Ring:Planning Backend Refactor logo

Ring:Planning Backend Refactor

Organization
LerianStudio
ring:planning-backend-refactor

Planning a backend refactor: audits an existing Go or TypeScript backend against Ring/Lerian standards and produces a prioritized task list (findings.md + tasks.md) ready for ring:running-dev-cycle. Plans only — no edits. Use when an existing backend service needs to meet standards or an audit is requested. Skip for greenfield projects, single-file fixes, or frontend (use ring:planning-frontend-refactor).

Overview

PublisherLerianStudio
Repositoryring
Skill namering:planning-backend-refactor
Stars
215
Forks
28
Bundled files
Instructions only
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by LerianStudio on GitHub. Read the source before you install it.

Installation

Install the Ring:Planning Backend Refactor AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/LerianStudio/ring.git /tmp/ring
mkdir -p .claude/skills
cp -r /tmp/ring/dev-team/skills/planning-backend-refactor .claude/skills/lerianstudio-ring-planning-backend-refactor
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Ring:Planning Backend Refactor in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Ring:Planning Backend Refactor on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Ring:Planning Backend Refactor is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Dev Refactor Skill

When to use

  • User wants to refactor existing project to follow standards
  • Legacy codebase needs modernization
  • Project audit requested

Skip when

  • Greenfield project → Use ring:planning-large-features or ring:planning-small-features instead
  • Single file fix → Use ring:running-dev-cycle directly
  • Frontend project → Use ring:planning-frontend-refactor

Analyzes existing backend codebase against Ring/Lerian standards and generates refactoring tasks for ring:running-dev-cycle.

You orchestrate. Agents analyze. NEVER run Bash/Grep/Read to analyze code directly — dispatch agents.

Gap Principle

Every divergence from Ring standards = a mandatory gap to implement. No exceptions.

All divergences → FINDING-XXX → REFACTOR-XXX task → ring:running-dev-cycle input.

Architecture Pattern Applicability

Service TypeApply Hexagonal/Lerian Pattern?
CRUD API✅ YES
Complex business logic✅ YES
Event-driven systems✅ YES
CLI tools / scripts❌ NO
Workers / background jobs❌ NO
Simple lambdas❌ NO

Execution Steps

Step 1: Validate Prerequisites

  • Check docs/PROJECT_RULES.md exists → STOP if missing
  • Detect stack: go.mod → Go; package.json + Express/Fastify/NestJS (no React) → TypeScript
  • If package.json + React/Next.js → STOP: use ring:planning-frontend-refactor

Step 2: Generate Codebase Report

Dispatch ring:codebase-explorer:

Generate comprehensive codebase report: project structure, architecture pattern,
tech stack, code patterns (config, database, handlers, errors, telemetry, testing),
key files inventory with file:line references, code snippets.
Output: docs/ring:planning-backend-refactor/{timestamp}/codebase-report.md

Step 3: Dispatch Specialist Agents (parallel)

Verify codebase-report.md exists before dispatching.

For Go projects — dispatch backend analysis:

yaml
Task 1: ring:backend-go (MODE: ANALYSIS only)
  - Load golang.md via WebFetch
  - Check all sections per shared-patterns/standards-coverage-table.md
  - Flag framework/library mismatches vs standards
  - File size enforcement: >1000 lines = ISSUE-XXX (HIGH), >1500 = CRITICAL
  - Multi-tenant analysis per shared-patterns/multi-tenant-analysis.md
  - Check tests, coverage, docker-compose/local runtime, and observability as backend-owned responsibilities
  - Output: Standards Coverage Table + ISSUE-XXX per finding

For TypeScript projects: Use ring:backend-ts with the same analysis contract.

Step 4: Map Findings → Tasks

After all agents complete:

  1. Save individual agent reports to docs/ring:planning-backend-refactor/{timestamp}/
  2. Map each ISSUE-XXX → FINDING-XXX (normalize severity, add file:line, current vs expected)
  3. Generate docs/ring:planning-backend-refactor/{timestamp}/findings.md
  4. Map each FINDING-XXX → one REFACTOR-XXX task (1:1 mapping)
  5. Generate docs/ring:planning-backend-refactor/{timestamp}/tasks.md (ring:running-dev-cycle compatible)

Findings template:

markdown
# {project-name} Refactor Findings

## FINDING-001: {Pattern Name} in {file_path}
- **Severity:** CRITICAL | HIGH | MEDIUM | LOW
- **File:** {path}:{line}
- **Current:** {code or description}
- **Expected:** {Ring standard}
- **Standard Reference:** {standards doc section}

Tasks template:

markdown
# {project-name} Refactor Tasks

## REFACTOR-001: {Pattern Name} in {file_path}
- **Finding:** FINDING-001
- **Estimated Complexity:** trivial | moderate | complex
- **Acceptance Criteria:**
  - [ ] {specific, testable criteria}

Step 5: Visual Change Report + User Approval

Generate visual HTML summary of KILL/CHANGE/ADD operations → dispatch ring:visualizing.

Present to user for approval. Wait for explicit APPROVED.

Step 6: Save + Handoff

Save all artifacts to docs/ring:planning-backend-refactor/{timestamp}/.

Handoff to ring:running-dev-cycle: feed tasks.md as input.

Agent Analysis Report Template

markdown
# {Agent Name} Analysis Report

## EXPLORATION SUMMARY
High-level architecture assessment

## KEY FINDINGS
ISSUE-XXX list with file:line, current, expected

## ARCHITECTURE INSIGHTS
Patterns detected, notable deviations

## RELEVANT FILES
Files most impacted by findings

## RECOMMENDATIONS
Priority order for refactoring

Frequently asked questions

What does the Ring:Planning Backend Refactor AI skill do?

Planning a backend refactor: audits an existing Go or TypeScript backend against Ring/Lerian standards and produces a prioritized task list (findings.md + tasks.md) ready for ring:running-dev-cycle. Plans only — no edits. Use when an existing backend service needs to meet standards or an audit is requested. Skip for greenfield projects, single-file fixes, or frontend (use ring:planning-frontend-refactor).

Why use Ring:Planning Backend Refactor on TypingMind?

Because you install it once and use it with any model. Ring:Planning Backend Refactor is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Ring:Planning Backend Refactor in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/LerianStudio/ring/tree/main/dev-team/skills/planning-backend-refactor. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Ring:Planning Backend Refactor?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Ring:Planning Backend Refactor?

As many as you like. As long as a model supports skills, you can use Ring:Planning Backend Refactor with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Ring:Planning Backend Refactor AI skill free?

Yes. It is published on GitHub by LerianStudio under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇