SuperML
← All issues

Inside smart-sdlc: The Skill-First Agentic Framework That Turns Copilot and Claude Into a Full SDLC Team

smart-sdlc is a markdown-only agentic SDLC framework that runs inside GitHub Copilot, Claude, or any AI assistant — six personas (Aria, Rex, Nova, Sage, Lead, Scout), six phases, zero runtime. Here's why the 'skill-first, no platform' bet is interesting.

Hi there,

Most 'agentic SDLC' announcements this year have been about new platforms — Duo, Copilot Workspaces, GitLab's new orchestrator, pick one. smart-sdlc from superml.dev goes the other direction: zero runtime, no platform, just markdown skill files your existing AI assistant (Copilot, Claude, Cursor — any of them) reads and activates on demand. Six personas, six SDLC phases, and a two-phase setup that separates team-wide config from personal workspace. I dug into it and wrote up what's different.

🔥 Featured Post

Inside smart-sdlc: The Skill-First Agentic Framework That Turns Copilot and Claude Into a Full SDLC Team

  • smart-sdlc is explicitly "a standalone AI-driven agile development framework that works natively inside GitHub Copilot, Claude, or any AI coding assistant" — no external runtime, no daemon, no new IDE to install.
  • Six personas cover the full lifecycle: Aria (Product/BA), Rex (Architect), Nova (Developer), Sage (Modernization), Lead (Team Lead/PM), and Scout (Code Archaeologist) — each addressable as @sml-agent-* inside Copilot Chat.
  • Six numbered phases — from 0-relearn (codebase onboarding) through 5-modernize (legacy analysis) — plus core utilities and an integrations layer for JIRA, Confluence, GitHub, GitLab, and Azure DevOps via REST or MCP.
  • Two-phase setup separates concerns: npx @supermldev/smart-sdlc init configures the team once (committed), npx @supermldev/smart-sdlc persona sets up each developer's individual workspace (gitignored).
  • The "meetings" command — npx @supermldev/smart-sdlc meeting — generates structured context prompts that bring multiple personas into a single AI session for design reviews and sprint planning.

Read the full post →

📚 In Case You Missed It

AI's Trust Test: Surgical Robots, Broken Benchmarks, and the EU's 100-Day Countdown — NVIDIA's healthcare physical AI stack (Open-H, Cosmos-H, GR00T-H, Rheo) ships into real operating rooms, Berkeley researchers prove the top 8 agent benchmarks can be hacked, and the EU AI Act deadline is now 103 days away. Trust is the new frontier.

The Silicon Decoupling: Meta's 1GW MTIA, OpenAI's $20B Cerebras Deal, and AI's Quiet Escape From Nvidia — Meta's 1-gigawatt Broadcom MTIA deal, OpenAI's $20B Cerebras contract, and Perplexity's Personal Computer on Mac — three stories, one pattern: AI compute is decoupling from Nvidia and from the cloud.

Human-Led, AI-Accelerated: Why the Winning Stack in 2026 Isn't Fully Autonomous — Gartner expects 40% of agentic-AI projects cancelled by 2027 and production agent reliability still sits near 25% failure — but the 'human-led, AI-accelerated' stack is quietly winning across coding, research, ops, and content. Here's the pattern, the evidence, and how to design for it.

More posts dropping every day. Stay curious.

— Bhanu @ superml.dev