Files
ai-for-dummies/hands-on/rules
Marcos Paulo f526a42ddd feat(hands-on): add guardrails rules lab and wire into docs
- New hands-on/rules/ interactive page: five toggleable rule sources
  (AGENTS.md, gate-discipline skill, Husky pre-commit, check-ui-contract
  enforcer, commitlint) rebuild a ruled prompt live against a naive prompt.
- Visual system mirrors hands-on/starter (same palette, vanilla JS).
- index.html hands-on section now links both labs.
- docs/operations-guide.md gains a 'Hands-on rules lab' subsection.
- README project structure lists the new lab.
- verify.mjs passes content, interaction, and standalone checks for both labs.
2026-09-02 15:30:45 +00:00
..

Hands-on · Rules

A tiny, zero-dependency demo showing how rule sources reshape the same prompt.

Run

Open index.html directly. No build, no server, no npm install.

What it shows

  • Five rule sources, taken from a real monorepo (netcracker/interview):
    • AGENTS.md — repo-wide instruction file.
    • .agents/skills/gate-discipline/SKILL.md — skill body loaded on demand.
    • .husky/pre-commit — git hook that runs other enforcers.
    • scripts/check-ui-contract.mjs — custom CLI enforcer (ratchet).
    • commitlint.config.cjs — commit-msg linter.
  • Each rule has an on/off switch. Toggling a rule prepends its body to the ruled prompt.
  • EN ↔ PT toggle keeps both languages useful.
  • "Copy ruled prompt" copies the current ruled-prompt text to clipboard.
  • Responsive on mobile, Full HD, and 4K (one column under 720 px).

Mirror of /hands-on/starter

Same visual system (--paper, --ink, --blue, --gold), same vanilla JS pattern, same single-file layout. Drop-in alongside the starter page under hands-on/rules/.

Token budget

Page weight: ~5 KB total, no framework, no fetch.