Loading…
Expert audit of a project's design system across TWO dimensions — (1) clean codebase and (2) AI-native structure (can an LLM read it and build on-brand reliably). Scores explicit criteria with evidence, then returns turnkey fixes that point to the design-system-template files to copy. Use when the user says "audit my DS", "is my design system AI-native", "check/score my design system", "what's missing", "am I ready to build UI with Claude here", or when onboarding an existing or new project to the design system. Most projects already have code — the job is to diagnose and fill the gaps using the template as the model, not rebuild from scratch.
ds-audit is an agent skill entry in ChatHome Skills, sourced from GitHub Skill Search and scored 58/100. # DS Audit — clean codebase + AI-native, with turnkey fixes Two questions, scored separately: 1. **Is the codebase clean?** — no hardcoded values, one canonical. As an agent skill, it packages a reusable instruction set that AI coding agents such as Codex and Claude Code can load to perform this task without hand-written glue code. ChatHome Skills discovered this entry through its daily ingest of official registries and GitHub discovery queries, and re-verifies repository facts, freshness signals, and install metadata on every run. The quality score weighs official-registry presence, a working install command, license clarity, GitHub star trajectory, and repository freshness — the full formula is on the Sources page. The install command above is ready to copy. Review the last-pushed date and repository status before adding ds-audit to a production agent workflow; the snapshot facts below are point-in-time values from the most recent ingest.
codex skill install eFounders/design-system-templateReview the upstream source before running this command.
Scan coverage: Install metadata and the indexed document body.
Automated signals from install metadata and a bounded skill body — not a full code security audit and not a recursive source or dependency review.
# DS Audit — clean codebase + AI-native, with turnkey fixes Two questions, scored separately: 1. **Is the codebase clean?** — no hardcoded values, one canonical component per role,