system-benchmark

# System Benchmark A skill for benchmarking a design system against industry standards and comparable public systems, producing a qualitative comparison with specific reference points that answer: "How does our system compare to what good looks like?" **Output type:** Proposal only. This skill produces analysis and comparisons. It does not make changes. It produces a benchmark report with findings, comparison context, and prioritised improvement areas. --- ## Before you begin: verify references Before doing anything else, confirm that every file listed in this skill's frontmatter `references:` field exists at its relative path from this SKILL.md. If any are missing, stop — the install is incomplete. This usually means a third-party installer (for example `npx skills install`) flattened the skill into a standalone folder and dropped the repo-root `knowledge-notes/` directory this skill depends on. Tell the user to reinstall using a supported method from `1-INSTALL.md` (git clone, or the `.plugin` bundle in Cowork) and to run `verify-install.sh` from the install root to confirm the fix. Only proceed without the references if the user explicitly says to — and if they do, state clearly in your output that it was produced in degraded mode without the pack's reference material. ## Why this exists System-health tells you if your system is healthy on its own terms. But it cannot answer: "Is our token architecture actually good? What do systems we admire look like at this layer...