cellm/skills/dse-audit/SKILL.md
Audit the CELLM Design System Engine for quality, coverage, and codebase alignment. Use when: 'audit DSE', 'check design system', 'are UI components following DSE decisions', 'review design system completeness'.
npx skillsauth add murillodutt/cellm cellm/skills/dse-auditInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Review the design system for decision quality, coverage gaps, and code alignment.
dse_search("*") with each type filter to enumerate all entities| Check | Method | Pass Criteria | |-------|--------|---------------| | Decision coverage | Count entities with empty decisions[] | Zero empty decisions | | ATOM format | Verify intent readable without parenthetical | Each decision expresses intent, not just implementation | | Vocabulary | Grep decisions for raw Tailwind (text-gray-, bg-gray-) | Zero raw Tailwind in decisions — use semantic (text-dimmed, bg-muted) | | L2 purity | Check decisions don't duplicate framework docs | No "UButton accepts variant prop" style L1 content | | Token completeness | Check semantic colors defined | All 6 core colors present | | Code alignment | Grep .vue files for hardcoded colors | Zero hardcoded hex in components | | Avoid compliance | Check .vue files against avoid rules | No violations found |
DSE Audit Report — {project}
| Finding | Severity | Count |
|---------|----------|-------|
| Entities without decisions | medium | 12/49 |
| Hardcoded hex colors in .vue | high | 3 files |
| Missing semantic tokens | low | 0 |
.vue files — this is a read-only audit, do not "fix" alignment issues automatically.data-ai
Prose override — temporarily disable quantization and respond in readable prose. Use when relational density matters, for safety-critical explanations, onboarding handoffs, or when token economy is not the priority.
development
Govern explicit weekly Super PRs or maintainer-requested PR merges. Evaluates a 10-criterion readiness checklist and performs governed merge only when a user-requested PR is READY. Never creates or keeps permanent PRs. Use when: 'pr-check', 'pr-merge', 'merge this PR safely', 'is PR ready', 'guard merge', or /sk-git delegates pr-merge.
data-ai
Operational surface for the compress-llm Layer-1 token I/O compressor. Enable, disable, switch mode, and inspect status without editing config files. Use when tuning compression pressure for the current session or project.
tools
Generate structured upstream feedback for the CELLM engineering team. Produces evidence-first Markdown at docs/evidence/<date>-cellm-feedback-*.md for bugs, anti-patterns, deprecation gaps, and harness surprises, with optional atom registration via knowledge_ops. Use when: 'feedback for CELLM', 'send to CELLM team', 'register this as atom', 'document this anti-pattern', 'report this bug upstream'. Trigger proactively on MCP schema/runtime mismatches, mechanical edit loops (>=3 sequential edits), short deprecation windows (<6 weeks), or reusable harness surprises. Do NOT trigger for routine feature work or project-local bugs.