analyzing-options
Analyzing different approaches for a task or problem with structured comparisons, effort…
Planning a frontend refactor: audits an existing React/Next.js frontend against Ring standards (architecture, design system, accessibility, testing) and produces a prioritized task list (findings.md + tasks.md) for ring:running-dev-cycle-frontend. Plans only — no edits. Use when
$ npx -y skills add LerianStudio/ring --skill planning-frontend-refactor --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/planning-frontend-refactorContext preview
The summary Claude sees to decide when to auto-load this skill.
Planning a frontend refactor: audits an existing React/Next.js frontend against Ring standards (architecture, design system, accessibility, testing) and produces a prioritized task list (findings.md + tasks.md) for ring:running-dev-cycle-frontend. Plans only — no edits. Use when
name: ring:planning-frontend-refactor description: "Planning a frontend refactor: audits an existing React/Next.js frontend against Ring standards (architecture, design system, accessibility, testing) and produces a prioritized task list (findings.md + tasks.md) for ring:running-dev-cycle-frontend. Plans only — no edits. Use when an existing frontend needs to meet standards or an audit is requested. Skip for greenfield, single-file fixes, or backend (use ring:planning-backend-refactor)."
**Runs before:** ring:running-dev-cycle-frontend
Analyzes existing frontend codebase against Ring/Lerian standards and generates refactoring tasks for ring:running-dev-cycle-frontend.
You orchestrate. Agents analyze. NEVER use Bash/Grep/Read to analyze code — dispatch agents.
Every divergence from Ring standards = a mandatory gap. No exceptions.
All divergences → FINDING-XXX → REFACTOR-XXX task → ring:running-dev-cycle-frontend input.
| Project Type | Apply Frontend Standards? | |---|---| | Full React/Next.js App | ✅ YES — all frontend.md sections | | Design System Library | ✅ YES | | Landing page / static | ⚡ PARTIAL — directory + styling only | | Utility / config package | ❌ NO |
Pre-fetch before any step:
WebFetch: https://raw.githubusercontent.com/LerianStudio/ring/main/CLAUDE.md WebFetch: https://raw.githubusercontent.com/LerianStudio/ring/main/dev-team/docs/standards/frontend.md WebFetch: testing-accessibility.md, testing-visual.md, testing-e2e.md, testing-performance.md
STOP if any fetch fails.
<!-- Replace @your-org/design-system with your organization's design system package. -->
Dispatch `ring:codebase-explorer`:
Generate comprehensive codebase report: project structure, React/Next.js patterns,
component architecture, state management, forms, styling, testing approach,
package.json dependencies. Output: docs/ring:planning-frontend-refactor/{timestamp}/codebase-report.mdVerify `codebase-report.md` exists before dispatching.
**Dispatch all 3 in ONE message:**
Task 1: ring:frontend (MODE: ANALYSIS only)
- Load frontend.md via WebFetch
- Check all 19 sections per standards-coverage-table.md
- Flag framework/library mismatches vs standards
- File size enforcement: >1000 lines = ISSUE-XXX
- UI Library Mode: {ui_library_mode}
- Output: Standards Coverage Table + ISSUE-XXX per finding
Task 2: ring:qa-frontend (MODE: ANALYSIS only)
- Check all 19 testing sections (ACC, VIS, E2E, PERF)
- UI Library Mode: {ui_library_mode}
- Output: Standards Coverage Table + ISSUE-XXX for gaps
Task 3: ring:ui-engineer (MODE: ANALYSIS only)
- Check design system component usage compliance
- If ui_library_mode = "fallback-only", check custom component WCAG 2.1 AA accessibility, responsive/layout fallback behavior, and design-token/theme fallback usage
- For fallback-only mode, output ISSUE-XXX per violation plus a short note that frontend and qa-frontend own baseline implementation/testing coverage
- Output: ISSUE-XXX for non-compliant usageAfter all agents complete:
1. Save reports to `docs/ring:planning-frontend-refactor/{timestamp}/` 2. Map each ISSUE-XXX → FINDING-XXX 3. Generate `findings.md` 4. Map each FINDING-XXX → REFACTOR-XXX (1:1) 5. Generate `tasks.md` (ring:running-dev-cycle-frontend compatible)
**Findings template:**
## FINDING-001: {Pattern Name} in {file_path}
- **Severity:** CRITICAL | HIGH | MEDIUM | LOW
- **File:** {path}:{line}
- **Current:** {code or description}
- **Expected:** {Ring standard}Generate visual HTML summary → `ring:visualizing`. Present to user. Wait for explicit APPROVED.
Save all artifacts. Handoff to `ring:running-dev-cycle-frontend`.
| Severity | Criteria | |---|---| | CRITICAL | Security risk, WCAG legal issue, build broken | | HIGH | Missing server components, Lighthouse < 80, wrong pattern | | MEDIUM | Client component overuse, missing snapshots | | LOW | Naming conventions, file organization |
Proven engineering practices, enforced through skills. Ring is a comprehensive skills library and workflow system for AI agents that transforms how AI assistants approach software development.
Repo: LerianStudio/ring
Analyzing different approaches for a task or problem with structured comparisons, effort…
Auditing a service's production readiness against Ring engineering standards across base…
Cleaning redundant and obvious comments following clean code principles while preserving…
Commit changes with scope allowlist enforcement, atomic grouping, GPG-signed conventional…
Creating a handoff document that captures session state (completed work, decisions, open…
Creating an isolated git worktree for parallel branch work: selects the directory by priority…