Denis Voituron’s Post

Manage agent skills with GitHub CLI Agent skills are the new way to give your agents super abilities !! GitHub is launching gh skill, a new command in the GitHub CLI that makes it easy to discover, install, manage, and publish agent skills from GitHub repositories. Skills are portable, reusable packages of instructions, scripts, and resources that extend the specialized capabilities of AI agents. Unlike generic instructions, skills allow an agent to become a "specialist" in a specific domain—such as legal workflows, data analysis, or debugging—by bundling complex procedural knowledge into a modular format. https://lnkd.in/g_wvBcrs

Over the past few months I've used Cursor, Claude Code, and GitHub Copilot side by side on the same projects. Each is pretty good at different things, but they share one annoying trait: every one of them wants to read your skills, slash commands, and rules from a different folder. After the third time I caught myself copy-pasting a skill between .cursor/, .claude/, and .github/ (and inevitably missing something), I built a small fix to keep the agents in sync. The idea is simple: - One canonical .agents/ folder at the root of your repo holds every skill, command, and rule. - A tiny sync script mirrors it into the exact paths each tool expects. - No symlinks (which break on Windows without Developer Mode and trip Cursor's symlink bug anyway), no runtime dependency, no git hooks. - Windows PowerShell and macOS/Linux bash are both supported. The repo ships with a small hello-world demo skill you can use to verify all three agents are picking up the same source, then delete once you're set up. If you're juggling multiple AI coding agents in a single workspace, this might save you an afternoon of frustration. MIT licensed and open to feedback. https://lnkd.in/gizgM_Nd #AI #DeveloperTools #OpenSource #Cursor #ClaudeCode

Found a great resource for those on a GitHub Copilot journey - no matter what UI you put on top - gravity always seems to pull back to the CLI/"Command Line" - the UI that's stood the test of time :) - Quick Start - First Steps - Context and Conversations - Development Workflows - Create Specialized AI Assistants - Automate Repetitive Tasks - Connect to GitHub, Databases & APIs - Putting It All Together https://lnkd.in/ec4hj5Bg #GitHub

I reported a bug to GitHub. They fixed it in 2 days—then revamped their entire extension system. Here's what happened: While using GitHub Copilot CLI's extension system, I discovered a critical issue: creating a hook in an extension would override all global hooks. This broke my hook flows—the system I use to harden security across all my repositories. So I filed an issue. Within one week: • Root cause identified • Fix shipped to production • Complete extension system overhaul released The new capabilities are significant: → Custom slash commands now supported in the SDK → UI elicitation dialogs for structured user input → In-session management via /extensions command → Multi-language SDK support (Node.js, Python, Go, .NET) → Hot reload without full session restart This isn't just a bug fix. It's a signal. GitHub is treating Copilot CLI extensions as a first-class extensibility platform. For teams building internal tooling, security enforcement, or custom workflows—this changes the game. The speed of iteration here is remarkable. From power-user secret to documented, multi-language platform in 9 days. We're entering an era where developer feedback directly shapes the AI tools we use daily. If you're not experimenting with Copilot CLI extensions yet, now is the time. Full story in the video. Link in comments. #GitHubCopilot #DeveloperExperience #DevTools

GitHub shipped `gh skill`, a new CLI command for discovering, installing, and publishing agent skills. Skills are portable bundles of instructions, scripts, and context that teach AI agents how to do specific tasks. The mechanics are simple: `gh skill install` pulls a skill from a GitHub repository into your environment, `gh skill publish` shares one you've built. There's a discovery layer so you're not hunting for things by URL. The skills command makes it something you can install, version, and share systematically. If you want something closer to a full dependency manifest for agent config — skills, instructions, MCP servers, plugins all declared in a lockfile, APM is a great, comprehensive option and is worth a look alongside this. - gh skill: https://lnkd.in/gDkZ9HmV - microsoft/apm: https://lnkd.in/gsNFs-4P

GitHub’s new gh skill command is more important than it looks. Not because developers needed one more CLI command. Because it turns agent behaviour into something you can install, pin, update, and audit like software. That is a bigger shift than it sounds. A lot of useful know-how in AI coding workflows still lives in prompts, wiki pages, or tribal memory inside one team. Skills package that know-how into portable units with instructions, scripts, and resources that can move across hosts like Copilot, Claude Code, Cursor, Codex, and Gemini CLI. The part I like most is the boring part: versioning. Git tags. Tree SHAs. Immutable releases. Pinning. If skills shape how an agent works, treating them like unversioned snippets was never going to scale. I think this creates a new layer in the stack: • models generate • tools execute • skills encode repeatable working methods That middle layer is where a lot of durable advantage will sit. The teams that get the most from coding agents will not just pick the best model. They will build the best skills library for how they test, review, document, migrate, and run software. 🛠️ That is a much better asset than prompt folklore. 🔗 https://lnkd.in/g3nWMRXk #AIAgents #DeveloperTools #GitHubCLI #SoftwareEngineering #AIEngineering

13,800 installations. 500 stars on GitHub. 67 Discord members. All in just 14 days. I am still trying to process these numbers... When I released the lean-ctx engine two weeks ago, my goal was simple: I wanted to stop the massive "token burn" in AI coding and see if I could make the whole process more efficient and sustainable. The feedback from these first 13,000+ users has been incredible, but it also highlighted a frustrating bottleneck. I’ve been using lean-ctx as an MCP server and via shell hooks with tools like Cursor and Claude Code. It works, but it feels like there is a limit to what an external tool can achieve. These platforms are essentially "black boxes." They hard-code system prompts and lock the model's parameters, meaning I have zero control over how the LLM actually operates. Even with perfect context filtering, the model doesn't always follow instructions because the third-party interface gets in the way. I was still paying for "noise" simply because I couldn't reach the engine inside. This realization led me to a new question: What if I didn't have to fight against a third-party interface? What if I built a coding engine where context intelligence is baked directly into the binary? I decided to build exactly that. I am calling it LeanCTL. It is a CLI built from scratch in Rust. By moving away from external bridges and compiling the compression logic directly into the heart of the tool, everything changed. In my tests—running against local models and various APIs—I am seeing 60% to 85% token savings without any drop in code quality. In some scenarios, the savings even reach 95%. The most important feature for me is Thinking Steering. Instead of letting the model run at full power for every small change, LeanCTL analyzes the prompt first. If I am just fixing a typo, it constrains the thinking budget. If I am debugging a complex architectural flaw, it scales that budget up. For the first time, I feel like I am actually steering the model instead of just watching it burn through my credits. I’m moving away from trying to patch the gaps in other people's tools. I just want to build the environment I’ve always wanted to work in. The first beta is now live at https://leanctl.com.

GitHub Copilot Pulls Drawstring On Tighter Developer Usage Limits GitHub Copilot is popular. The AI-powered code completion tool (originally developed by GitHub and OpenAI) works to give software application developers a so-called “AI pair programmer” buddy that offers suggested code snippets and (when called upon) entire functions – and it happens directly within an engineer’s Integrated Development Environment (IDE) of choice. All of which means that GitHub Copilot isn’t just popular in terms of total usage; the tool is reporting an increase in patterns of high concurrency (individual developers performing similar operations, but more likely different developers requesting the same types of functions) and intense usage among power-users....

Three GitHub repos blew up this week. All three solve problems you probably have right now. 1. microsoft/markitdown Converts PDFs, Word docs, HTML, and images into clean Markdown. If you're building anything with LLMs and need to feed documents into a pipeline, this replaces your messy parsing scripts. One install. Works. 2. coleam00/Archon Defines your AI coding workflow in YAML. Think GitHub Actions but for coding agents. Plan, implement, validate, review, PR. Same steps every time. No more "I got different results than yesterday." Each run happens in an isolated git worktree so nothing bleeds across tasks. 3. multica-ai/multica If you're running multiple Claude Code or Codex sessions and manually switching terminals to track progress, Multica treats them like actual teammates. They claim tasks, report blockers, share skills across the team. Your code stays local. Their servers only coordinate state. None of these require you to change how you work. They slot into what you're already doing and remove the friction you've been tolerating. All three are open source. #AIAssistedDevelopment #GenAI #DeveloperTools #OpenSource #GitHubTrending

Something unexpected I had to do recently... GitHub has been flaky for a few weeks. Short outages, actions stuck in queue... Just unreliable enough to waste your afternoon. The worst part is the first 30 minutes where you're sure it's you. You rewrite the command. Check your git config. Re-auth. Wonder if you broke something earlier. Then you finally open status.github.com and see a red screaming banner 🤦♂️. Looks like AI coding has quietly pushed up the load on all of these tools. More code, shipped faster, through the same few providers - GitHub, Vercel, OpenAI, Anthropic. Incidents happen more often, and they eat more of your day when they do. I set up notifications for Claude a while back and it felt natural. You expect an AI API to have hiccups. But a GitHub status alert? I wouldn't have guessed I'd need one a year ago. That's why we had to integrate more status updates with Slack recently at LowCode Agency to stay up to day with these outages.