Context Engineering for Coding Agents
Package the right files, constraints, architecture notes, and acceptance checks before asking a coding agent to edit a repo.
normalize from pbakaus/impeccable: Analyze and redesign features to match your design system standards and ensure consistency.
normalize is a reusable agent skill listed on skills.sh under pbakaus/impeccable. skills.sh rank #201, installs 54.6K, GitHub stars 29.9K, first seen Mar 4, 2026.
Analyze and redesign features to match your design system standards and ensure consistency. Requires upfront design system discovery—searches for documentation, UI guidelines, and design tokens before making changes; asks clarifying questions rather than guessing at principles Systematically normalizes typography, color, spacing, components, motion, responsive behavior, and accessibility across eight key dimensions Prioritizes UX consistency and usability over visual polish; replaces custom implementations with design system equivalents and removes hard-coded values in favor of design tokens Includes cleanup phase to consolidate reusable components, remove orphaned code, and verify quality against repository standards
SKILL.md and only load extra files referenced by that skill.npx skills add https://github.com/pbakaus/impeccable --skill normalizeIs normalize an agent, a prompt, or a skill?
It is a skill: a reusable package of task-specific instructions and supporting files that an agent can load when the user's request matches the workflow.
Should I install it automatically?
Only after checking the repository, install command, audit status, and whether the user wants this capability in the current agent environment.
What makes it useful for AIDreamHub users?
It helps users discover practical agent capabilities from the open skills ecosystem and compare them by task, source, install count, and operational risk.
npx skills add https://github.com/pbakaus/impeccable --skill normalizenpx skills add https://github.com/pbakaus/impeccable --skill normalizePackage the right files, constraints, architecture notes, and acceptance checks before asking a coding agent to edit a repo.
Manage prompts like production code with versions, eval sets, release notes, and rollback criteria.
Design agent workflows that use MCP tools safely, with permissions, secrets, audit logs, and human approvals.
Write reusable agent skills with clear triggers, workflows, assets, quality gates, and safe boundaries.