What problem does it solve? AI coding agents produce more code than anyone reviews, and without a written quality bar they quietly lower standards — adding @ts-ignore suppressions, skipping tests, or weakening thresholds to get checks green. This Skill turns your project's quality bar into a written, mechanically enforced contract that outlives any single session. ## Core Features & Use Cases - Structured constraint interview: Four questions with sane defaults capture which dimensions matter (coverage, security, performance, accessibility, architecture) and produce a working config even when the user has no numbers in mind. - CONSTRAINTS.md generation: Writes a repo-root contract with an always-enforced floor, numbered dimensions mapped to de facto tools (Semgrep, gitleaks, osv-scanner, Lighthouse, axe-core), ratchets for unenforced metrics, and tracked exceptions with owners and expiry dates. - Floor guard reference implementation: Ships a diff-scoped Node script that detects the five bar-lowering moves — weakened thresholds, easier tests, silenced checkers, unfinished stubs, and surprise exceptions — with clean exit codes. - Use Case: Before running an autonomous build loop on a TypeScript project, use this Skill to interview the team, write CONSTRAINTS.md with an 80% changed-line coverage gate and security scanning, and wire fast/task/full check stages into the lifecycle so the agent cannot ship code that lowers the bar. ## Quick Start Ask the agent to set up quality constraints for this project and write a CONSTRAINTS.md with enforced coverage and security gates.
