Install
$ agentstack add skill-lerianstudio-ring-planning-frontend-refactor ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Dev Refactor Frontend
When to use
- User wants to refactor existing frontend project to follow standards
- Legacy React/Next.js codebase needs modernization
- Frontend project audit requested
Skip when
- Greenfield project → Use /ring:planning-small-features or /ring:planning-large-features instead
- Single file fix → Use ring:running-dev-cycle-frontend directly
- Backend-only project → Use ring:planning-backend-refactor instead
Sequence
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.
Gap Principle
Every divergence from Ring standards = a mandatory gap. No exceptions.
All divergences → FINDING-XXX → REFACTOR-XXX task → ring:running-dev-cycle-frontend input.
Architecture Pattern Applicability
| 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 |
Standards Loading
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.
Execution Steps
Step 1: Validate Prerequisites
- Check
docs/PROJECT_RULES.mdexists → STOP if missing - Detect UI library mode: read
package.json @lerianstudio/sindarian-ui→sindarian-ui- Otherwise →
fallback-only - If
go.modand no React → STOP: usering:planning-backend-refactor
Step 2: Generate Codebase Report
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.md
Step 3: Dispatch Frontend Specialist Agents (parallel)
Verify 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 Sindarian UI 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 usage
Step 4: Map Findings → Tasks
After all agents complete:
- Save reports to
docs/ring:planning-frontend-refactor/{timestamp}/ - Map each ISSUE-XXX → FINDING-XXX
- Generate
findings.md - Map each FINDING-XXX → REFACTOR-XXX (1:1)
- 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}
Step 5: Visual Report + User Approval
Generate visual HTML summary → ring:visualizing. Present to user. Wait for explicit APPROVED.
Step 6: Save + Handoff
Save all artifacts. Handoff to ring:running-dev-cycle-frontend.
Severity Reference
| 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 |
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: LerianStudio
- Source: LerianStudio/ring
- License: Apache-2.0
- Homepage: https://lerian.studio
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.