HN Explorer

Show HN: AI SDLC Scaffold, repo template for AI-assisted software development (github.com)

27 points by pangon ↗ HN
I built an open-source repo template that brings structure to AI-assisted software development, starting from the pre-coding phases: objectives, user stories, requirements, architecture decisions.

It's designed around Claude Code but the ideas are tool-agnostic. I've been a computer science researcher and full-stack software engineer for 25 years, working mainly in startups. I've been using this approach on my personal projects for a while, then, when I decided to package it up as scaffold for more easy reuse, I figured it might be useful to others too. I published it under Apache 2.0, fork it and make it yours.

You can easily try it out: follow the instructions in the README to start using it.

The problem it solves:

AI coding agents are great at writing code, but they work much better when they have clear context about what to build and why. Most projects jump straight to implementation. This scaffold provides a structured workflow for the pre-coding phases, and organizes the output so that agents can navigate it efficiently across sessions.

How it works:

Everything lives in the repo alongside source code. The AI guidance is split into three layers, each optimized for context-window usage:

1. Instruction files (CLAUDE.md, CLAUDE.<phase>.md): always loaded, kept small. They are organized hierarchically, describe repo structure, maintain artifact indexes, and define cross-phase rules like traceability invariants.

2. Skills (.claude/skills/SDLC-*): loaded on demand. Step-by-step procedures for each SDLC activity: eliciting requirements, gap analysis, drafting architecture, decomposing into components, planning tasks, implementation.

3. Project artifacts: structured markdown files that accumulate as work progresses: stakeholders, goals, user stories, requirements, assumptions, constraints, decisions, architecture, data model, API design, task tracking. Accessed selectively through indexes.

This separation matters because instruction files stay in the context window permanently and must be lean, skills can be detailed since they're loaded only when invoked, and artifacts scale with the project but are navigated via indexed tables rather than read in full.

Key design choices:

Context-window efficiency: artifact collections use markdown index tables (one-line description and trigger conditions) so the agent can locate what it needs without reading everything.

Decision capture: decisions made during AI reasoning and human feedback are persisted as a structured artifact, to make them reviewable, traceable, and consistently applied across sessions.

Waterfall-ish flow: sequential phases with defined outputs. Tedious for human teams, but AI agents don't mind the overhead, and the explicit structure prevents the unconstrained "just start vibecoding" failure mode.

How I use it:

Short, focused sessions. Each session invokes one skill, produces its output, and ends. The knowledge organization means the next session picks up without losing context. I've found that free-form prompting between skills is usually a sign the workflow is missing a piece.

Current limitations:

I haven't found a good way to integrate Figma MCP for importing existing UI/UX designs into the workflow. Suggestions welcome.

Feedback, criticism, and contributions are very welcome!

15 comments

[ 3.1 ms ] story [ 46.2 ms ] thread
zihotki
Please show your benchmarks and evals to prove that your template actually makes any sense and doesn't waste the credits/tokens/requests/etc.
gzoo
Figma would make this even more amazing but great work!
gzoo
Have you seen Google Stitch? I have a feeling Figma is going to get a run for their money.
grapheneposter
I built a big brain download of how I think the day to day SDLC rolls now and used it to teleport my ideas into any harness as needed.
milkoslavov
We have built something similar for our SDLC, but it is based on Claude Code slash commands:

  - /tasks:capture — Quick capture idea/bug/task to tasks/ideas/

  - /tasks:groom — Expand with detailed requirements → tasks/backlog/

  - /tasks:plan — Create implementation plan → tasks/planned/

  - /tasks:implement — Execute plan, run tests → tasks/done/

  - /tasks:review-plan — Format plan for team review (optionally Slack)

  - /tasks:send — Send to autonomous dev pipeline via GitHub issue

  - /tasks:fast-track — Capture → groom → plan → review in one pass

  - /tasks:status — Kanban-style overview of all tasks
Workflow: capture → groom → plan → implement → done (with optional review-plan before implement, or send for autonomous execution).
klabetron
Thoughts on publishing an example output perhaps in another repo? Perhaps just the first two phases? Would be interesting to see what the output looks like practically speaking (before committing to using it for a project).
pangon
You are totally right, I should have done that from the start. I have just made public a repo I used to test that version of the scaffold: https://github.com/pangon/local-TTS-web-app

It's currently in the coding phase, so the requirements definition and the design phase is done.

You can see the repo yourself, the most interesting artefacts generated are from the ojectives phase and are indexed in this file: https://github.com/pangon/local-TTS-web-app/blob/main/1-obje...

Another interesting output of the scaffold skill is the execution plan, organized in phases with milestones, where the new capabilities delivered can be tested after completing a phase: https://github.com/pangon/local-TTS-web-app/blob/main/3-code...