← ClaudeAtlas

design-system-coveragelisted

Grade the project's design-system contract for completeness and produce a coverage inventory every downstream design-test skill references. Analog of stride-threat-model.
Eliyce/paqad-ai · ★ 4 · AI & Automation · score 76
Install: claude install-skill Eliyce/paqad-ai
## What It Does Grades `docs/instructions/design-system/` for completeness, produces a coverage inventory, and emits the **tier** (`missing | bare | adequate | strong`) the rest of the workflow uses to decide whether to stop, warn, or proceed in strict mode. Runs as Step 0 (readiness gate) and as the first skill in Step 1 — every downstream skill consumes this inventory. ## Use This When Use this as the **first skill in every design-test run**. The tier it emits gates the entire workflow. Never skip it; never run other design-test skills without it. ## Inputs - Read every file under `docs/instructions/design-system/` (typically `tokens.md`, `components.md`, `accessibility.md`, `motion.md`, `patterns.md`, `responsive.md`). - Read `references/contract-clauses.md` before grading. ## Procedure The decisions in steps 1–3 are deterministic — drive them with the scripts in `scripts/` rather than re-deriving the logic from prose each run. 1. Run `scripts/list-contract-files.sh` to enumerate which contract files exist and which are empty/stub. 2. For each file, run `scripts/count-clauses.sh <file>` to count contract clauses (the file emits `<path>\t<count>` and skips headings, blank lines, frontmatter delimiters, and lines inside fenced code blocks). Concatenate the rows. 3. Pipe the concatenated counts into `scripts/derive-tier.sh` — it emits a single `tier=<missing|bare|adequate|strong>` line. This is the gate decision: don't second-guess it. 4. Emit the coverage inventory p