ai-sdlc-starter
CLAUDE.md1 starsChanged 58 days agoMITView on GitHub
One-command scaffolder for Anthropic's AI-Native SDLC playbook, plus its landing page. - UI work (anything in index.html, assets/, or any new page): invoke the design-system skill first and follow design-system/DESIGN.md. Style only with tokens from design-system/tokens.css and recipes from design-system/components.css. - To change the design language from a reference site: /design-system <url>. - Scripts: init.sh and init.ps1 must produce byte-identical files. Change both together. Keep them ASCII-only and dependency-free. - Bump VERSION and the version string inside both scripts together,…
In this repository2 other files it gives its agents.
- design-systemSkill
- extract-designSkill
The file
Files
ai-sdlc-starter
One-command scaffolder for Anthropic's AI-Native SDLC playbook, plus its landing page.
init.sh/init.ps1- the scaffolders.VERSION- current release.index.html,assets/- landing page, served by GitHub Pages from the repo root.design-system/- UI rules and tokens for every page in this repo.
Rules
- UI work (anything in
index.html,assets/, or any new page): invoke thedesign-systemskill first and followdesign-system/DESIGN.md. Style only with tokens fromdesign-system/tokens.cssand recipes fromdesign-system/components.css. - To change the design language from a reference site:
/design-system <url>. - Scripts:
init.shandinit.ps1must produce byte-identical files. Change both together. Keep them ASCII-only and dependency-free. - Bump
VERSIONand the version string inside both scripts together, then tagv<VERSION>. - CI (
.github/workflows/scaffold-test.yml) runs both scripts on Linux, macOS and Windows and diffs the output. Keep it green.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

