPT-org/chaingpt-claude-skill Anyone can build with ChainGPT AI!
0:11

How to build a viral Web3 app in an afternoon using the ChainGPT AI skill for Claude Code. No coding experience required. I built Roast My Wallet. Paste any Ethereum wallet address, get a savage AI-generated roast of your trading history, a Degen Score out of 100, an on-chain report card, and three AI-generated NFT portraits. Here's exactly how it came together. Setup (3 minutes): 🔸Install Claude Code at 🔸Run /plugin install ChainGPT-org/chaingpt-claude-skill 🔸Get an API key at 🔸Type /chaingpt and describe what you want to build What the skill actually does: The ChainGPT skill doesn't just give you starter code. It knows the entire API. Every endpoint, every parameter, every credit cost, every error code. When I asked it to build the roast feature, it knew to call the LLM endpoint, how to stream the response back to the browser in real time, and how to handle errors automatically. I didn't look up a single thing. How it works under the hood: 1. Pulls real ETH balance and transaction count from the Ethereum blockchain 2. Feeds those numbers into ChainGPT's LLM and streams the roast back live 3. Calculates a Degen Score from your tx count vs balance ratio 4. Generates a report card with letter grades across Trading, Patience, Risk, Diamond Hands, and NGMI 5. Uses the roast text to generate three custom NFT portraits in parallel via VeloGen 6. Packages everything into a downloadable PNG card ready to post 7. Every feature came from describing what I wanted: 8. "Make the API key server-side." Done. 9. "Add an animated arc gauge for the degen score." Done. 10. "Generate NFT portraits using the roast text as context." Done. I never wrote a function or debugged an API response. I described outcomes. The ChainGPT skill handled the rest. If you can describe what you want to build, you can build it. Get your API key. Install the skill. /plugin install ChainGPT-org/chaingpt-claude-skill Anyone can build with ChainGPT AI!

ChainGPT

29,323 views • 3 months ago

Impeccable 3.7 brings linting to design. Until now it was a skill you asked for help. Now it's a design-system-aware feedback loop that runs while your agent builds, catching slop and design drift before they land. 🪝 Design hooks for Claude, Codex, and Cursor They run after every UI edit and quietly nudge your agent to fix slop and drift. The output isn't another wall of lint: it separates new findings from already-seen ones, flags clean scans, and asks the agent to use judgment. Fix real issues, leave intentional demos alone, save exceptions to config instead of littering your source. 🎨 Slop detection is now project-aware Reads your actual design system from DESIGN.md, your typography, palette, radius scale, and tokens, and flags drift from your system, not just generic AI slop: • this font isn't in your design system • this color is outside your documented palette • this radius doesn't match your rounded scale The same engine powers both the hooks and the CLI, and it's where we're investing next. 🖥️ Live Mode, ready for real projects Svelte/SvelteKit now preview variants as temporary framework components with live params, then accept cleanly back into your source component. Manual text edits got evidence / apply / discard routes, insertions preserve their anchors, and mapped lists and JSX slots clean up far more reliably. ⚡ Leaner core, sharper detector Rule-level evals across 3 providers and 4 niches cut guidance with no measurable lift and dropped examples that taught models bad patterns. The detector now skips hidden and screen-reader-only elements, understands OKLCH alpha and Sass-like inputs, and tightened checks for repeated kickers, oversized H1s, clipped overflow, and cramped padding. 🛠️ CLI caught up impeccable detect loads DESIGN.md by default, motion findings name the exact token or cubic-bezier instead of just "bounce," and impeccable ignores gives real CRUD for exceptions. Hooks and CLI share the same ignores. No split-brain config. Plus a much-improved interactive installer with hooks setup built in. Upgrade: npx impeccable install npm i -g impeccable
0:12

Impeccable 3.7 brings linting to design. Until now it was a skill you asked for help. Now it's a design-system-aware feedback loop that runs while your agent builds, catching slop and design drift before they land. 🪝 Design hooks for Claude, Codex, and Cursor They run after every UI edit and quietly nudge your agent to fix slop and drift. The output isn't another wall of lint: it separates new findings from already-seen ones, flags clean scans, and asks the agent to use judgment. Fix real issues, leave intentional demos alone, save exceptions to config instead of littering your source. 🎨 Slop detection is now project-aware Reads your actual design system from DESIGN.md, your typography, palette, radius scale, and tokens, and flags drift from your system, not just generic AI slop: • this font isn't in your design system • this color is outside your documented palette • this radius doesn't match your rounded scale The same engine powers both the hooks and the CLI, and it's where we're investing next. 🖥️ Live Mode, ready for real projects Svelte/SvelteKit now preview variants as temporary framework components with live params, then accept cleanly back into your source component. Manual text edits got evidence / apply / discard routes, insertions preserve their anchors, and mapped lists and JSX slots clean up far more reliably. ⚡ Leaner core, sharper detector Rule-level evals across 3 providers and 4 niches cut guidance with no measurable lift and dropped examples that taught models bad patterns. The detector now skips hidden and screen-reader-only elements, understands OKLCH alpha and Sass-like inputs, and tightened checks for repeated kickers, oversized H1s, clipped overflow, and cramped padding. 🛠️ CLI caught up impeccable detect loads DESIGN.md by default, motion findings name the exact token or cubic-bezier instead of just "bounce," and impeccable ignores gives real CRUD for exceptions. Hooks and CLI share the same ignores. No split-brain config. Plus a much-improved interactive installer with hooks setup built in. Upgrade: npx impeccable install npm i -g impeccable

Impeccable

233,051 views • 2 months ago

LLM Knowledge Base → Slides When Andrej Karpathy shared his LLM Knowledge Base setup, many were wondering how to generate more visual forms of the wiki. There are many options, but I think Gamma is one of the best at producing high-quality, rich presentations. To showcase this, I just built a pipeline that turns my AI papers wiki (1K+ papers across 20 AI agent topics) into polished slide presentations using Gamma. The flow: Obsidian vault → Gamma MCP → embedded preview in my dashboard. I give one command to my agent, which pulls the top papers from each topic (via the wiki), feeds them to Gamma, and renders the presentation inline. The Gamma connector for Claude is a great choice for generating beautiful and professional slides. Easy to use. Go to your Claude instance and add the official Gamma connector. That's it! Claude Code will now have access to all the necessary MCP tools for generating slides. I use the Claude Agent SDK for my agent orchestrator, so I use the official Gamma MCP tools and embed the generated slides in an iframe via my artifact preview. See the clip below for an example.
0:19

LLM Knowledge Base → Slides When Andrej Karpathy shared his LLM Knowledge Base setup, many were wondering how to generate more visual forms of the wiki. There are many options, but I think Gamma is one of the best at producing high-quality, rich presentations. To showcase this, I just built a pipeline that turns my AI papers wiki (1K+ papers across 20 AI agent topics) into polished slide presentations using Gamma. The flow: Obsidian vault → Gamma MCP → embedded preview in my dashboard. I give one command to my agent, which pulls the top papers from each topic (via the wiki), feeds them to Gamma, and renders the presentation inline. The Gamma connector for Claude is a great choice for generating beautiful and professional slides. Easy to use. Go to your Claude instance and add the official Gamma connector. That's it! Claude Code will now have access to all the necessary MCP tools for generating slides. I use the Claude Agent SDK for my agent orchestrator, so I use the official Gamma MCP tools and embed the generated slides in an iframe via my artifact preview. See the clip below for an example.

elvis

47,989 views • 4 months ago

I just built a Claude Cowork skill that turns your Google Ads data into a visual performance dashboard in 60 seconds 🤯 One prompt → campaign breakdowns, CPA trends, spend vs conversions charts, and hourly conversion patterns, all rendered as an interactive HTML dashboard you open in Chrome. All inside Claude Cowork. Perfect for DTC brands and agencies who are pulling Google Ads data into spreadsheets every week, manually building charts, and spending an hour formatting a report that's outdated by the time you send it. If you're managing Google Ads and your weekly reporting workflow looks like this — export a CSV, open Google Sheets, build a pivot table, copy the numbers into a slide deck, manually create charts, format everything, realize you forgot a campaign, start over ... This skill does the whole thing in one prompt: → Connects to your live Google Ads data via MCP → Pulls spend, conversions, CPA, ROAS, CTR across every campaign → Builds an interactive HTML dashboard → Summary cards at the top: total spend, total conversions, avg CPA, avg ROAS → Bar chart comparing spend vs conversions by campaign → CPA trend line over the last 30 days → Campaign table ranked by performance, color-coded green/yellow/red → Opens in Chrome: hover over charts, compare campaigns, screenshot for your team No spreadsheets. No manual chart building. No hour-long formatting sessions. What you get: → A visual dashboard from live data in under 60 seconds → Campaign performance you can actually see, not just read in a table → CPA trends that show you where things are heading, not just where they are → A dashboard you can screenshot and drop into Slack, a client report, or a team standup → Reusable — run it weekly and the data updates automatically One prompt. Live data. A finished dashboard you open in your browser. I put together a playbook with the full skill file, the setup, and the exact prompts to customize the dashboard for your account. Want it for free? > Like this post > Comment "DASH" And I'll send it over (must be following so I can DM)
0:11

I just built a Claude Cowork skill that turns your Google Ads data into a visual performance dashboard in 60 seconds 🤯 One prompt → campaign breakdowns, CPA trends, spend vs conversions charts, and hourly conversion patterns, all rendered as an interactive HTML dashboard you open in Chrome. All inside Claude Cowork. Perfect for DTC brands and agencies who are pulling Google Ads data into spreadsheets every week, manually building charts, and spending an hour formatting a report that's outdated by the time you send it. If you're managing Google Ads and your weekly reporting workflow looks like this — export a CSV, open Google Sheets, build a pivot table, copy the numbers into a slide deck, manually create charts, format everything, realize you forgot a campaign, start over ... This skill does the whole thing in one prompt: → Connects to your live Google Ads data via MCP → Pulls spend, conversions, CPA, ROAS, CTR across every campaign → Builds an interactive HTML dashboard → Summary cards at the top: total spend, total conversions, avg CPA, avg ROAS → Bar chart comparing spend vs conversions by campaign → CPA trend line over the last 30 days → Campaign table ranked by performance, color-coded green/yellow/red → Opens in Chrome: hover over charts, compare campaigns, screenshot for your team No spreadsheets. No manual chart building. No hour-long formatting sessions. What you get: → A visual dashboard from live data in under 60 seconds → Campaign performance you can actually see, not just read in a table → CPA trends that show you where things are heading, not just where they are → A dashboard you can screenshot and drop into Slack, a client report, or a team standup → Reusable — run it weekly and the data updates automatically One prompt. Live data. A finished dashboard you open in your browser. I put together a playbook with the full skill file, the setup, and the exact prompts to customize the dashboard for your account. Want it for free? > Like this post > Comment "DASH" And I'll send it over (must be following so I can DM)

Mike Futia

38,936 views • 5 months ago

HERMES AGENT NOW SUPPORTS COMPUTER USE ON WINDOWS AND LINUX. CLICKS, TYPES, SCROLLS YOUR DESKTOP IN THE BACKGROUND WHILE YOU WORK. computer use was macOS only. now it works on Windows and Linux too via Cua. Nous Research HOW IT WORKS: cua-driver runs as an MCP server. Hermes takes a screenshot with numbered elements. clicks element #14 (the search field). types a query. submits. reads the result. during all of this: → your cursor stays where you left it → keyboard focus doesn't change → windows don't come to front → macOS doesn't switch Spaces you and the agent co-work on the same machine. WHAT IT CAN DO: → find your latest Stripe email and summarize it → fill forms in a web app that has no API → navigate desktop apps (Mail, browser, Finder) → interact with any GUI application → extract data from apps only accessible via screen WORKS WITH ANY VISION MODEL: not locked to Anthropic. | Provider | Works | |---|---| | Claude (Sonnet/Opus) | best overall | | GPT-4+, GPT-5.5 | full support | | Gemini (via OpenRouter) | full support | | Local vLLM / LM Studio | if model supports vision | | Text-only models | degraded (accessibility tree only) | SETUP: hermes computer-use install or: hermes tools → Computer Use → cua-driver grant permissions when prompted: → Accessibility (system settings) → Screen Recording (system settings) start a session: hermes -t computer_use chat or add to config.yaml / Desktop app settings to enable permanently. SAFETY: → destructive actions require your approval → blocked key combos: empty trash, force delete, lock screen, log out → blocked type patterns: curl | bash, sudo rm -rf /, fork bombs → agent cannot click permission dialogs → agent cannot type passwords → agent cannot follow instructions embedded in screenshots pair with approvals.mode: manual if you want every single click confirmed. TOKEN NOTE: screenshots are expensive. each one adds vision tokens to context. use computer_use for tasks where no API exists. if the tool has an API or MCP server, use that instead. 15 levels of Hermes Agent👇
0:11

HERMES AGENT NOW SUPPORTS COMPUTER USE ON WINDOWS AND LINUX. CLICKS, TYPES, SCROLLS YOUR DESKTOP IN THE BACKGROUND WHILE YOU WORK. computer use was macOS only. now it works on Windows and Linux too via Cua. Nous Research HOW IT WORKS: cua-driver runs as an MCP server. Hermes takes a screenshot with numbered elements. clicks element #14 (the search field). types a query. submits. reads the result. during all of this: → your cursor stays where you left it → keyboard focus doesn't change → windows don't come to front → macOS doesn't switch Spaces you and the agent co-work on the same machine. WHAT IT CAN DO: → find your latest Stripe email and summarize it → fill forms in a web app that has no API → navigate desktop apps (Mail, browser, Finder) → interact with any GUI application → extract data from apps only accessible via screen WORKS WITH ANY VISION MODEL: not locked to Anthropic. | Provider | Works | |---|---| | Claude (Sonnet/Opus) | best overall | | GPT-4+, GPT-5.5 | full support | | Gemini (via OpenRouter) | full support | | Local vLLM / LM Studio | if model supports vision | | Text-only models | degraded (accessibility tree only) | SETUP: hermes computer-use install or: hermes tools → Computer Use → cua-driver grant permissions when prompted: → Accessibility (system settings) → Screen Recording (system settings) start a session: hermes -t computer_use chat or add to config.yaml / Desktop app settings to enable permanently. SAFETY: → destructive actions require your approval → blocked key combos: empty trash, force delete, lock screen, log out → blocked type patterns: curl | bash, sudo rm -rf /, fork bombs → agent cannot click permission dialogs → agent cannot type passwords → agent cannot follow instructions embedded in screenshots pair with approvals.mode: manual if you want every single click confirmed. TOKEN NOTE: screenshots are expensive. each one adds vision tokens to context. use computer_use for tasks where no API exists. if the tool has an API or MCP server, use that instead. 15 levels of Hermes Agent👇

YanXbt

29,127 views • 2 months ago

LLM Artifacts Connected to Andrej Karpathy's LLM Knowledge base idea, I've been building out a fun way to generate dynamic artifacts from these knowledge bases with the goal of discovering and revealing meaningful and deeper insights. LLM KBs are hard to consume for humans, as I think they are more built for agents. So the question is, what form would be useful for humans to take actions and make important decisions? That's what I am trying to figure out with these artifacts. The artifact example shows a pulse on HN discussions around AI-related stories. The insights can go deeper, of course, but this is already super fun and thought-provoking, like some of my favorite podcasts. The format and depth matter a lot. The aggregation skills of agents are outstanding if you tune the prompts and skill carefully. I built this artifact generator in a few minutes through an agent skill, but I feel like there are so many ways that LLM-generated information can be used and consumed. Like generating deeper insights and analysis, and things that are just not feasible for humans today. The generated artifact (including its data and design) serves as reusable templates or can be updated in real-time via auomations, which is something I am also working on. It is truly an insane way to monitor and track information. Better than a newsletter. Better than newspapers. There is something about this that gets me really excited about the future of AI agents for knowledge generation and discovery. Lots of hidden gems everywhere just waiting to be discovered and acted on if the information is presented correctly. This is not perfect. The format, style/prose can be improved, but this is easy to customize via skill. You can personalize it to your liking. I feel like these dynamic artifacts are going to emerge as a strong new medium to stay on the cutting edge of things, both for agents and humans. My target is research, of course. This was just a basic example. Besides animation, I am also targeting other components like voice, videos, images, slides, etc. This space is full of opportunities to explore. Skill for this coming soon.
0:18

LLM Artifacts Connected to Andrej Karpathy's LLM Knowledge base idea, I've been building out a fun way to generate dynamic artifacts from these knowledge bases with the goal of discovering and revealing meaningful and deeper insights. LLM KBs are hard to consume for humans, as I think they are more built for agents. So the question is, what form would be useful for humans to take actions and make important decisions? That's what I am trying to figure out with these artifacts. The artifact example shows a pulse on HN discussions around AI-related stories. The insights can go deeper, of course, but this is already super fun and thought-provoking, like some of my favorite podcasts. The format and depth matter a lot. The aggregation skills of agents are outstanding if you tune the prompts and skill carefully. I built this artifact generator in a few minutes through an agent skill, but I feel like there are so many ways that LLM-generated information can be used and consumed. Like generating deeper insights and analysis, and things that are just not feasible for humans today. The generated artifact (including its data and design) serves as reusable templates or can be updated in real-time via auomations, which is something I am also working on. It is truly an insane way to monitor and track information. Better than a newsletter. Better than newspapers. There is something about this that gets me really excited about the future of AI agents for knowledge generation and discovery. Lots of hidden gems everywhere just waiting to be discovered and acted on if the information is presented correctly. This is not perfect. The format, style/prose can be improved, but this is easy to customize via skill. You can personalize it to your liking. I feel like these dynamic artifacts are going to emerge as a strong new medium to stay on the cutting edge of things, both for agents and humans. My target is research, of course. This was just a basic example. Besides animation, I am also targeting other components like voice, videos, images, slides, etc. This space is full of opportunities to explore. Skill for this coming soon.

elvis

31,314 views • 4 months ago

BREAKING: SpaceXAI has released another major new update for Grok Build (v1.0.22) This update is focused on smoother workflows, better safety and improved reliability. It adds stronger desktop and MCP integration, clearer file-edit previews, a redesigned dashboard and better subagent support. It also fixes problems with sessions, skills, authentication and background commands while making sessions faster to open and resume. Features Built-in agent tools now take precedence over user MCP servers when tool names collide. Desktop app tools are now available through a dedicated first-party MCP server. Remote control pickers can now group servers by device using announced device identity. edit_file diffs now show real file line numbers instead of starting at line 1. Permission prompts for file edits now auto-expand the diff row so you can see the change before approving. Sending a message to a finished subagent now continues that same subagent instead of failing. Background subagent completion messages now show the actual output instead of just a pointer to run the tool. Dashboard now shows a unified header with a location picker and an actions row for creating agents or resuming previous sessions. New grok-workspaced daemon mode lets a long-lived process expose folders to the Computer Hub, separate from the Desktop-supervised sidecar. Bug Fixes MCP connectors now correctly show when they need re-authentication, even if no tools are listed. Extensions modal shortcuts now work when the tab bar is focused, and invalid actions on headers show helpful messages. The Send now button and shortcuts now work correctly when an automatic background turn is running. Resumed sessions now show the exact text you typed for mid-turn follow-ups instead of the wrapped system message. The /skills command now updates the model with newly installed skills, even when written from another NFS client. Auto mode no longer instantly runs destructive git checkout -- commands; they now go through the model for safety. Fixed a crash that could occur when restoring pasted content after certain skill injections or rewinds. Subagents and workflows now respect the same bash timeout and auto-background settings configured for the parent session. Fixed model backend selection so an explicit chat_completions setting in config.toml is no longer overwritten by same-slug siblings. Slash command advertisements no longer spam repeatedly when your current directory is your home folder. Foreground shell commands no longer produce spurious background-task reminders or incorrect kill results. Queued follow-up buttons now appear in the order [Send now][edit][Cancel]. /compact instructions in the pager are now passed to the compaction backend. Bare /compact is unchanged. /goal, and resume after pressing Esc, now correctly starts the goal planner instead of failing with “Planning failed.” run_terminal_cmd now correctly tells the model that foreground commands are backgrounded after approximately 15 seconds instead of the 120-second timeout value. Skill announcements no longer repeat the same list of available skills multiple times in a session. Monitor events in multi-session processes now correctly wake idle sessions instead of being buffered until the next prompt. Performance Opening or resuming sessions no longer pauses the interface while reading MCP configuration files. Download Grok Build: Update to the latest Alpha release: grok update --alpha Update to the latest Stable release: grok update
0:12

BREAKING: SpaceXAI has released another major new update for Grok Build (v1.0.22) This update is focused on smoother workflows, better safety and improved reliability. It adds stronger desktop and MCP integration, clearer file-edit previews, a redesigned dashboard and better subagent support. It also fixes problems with sessions, skills, authentication and background commands while making sessions faster to open and resume. Features Built-in agent tools now take precedence over user MCP servers when tool names collide. Desktop app tools are now available through a dedicated first-party MCP server. Remote control pickers can now group servers by device using announced device identity. edit_file diffs now show real file line numbers instead of starting at line 1. Permission prompts for file edits now auto-expand the diff row so you can see the change before approving. Sending a message to a finished subagent now continues that same subagent instead of failing. Background subagent completion messages now show the actual output instead of just a pointer to run the tool. Dashboard now shows a unified header with a location picker and an actions row for creating agents or resuming previous sessions. New grok-workspaced daemon mode lets a long-lived process expose folders to the Computer Hub, separate from the Desktop-supervised sidecar. Bug Fixes MCP connectors now correctly show when they need re-authentication, even if no tools are listed. Extensions modal shortcuts now work when the tab bar is focused, and invalid actions on headers show helpful messages. The Send now button and shortcuts now work correctly when an automatic background turn is running. Resumed sessions now show the exact text you typed for mid-turn follow-ups instead of the wrapped system message. The /skills command now updates the model with newly installed skills, even when written from another NFS client. Auto mode no longer instantly runs destructive git checkout -- commands; they now go through the model for safety. Fixed a crash that could occur when restoring pasted content after certain skill injections or rewinds. Subagents and workflows now respect the same bash timeout and auto-background settings configured for the parent session. Fixed model backend selection so an explicit chat_completions setting in config.toml is no longer overwritten by same-slug siblings. Slash command advertisements no longer spam repeatedly when your current directory is your home folder. Foreground shell commands no longer produce spurious background-task reminders or incorrect kill results. Queued follow-up buttons now appear in the order [Send now][edit][Cancel]. /compact instructions in the pager are now passed to the compaction backend. Bare /compact is unchanged. /goal, and resume after pressing Esc, now correctly starts the goal planner instead of failing with “Planning failed.” run_terminal_cmd now correctly tells the model that foreground commands are backgrounded after approximately 15 seconds instead of the 120-second timeout value. Skill announcements no longer repeat the same list of available skills multiple times in a session. Monitor events in multi-session processes now correctly wake idle sessions instead of being buffered until the next prompt. Performance Opening or resuming sessions no longer pauses the interface while reading MCP configuration files. Download Grok Build: Update to the latest Alpha release: grok update --alpha Update to the latest Stable release: grok update

DogeDesigner

58,736 views • 1 day ago

Pulling wheelies on a clutchless Honda commuter bike on Hulhumale-Male’ highway isn’t motorsport anywhere in the real world. Real racing requires a real motorbike, meaning a manual clutch, proper gearbox, engine braking, race grade suspension and brakes. If you want to race, do it the way the rest of the world does. Get a proper motorbike, get gov permission, use designated areas (Hulhumale’), set safety rules and keep it off public roads. That’s racing. What’s happening now isn’t skill. It’s the easiest machine, zero clutch control, zero discipline, maximum danger to people who never consented to be part of your low quality stunt. Maldivians have a short memory. The last time people got angry was after someone died. Then time passed, everyone forgot, and the same behaviour started again. Silence continues, until the next death. Then it’s suddenly “why didn’t anyone stop this?”
0:15

Pulling wheelies on a clutchless Honda commuter bike on Hulhumale-Male’ highway isn’t motorsport anywhere in the real world. Real racing requires a real motorbike, meaning a manual clutch, proper gearbox, engine braking, race grade suspension and brakes. If you want to race, do it the way the rest of the world does. Get a proper motorbike, get gov permission, use designated areas (Hulhumale’), set safety rules and keep it off public roads. That’s racing. What’s happening now isn’t skill. It’s the easiest machine, zero clutch control, zero discipline, maximum danger to people who never consented to be part of your low quality stunt. Maldivians have a short memory. The last time people got angry was after someone died. Then time passed, everyone forgot, and the same behaviour started again. Silence continues, until the next death. Then it’s suddenly “why didn’t anyone stop this?”

Hassan Kurusee

90,155 views • 8 months ago

HERMES AGENT HAS A SECOND BRAIN. 1,100+ KNOWLEDGE FILES. AUTO-LINKED. SELF-IMPROVING. GROWING EVERY NIGHT. THIS IS THE OBSIDIAN GRAPH BEHIND IT. every dot = one knowledge file (markdown) every line = one wiki-link between files every color = one category (skills, notes, decisions, sources, entities) HOW IT BUILDS ITSELF: Hermes ships with a bundled LLM Wiki skill. based on Andrej Karpathy's pattern. unlike RAG (rediscovers knowledge from scratch every query), the wiki compiles knowledge once and keeps it current. when you feed the agent a source: → it reads the content → writes a structured markdown page → auto-links to every related existing page → flags contradictions with previous entries → updates all affected pages one source in. multiple connections created. the graph grows denser with every entry. WHAT FEEDS THE WIKI: → articles and URLs you find interesting → meeting transcripts → PDF documents and research papers → conversation history from Hermes sessions → Claude Code and Codex session history → Slack logs, email threads, saved notes → YouTube transcripts → raw text dropped into a _raw/ folder the obsidian-wiki package supports multi-agent ingest from Hermes, Claude Code, Codex, OpenClaw, Pi, Windsurf, and ChatGPT exports. install: pip install obsidian-wiki obsidian-wiki setup --vault ~/wiki AUTOMATE THE GROWTH: set cron jobs to feed the wiki overnight: "every day at 9am, check for new meetings. ingest transcripts into the wiki." "every week, check arXiv for new papers in [niche]. summarize and file into the wiki." "every day, ingest today's Hermes sessions into the wiki under session-history." month 1: 50 entries. scattered. month 3: 300+ entries. cross-referenced. month 6: 1,000+ entries. the agent surfaces patterns you never searched for. WHY OBSIDIAN: the wiki is plain markdown files. no database. no lock-in. open it in Obsidian for graph view: → nodes show knowledge density → links show how ideas connect → clusters reveal your strongest domains → orphan nodes reveal gaps Hermes writes from a VPS. Obsidian reads on your laptop. obsidian-headless syncs without a GUI. agent writes from the server, you browse on your device. FOUR MEMORY LAYERS: Layer 1: memory.md + user.md (~2,200 + 1,375 chars. short-term.) Layer 2: SQLite with FTS5 (full session transcripts. searchable.) Layer 3: external providers (Mem0, SuperMemory, Honcho. optional.) Layer 4: Obsidian wiki via LLM Wiki skill (unlimited. compounding. the long-term brain.) layers 1-3 handle memory. layer 4 handles knowledge. the graph in this post is layer 4. SETUP: set in Desktop app, Dashboard, or config.yaml: WIKI_PATH=~/wiki OBSIDIAN_VAULT_PATH=~/wiki first run: Hermes asks for your domain. answer with your niche. the skill builds SCHEMA.md with tag taxonomy. after that: "index this into my wiki: [URL or text]" the wiki grows. the graph densifies. the agent gets smarter because the knowledge base got smarter. full 15 levels breakdown in the article 👇
0:11

HERMES AGENT HAS A SECOND BRAIN. 1,100+ KNOWLEDGE FILES. AUTO-LINKED. SELF-IMPROVING. GROWING EVERY NIGHT. THIS IS THE OBSIDIAN GRAPH BEHIND IT. every dot = one knowledge file (markdown) every line = one wiki-link between files every color = one category (skills, notes, decisions, sources, entities) HOW IT BUILDS ITSELF: Hermes ships with a bundled LLM Wiki skill. based on Andrej Karpathy's pattern. unlike RAG (rediscovers knowledge from scratch every query), the wiki compiles knowledge once and keeps it current. when you feed the agent a source: → it reads the content → writes a structured markdown page → auto-links to every related existing page → flags contradictions with previous entries → updates all affected pages one source in. multiple connections created. the graph grows denser with every entry. WHAT FEEDS THE WIKI: → articles and URLs you find interesting → meeting transcripts → PDF documents and research papers → conversation history from Hermes sessions → Claude Code and Codex session history → Slack logs, email threads, saved notes → YouTube transcripts → raw text dropped into a _raw/ folder the obsidian-wiki package supports multi-agent ingest from Hermes, Claude Code, Codex, OpenClaw, Pi, Windsurf, and ChatGPT exports. install: pip install obsidian-wiki obsidian-wiki setup --vault ~/wiki AUTOMATE THE GROWTH: set cron jobs to feed the wiki overnight: "every day at 9am, check for new meetings. ingest transcripts into the wiki." "every week, check arXiv for new papers in [niche]. summarize and file into the wiki." "every day, ingest today's Hermes sessions into the wiki under session-history." month 1: 50 entries. scattered. month 3: 300+ entries. cross-referenced. month 6: 1,000+ entries. the agent surfaces patterns you never searched for. WHY OBSIDIAN: the wiki is plain markdown files. no database. no lock-in. open it in Obsidian for graph view: → nodes show knowledge density → links show how ideas connect → clusters reveal your strongest domains → orphan nodes reveal gaps Hermes writes from a VPS. Obsidian reads on your laptop. obsidian-headless syncs without a GUI. agent writes from the server, you browse on your device. FOUR MEMORY LAYERS: Layer 1: memory.md + user.md (~2,200 + 1,375 chars. short-term.) Layer 2: SQLite with FTS5 (full session transcripts. searchable.) Layer 3: external providers (Mem0, SuperMemory, Honcho. optional.) Layer 4: Obsidian wiki via LLM Wiki skill (unlimited. compounding. the long-term brain.) layers 1-3 handle memory. layer 4 handles knowledge. the graph in this post is layer 4. SETUP: set in Desktop app, Dashboard, or config.yaml: WIKI_PATH=~/wiki OBSIDIAN_VAULT_PATH=~/wiki first run: Hermes asks for your domain. answer with your niche. the skill builds SCHEMA.md with tag taxonomy. after that: "index this into my wiki: [URL or text]" the wiki grows. the graph densifies. the agent gets smarter because the knowledge base got smarter. full 15 levels breakdown in the article 👇

YanXbt

34,987 views • 2 months ago

I just built a Meta ad policy checker in Claude Code that catches rejections BEFORE Meta does 🤯 Drop in your ad copy → it pulls Meta's LIVE Advertising Standards, checks every line against the actual policy text, and hands each ad a verdict: Cleared for launch, Fix before launch, or Grounded. All inside Claude Code. Perfect for media buyers and DTC brands who've had ads bounced — or an account restricted — and never got a straight answer why. If you're finding out about policy problems only after the rejection email, resubmitting the same ad and praying, losing days of delivery while the appeal sits in review, and every bounce quietly teaches Meta to trust your account a little less... This runs the review before Meta ever sees the ad: → Drop in your ad copy (one ad or a whole batch) → It reads each ad and figures out which of Meta's policies apply → Scrapes the live policy pages from Meta's Transparency Center → Flags the exact phrase that violates, with Meta's own policy quoted next to it → Rewrites the risky lines so the message survives but the violation doesn't → Renders a dashboard: every ad, every finding, every fix in one place No guessing which word killed the ad. No resubmit-and-pray loops. No stacking rejections on your account history. What you get: → A verdict on every ad before you spend a dollar → The violating phrase + the policy citation, side by side → Rewrites that keep the selling intent → A report you can hand straight to your team or client Built 100% in Claude Code. No API keys, no Meta login. I'm giving away the complete Claude skill file. Want the skill for free? > Like this post > Comment "META" And I'll send it over (must be following so I can DM)
0:18

I just built a Meta ad policy checker in Claude Code that catches rejections BEFORE Meta does 🤯 Drop in your ad copy → it pulls Meta's LIVE Advertising Standards, checks every line against the actual policy text, and hands each ad a verdict: Cleared for launch, Fix before launch, or Grounded. All inside Claude Code. Perfect for media buyers and DTC brands who've had ads bounced — or an account restricted — and never got a straight answer why. If you're finding out about policy problems only after the rejection email, resubmitting the same ad and praying, losing days of delivery while the appeal sits in review, and every bounce quietly teaches Meta to trust your account a little less... This runs the review before Meta ever sees the ad: → Drop in your ad copy (one ad or a whole batch) → It reads each ad and figures out which of Meta's policies apply → Scrapes the live policy pages from Meta's Transparency Center → Flags the exact phrase that violates, with Meta's own policy quoted next to it → Rewrites the risky lines so the message survives but the violation doesn't → Renders a dashboard: every ad, every finding, every fix in one place No guessing which word killed the ad. No resubmit-and-pray loops. No stacking rejections on your account history. What you get: → A verdict on every ad before you spend a dollar → The violating phrase + the policy citation, side by side → Rewrites that keep the selling intent → A report you can hand straight to your team or client Built 100% in Claude Code. No API keys, no Meta login. I'm giving away the complete Claude skill file. Want the skill for free? > Like this post > Comment "META" And I'll send it over (must be following so I can DM)

Mike Futia

17,399 views • 1 month ago

The Visual Studio Code insiders version that just shipped and will ship in the next few days will come with an insane amount of new capabilities. A few highlights: - You can now run sub-agents in parallel. Yes, really. I even attached a video. - Major UX improvements for sub agents, especially visible in the chat window - A new search tool wrapped as a sub-agent that iteratively runs multiple search tools: semantic_search, file_search, grep_search Which connects nicely to the point above: multiple searches running in parallel, efficiently and fast - Anthropic’s Message API is now enabled by default - You can choose the model for the cloud agent (three available, all premium) - Extended thinking support when using the Claude cloud agent This is part of the broader multi-vendor cloud support under AgentsHQ I wrote about a few weeks ago - Tasks sent to the background agent (basically the CLI tool) now always run in isolation, each with its own git worktree - In a multi-repo workspace, assigning a task to a cloud agent prompts you to choose the target repo Same behavior when opening an empty workspace with no repo - Support for building an external index for files not supported by GitHub’s default indexing - UI/UX improvements for starting new sessions and switching between local / background / cloud agents - Skills are now first-class citizens, just like prompt files, with better UX indicating when a skill is loaded - Improved API for dynamic contribution of prompt files New V2 includes skills as part of the model. Curious to see the extensions that will leverage this - Finally, initial support for showing context usage percentage per session - Skills are enabled by default - Resizable chat window and session view. Small thing, but it was driving me crazy 😁 - A new integrated browser meant to replace the old simple browser Maybe the beginning of real browser use? - Better UI/UX for token streaming in chat - Ability to index external files not supported by GitHub There’s a lot more. Some of it hasn’t fully landed yet, but everything that has is already in Insiders. The next stable release should drop in early February. As usual, I’m just shocked by the volume of features this team ships every month. After the holiday slowdown, this one is shaping up to be a wild release.
0:24

The Visual Studio Code insiders version that just shipped and will ship in the next few days will come with an insane amount of new capabilities. A few highlights: - You can now run sub-agents in parallel. Yes, really. I even attached a video. - Major UX improvements for sub agents, especially visible in the chat window - A new search tool wrapped as a sub-agent that iteratively runs multiple search tools: semantic_search, file_search, grep_search Which connects nicely to the point above: multiple searches running in parallel, efficiently and fast - Anthropic’s Message API is now enabled by default - You can choose the model for the cloud agent (three available, all premium) - Extended thinking support when using the Claude cloud agent This is part of the broader multi-vendor cloud support under AgentsHQ I wrote about a few weeks ago - Tasks sent to the background agent (basically the CLI tool) now always run in isolation, each with its own git worktree - In a multi-repo workspace, assigning a task to a cloud agent prompts you to choose the target repo Same behavior when opening an empty workspace with no repo - Support for building an external index for files not supported by GitHub’s default indexing - UI/UX improvements for starting new sessions and switching between local / background / cloud agents - Skills are now first-class citizens, just like prompt files, with better UX indicating when a skill is loaded - Improved API for dynamic contribution of prompt files New V2 includes skills as part of the model. Curious to see the extensions that will leverage this - Finally, initial support for showing context usage percentage per session - Skills are enabled by default - Resizable chat window and session view. Small thing, but it was driving me crazy 😁 - A new integrated browser meant to replace the old simple browser Maybe the beginning of real browser use? - Better UI/UX for token streaming in chat - Ability to index external files not supported by GitHub There’s a lot more. Some of it hasn’t fully landed yet, but everything that has is already in Insiders. The next stable release should drop in early February. As usual, I’m just shocked by the volume of features this team ships every month. After the holiday slowdown, this one is shaping up to be a wild release.

Oren Melamed

29,555 views • 7 months ago

Every serious Claude Code user is using this repo. if you're not, you're leaving 90% of Claude Code's power on the table. It's called claude-code-best-practice - 84 sourced tips, implementation examples for every major feature, workflow comparisons across 8 major repos, and the actual tips from Boris Cherny (creator of Claude Code) compiled in one place. Here's what's actually in it: → 84 tips organized by category -- prompting, planning, CLAUDE.md, agents, commands, skills, hooks, workflows, debugging, utilities, daily habits → best practice + implemented examples for every core concept: subagents, commands, skills, hooks, MCP servers, plugins, settings, memory, checkpointing, CLI flags → workflow comparison table -- Superpowers, BMAD-METHOD, Get Shit Done, OpenSpec, gstack, HumanLayer -- what makes each unique, how many agents/commands/skills each has → orchestration workflow -- Command → Agent → Skill pattern with a live demo → Boris Cherny tips compiled across 3 tweet threads (13 + 10 + 12 tips) and 5 podcast/video appearances → "billion dollar questions" section -- open questions about CLAUDE.md, agents vs commands vs skills, specs -- that nobody has definitively answered yet here's a few of the tips that actually change how you use it: → use subagents with "say use subagents" to throw more compute at a problem -- offload tasks to keep your main context clean → spin up a second Claude to review your plan as a staff engineer before executing → CLAUDE.md should target under 200 lines -- wrap domain-specific rules in ` ` tags so Claude doesn't ignore them as files grow → compress KV context at max 50%, not at the end -- avoid the "agent dumb zone" by doing manual /compact proactively → after a mediocre fix: "knowing everything you know now, scrap this and implement the elegant solution" was #1 trending on GitHub in March 2026. 19.7K GitHub stars. 1.7K forks. MIT license. 100% open source. (link in the comments)
0:14

Every serious Claude Code user is using this repo. if you're not, you're leaving 90% of Claude Code's power on the table. It's called claude-code-best-practice - 84 sourced tips, implementation examples for every major feature, workflow comparisons across 8 major repos, and the actual tips from Boris Cherny (creator of Claude Code) compiled in one place. Here's what's actually in it: → 84 tips organized by category -- prompting, planning, CLAUDE.md, agents, commands, skills, hooks, workflows, debugging, utilities, daily habits → best practice + implemented examples for every core concept: subagents, commands, skills, hooks, MCP servers, plugins, settings, memory, checkpointing, CLI flags → workflow comparison table -- Superpowers, BMAD-METHOD, Get Shit Done, OpenSpec, gstack, HumanLayer -- what makes each unique, how many agents/commands/skills each has → orchestration workflow -- Command → Agent → Skill pattern with a live demo → Boris Cherny tips compiled across 3 tweet threads (13 + 10 + 12 tips) and 5 podcast/video appearances → "billion dollar questions" section -- open questions about CLAUDE.md, agents vs commands vs skills, specs -- that nobody has definitively answered yet here's a few of the tips that actually change how you use it: → use subagents with "say use subagents" to throw more compute at a problem -- offload tasks to keep your main context clean → spin up a second Claude to review your plan as a staff engineer before executing → CLAUDE.md should target under 200 lines -- wrap domain-specific rules in ` ` tags so Claude doesn't ignore them as files grow → compress KV context at max 50%, not at the end -- avoid the "agent dumb zone" by doing manual /compact proactively → after a mediocre fix: "knowing everything you know now, scrap this and implement the elegant solution" was #1 trending on GitHub in March 2026. 19.7K GitHub stars. 1.7K forks. MIT license. 100% open source. (link in the comments)

Sukh Sroay

113,759 views • 4 months ago

AgentLinter is here! Is your agent sharp & secure? I built AgentLinter, a linter for and agent config files. Here's why. Whether you're vibe-coding or agent-coding, your AI's output quality comes down to one thing: how well you wrote your But managing these files properly? Way harder than it looks. 🎯 The Silent Failure Problem Vague instructions like "write good code" let the agent interpret however it wants. Output gets inconsistent, but nothing throws an error. The failure is silent. Anthropic's own docs say write "Use 2-space indentation" not "Format code properly." But as the file grows, spotting these with your eyes alone is nearly impossible. 🔐 The Security Problem People hard-code API keys and tokens directly into or and commit them, way more often than you'd think. AgentLinter stats show 1 in 5 workspaces has exposed credentials. .gitignore doesn't catch secrets buried inside markdown files. 💥 The Consistency Problem Multiple config files = contradictions. says "be a friendly assistant," says "concise, direct tone." The agent gets confused. references files that don't exist. Past 5 files, these conflicts triple. So I thought: is code. Code has ESLint. Why doesn't this have a linter? 🔍 What AgentLinter Does It diagnoses your agent config across 8 categories: 1) Structure: file organization 2) Clarity: instruction specificity 3) Completeness: missing definitions 4) Security: exposed secrets 5) Consistency: cross-file contradictions 6) Memory: session handoff 7) Runtime Config: gateway/auth settings 8) Skill Safety: dangerous shell commands & injection patterns Each scored 0–100 with concrete fix suggestions. Write "be helpful" and it tells you to specify response length, tone, and format. Find an API key? Instant CRITICAL alert to rotate. 🔒 Privacy-First & 100% Local Everything runs on your machine. Files never leave. Only the results are shared, and you can turn that off in settings. This matters — these files can contain system prompts, security rules, and personal context. Fully open source, MIT license, 100% free. 🛠️ Multi-Tool Support Works with Claude Code, Cursor, Windsurf, and Clawdbot. Detects for project mode, or clawdbot.json for agent mode and adjusts diagnostics automatically. 🚀 Get Started with one line npx agentlinter Node.js 18+, no config needed. Run it, check your score, fix what needs fixing. Happy vibe-coding & happy agent life! 🤙 Website: Github:
0:15

AgentLinter is here! Is your agent sharp & secure? I built AgentLinter, a linter for and agent config files. Here's why. Whether you're vibe-coding or agent-coding, your AI's output quality comes down to one thing: how well you wrote your But managing these files properly? Way harder than it looks. 🎯 The Silent Failure Problem Vague instructions like "write good code" let the agent interpret however it wants. Output gets inconsistent, but nothing throws an error. The failure is silent. Anthropic's own docs say write "Use 2-space indentation" not "Format code properly." But as the file grows, spotting these with your eyes alone is nearly impossible. 🔐 The Security Problem People hard-code API keys and tokens directly into or and commit them, way more often than you'd think. AgentLinter stats show 1 in 5 workspaces has exposed credentials. .gitignore doesn't catch secrets buried inside markdown files. 💥 The Consistency Problem Multiple config files = contradictions. says "be a friendly assistant," says "concise, direct tone." The agent gets confused. references files that don't exist. Past 5 files, these conflicts triple. So I thought: is code. Code has ESLint. Why doesn't this have a linter? 🔍 What AgentLinter Does It diagnoses your agent config across 8 categories: 1) Structure: file organization 2) Clarity: instruction specificity 3) Completeness: missing definitions 4) Security: exposed secrets 5) Consistency: cross-file contradictions 6) Memory: session handoff 7) Runtime Config: gateway/auth settings 8) Skill Safety: dangerous shell commands & injection patterns Each scored 0–100 with concrete fix suggestions. Write "be helpful" and it tells you to specify response length, tone, and format. Find an API key? Instant CRITICAL alert to rotate. 🔒 Privacy-First & 100% Local Everything runs on your machine. Files never leave. Only the results are shared, and you can turn that off in settings. This matters — these files can contain system prompts, security rules, and personal context. Fully open source, MIT license, 100% free. 🛠️ Multi-Tool Support Works with Claude Code, Cursor, Windsurf, and Clawdbot. Detects for project mode, or clawdbot.json for agent mode and adjusts diagnostics automatically. 🚀 Get Started with one line npx agentlinter Node.js 18+, no config needed. Run it, check your score, fix what needs fixing. Happy vibe-coding & happy agent life! 🤙 Website: Github:

Simon Kim

44,224 views • 7 months ago

I just built an influencer outreach AI agent in Claude Code 🤯 One prompt → it scrapes TikTok, finds creators in your niche, researches their content, and writes personalized outreach DMs that reference their actual videos. All inside Claude Code. Perfect for DTC brands and agencies who are still scrolling TikTok and Instagram manually, DMing creators one by one, and tracking everything in a messy spreadsheet. If you're spending hours every week searching for creators in your niche, checking follower counts, skimming their content to see if they're a fit, then writing the same generic "love your content!" DM twelve times... This agent eliminates the entire loop: → Give it a niche keyword and follower range → Scrapes TikTok via Apify and returns real creator profiles with engagement data → Filters by followers, engagement rate, and brand partnership signals → Deep-dives their recent content — what they post, what brands they already rep, their hook style → Writes a personalized outreach DM that references specific videos they've made No scrolling for hours. No copy-pasting bios into spreadsheets. No generic "collab?" DMs that get ignored. What you get: → A scored creator list with handles, followers, engagement rates, and contact info → Research briefs on each creator — content style, audience signals, brand fit assessment → Personalized pitches your team can send immediately → A brand context file that compounds — every campaign teaches the system what works Built 100% in Claude Code with Apify for scraping. I put together a full playbook with the exact skill files, brand context template, and the workflow to set this up yourself. Want the full playbook completely for free? > Like this post > Comment "AGENT" And I'll send it over (must be following so I can DM)
0:19

I just built an influencer outreach AI agent in Claude Code 🤯 One prompt → it scrapes TikTok, finds creators in your niche, researches their content, and writes personalized outreach DMs that reference their actual videos. All inside Claude Code. Perfect for DTC brands and agencies who are still scrolling TikTok and Instagram manually, DMing creators one by one, and tracking everything in a messy spreadsheet. If you're spending hours every week searching for creators in your niche, checking follower counts, skimming their content to see if they're a fit, then writing the same generic "love your content!" DM twelve times... This agent eliminates the entire loop: → Give it a niche keyword and follower range → Scrapes TikTok via Apify and returns real creator profiles with engagement data → Filters by followers, engagement rate, and brand partnership signals → Deep-dives their recent content — what they post, what brands they already rep, their hook style → Writes a personalized outreach DM that references specific videos they've made No scrolling for hours. No copy-pasting bios into spreadsheets. No generic "collab?" DMs that get ignored. What you get: → A scored creator list with handles, followers, engagement rates, and contact info → Research briefs on each creator — content style, audience signals, brand fit assessment → Personalized pitches your team can send immediately → A brand context file that compounds — every campaign teaches the system what works Built 100% in Claude Code with Apify for scraping. I put together a full playbook with the exact skill files, brand context template, and the workflow to set this up yourself. Want the full playbook completely for free? > Like this post > Comment "AGENT" And I'll send it over (must be following so I can DM)

Mike Futia

25,714 views • 6 months ago