Writing GitHub Copilot skills in Markdown

🚀 Why did GitHub build their official MCP Server in Go? If you haven’t seen it yet, GitHub just open-sourced their MCP Server — the official Model Context Protocol server that lets AI agents, Copilot, Cursor, Claude Desktop, and other tools directly read repos, manage issues/PRs, analyze code, monitor workflows, and automate like never before. Repo: https://lnkd.in/ezzwZDQr One of the smartest moves? They wrote it in Go. Here’s why Go was the perfect choice (and why it matters for the future of AI tooling): - Insane concurrency with zero drama AI agents fire off dozens of tool calls in parallel. Go’s goroutines + channels make handling streaming MCP sessions, HTTP events, and GitHub API calls feel effortless — without the complexity of threads or async callbacks in other languages. - Production-grade performance & efficiency Low memory footprint, blazing-fast startup, and compiles to a single static binary. Perfect for both the cloud-hosted version (https://lnkd.in/eKKd4fee) and the self-hosted Docker image. No heavy runtimes, no cold starts, just reliable speed. - Simplicity and reliability at scale Go’s standard library already gives you world-class HTTP, JSON, and crypto support. The codebase stays clean and maintainable — exactly what you want when you’re exposing GitHub’s entire platform to millions of AI interactions. - Battle-tested at GitHub They already ship the GitHub CLI and multiple internal services in Go. Reusing the same language, tooling, and operational knowledge just makes sense for a new critical piece of their AI infrastructure. In short: GitHub didn’t pick Go for hype — they picked it because it’s the language that lets them deliver fast, secure, and scalable AI context to developers without compromise. This is a master class in choosing the right tool for the job when building the next generation of developer platforms. 👉 Try it yourself: https://lnkd.in/ezzwZDQr #GitHub #GoLang #Golang #MCP #ModelContextProtocol #AI #Copilot #DevTools #OpenSource #SoftwareEngineering

Just Released! WasteLens AWS, a lightweight open source Python tool that scans an AWS account for a small set of common cost-waste signals and generates a simple HTML report with estimated monthly savings. I will be doing custom builds by request (Email: williamshehan@gmail.com for a quote) Live AWS scanning using boto3 HTML report generation Estimated monthly savings summary Windows-friendly install and run scripts Automated test suite Readable local logs https://lnkd.in/gKU-93iN

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

If you were a student, GitHub Education Pack was the cheat code. Free domains, free hosting, free everything. You didn't even have to think about costs while learning. But once you're past that stage and actually building things, nobody talks about what comes next. There's this thing called the 𝗔𝗜 𝗘𝗻𝗴𝗶𝗻𝗲𝗲𝗿 𝗣𝗮𝗰𝗸 𝗯𝘆 𝗘𝗹𝗲𝘃𝗲𝗻𝗟𝗮𝗯𝘀. Not free, but not "burn your savings" either. It's a bundle of credits and discounts across 50+ tools that you'd probably end up paying full price for anyway. Some examples of what's inside: Notion Business Plan free for 6 months (that's worth $12k alone). $2000 in E2B credits for running code sandboxes. $1000 in Daytona compute credits. Neon serverless Postgres, Sentry, Firecrawl, Upstash, n8n, Railway, Resend. Tailscale Enterprise for a full year. HuggingFace Pro for 6 months. The total value is honestly stupid if you add it up. See, the real problem most builders face isn't "I don't know what to build." It's "I know what to build but every tool costs money before I've made a single rupee from it." This pack doesn't solve everything but it buys you 3-6 months of breathing room to actually ship something without watching your wallet bleed on subscriptions. You just sign in with GitHub and claim what you need. No forms, no "schedule a demo," no sales calls. If you're past the learning phase and actually building, this is worth 10 minutes of your time. 𝗮𝗶𝗲𝗻𝗴𝗶𝗻𝗲𝗲𝗿𝗽𝗮𝗰𝗸.𝗰𝗼𝗺

I wrote down everything I wish someone had told me on day one with GitHub Actions. Stop using the log viewer. Break the push-wait-fail loop. Let Copilot write the YAML. And 6 other patterns that'll save you hours. https://lnkd.in/eh5SgUwt

Is GitHub something you’ve been meaning to get started with for a while but keep putting off? When most tutorials are aimed at developers rather than people working in research, I know that initial learning curve is daunting and we rarely have the time to sit down and parse out the information needed.  To help with this, I’ve put together a simple guide to introduce GitHub from a more academic perspective and to help with getting set up. It covers: • what GitHub actually is • the key bits of jargon • how it fits into working with R (including setup) • how it can be used across a local machine and an HPC Hopefully I can make Github feel a bit more approachable and convince you its much easier that it looks! 🔗https://lnkd.in/e8KP-cTb If you do end up using GitHub as a result of this guide, I’d love to hear about it. And if you have any Github tips or tricks, please share them below 🙂

From Microsoft Mission Critical Blog articles, Getting Started with GitHub Copilot SDK, by anishekkamal "GitHub Copilot has been a staple in developer workflows for a while — it suggests code, completes functions, and generally keeps you from looking..." https://lnkd.in/eJ_Cn2Ym

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

Just published a new open-source tool to GitHub. Claude Code has no built in way to track how many tokens you are burning across sessions, so I built one. It is a two-file setup. A Python server reads the JSONL session logs Claude Code writes to ~/.claude/projects/ and serves the data to a local browser dashboard. It breaks down input, output, cache write, and cache read tokens per session and calculates estimated cost using current Sonnet 4 rates. The whole thing auto-refreshes every 30 seconds and exports to CSV. No external dependencies, no cloud, nothing leaves your machine. Two features already in the pipeline. First is a configurable token budget alert that warns you in the dashboard when you cross a daily or monthly threshold. Second is an n8n workflow that pulls from the local API and delivers a usage digest by email on whatever schedule you want. #claudecode #aitools #anthropic #ITAutomation #DeveloperTools #opensource

I automated my standups with 100 lines of Python and a Slack webhook Every morning: open Slack, try to remember what I did yesterday, write something vague like "continued work on feature." Everyone nods. Nobody learned anything. So I built an MCP server that lets Claude read my git history across all my repos. Then I added a Slack webhook and a cron job. Now at 9am every weekday, a formatted standup drops into #standups automatically. The team can read it, edit it, or add context before the meeting. What it actually posts:  → 12 commits across 3 repos  → +10,897/-1,397 lines, 39 files changed  → Broken down by project with commit messages  → Monday mornings auto-cover the weekend (--days 3)  Three tools, ~100 lines of Python:  - git_standup - scans repos, returns formatted report  - post_to_slack - posts via Incoming Webhook  - git_repos - lists what repos it can see Or ask Claude directly: "what did I do this week?" and "post it to Slack." Also runs as a cron job for zero-touch daily posts: 0 9 * * 1-5 uv run python -m git_standup_mcp.cron My team loves it. Standups went from "uh, I worked on stuff" to actually knowing what everyone shipped. And anyone can edit the post before the meeting if the commit messages don't tell the full story. Took about 15 minutes to build. MCP just hit 97 million installs - if you haven't built one yet, this is a good first project. Code: https://lnkd.in/dYiXT_uy #buildInPublic #MCP #Python #DevTools #AIAgents #OpenSource