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 suppressions, skipping tests, or weakening thresholds to reach green. This Skill records the project's quality bar as a versioned CONSTRAINTS.md file with concrete numbers and tools, then guards the diff against attempts to weaken it. ## Core Features & Use Cases - Constraint Interview & Defaults: Runs a four-question intake with sane defaults (coverage, security, performance, accessibility) and writes the answers into CONSTRAINTS.md with a stated reason for every number. - Tool-Backed Enforcement: Maps each dimension to a de facto checker (tsc, eslint, gitleaks, Semgrep, osv-scanner, Lighthouse, axe-core, Stryker) and wires them into fast/task/CI stages scoped to the diff. - Floor Guard: Ships a reference implementation that scans the diff for new suppressions, skipped tests, removed assertions, stubs, lowered thresholds, and untracked exceptions. - Use Case: Before running an autonomous build loop on a TypeScript repo, use this Skill to define an 80% changed-line coverage gate, block new eslint-disable comments, and ratchet project coverage so it can never fall. ## Quick Start Ask the agent to set up quality constraints for this project and write them into CONSTRAINTS.md with enforced coverage and security checks.