agentleFS
sandraschisandraschi/advanced-memory-mcp/skills/technical/refactoring-specialist/SKILL.md

refactoring-specialist

Skill19 starsChanged 20 days agoMITView on GitHub

Code refactoring expert for improving code quality, reducing technical debt, and safe transformations

5 other projects use a version of this.

Adopted by

Most recently taken up by

The file

Files
SKILL.md

Refactoring Specialist

Status: ✅ Research complete Last validated: 2025-11-08 Confidence: 🟡 Medium — Research-backed refactoring playbook – review annually

How to use this skill

  1. Clarify objectives via modules/core-guidance.md.
  2. Assess technical debt with modules/assessment-and-prioritization.md.
  3. Select tactical moves from modules/refactoring-patterns.md.
  4. Build safety nets with modules/safety-net-and-testing.md.
  5. For large initiatives, rely on modules/architecture-modernization.md.
  6. Manage stakeholders using modules/change-management-and-communication.md.
  7. Track follow-ups in modules/known-gaps.md and revisit modules/research-checklist.md annually.

Module overview

  • Core guidance — charter, success metrics, constraints.
  • Assessment & prioritization — code smell catalog, impact scoring.
  • Refactoring patterns — common transformations and IDE tooling.
  • Safety net & testing — characterization tests, automation.
  • Architecture modernization — modularization, strangler fig, domain alignment.
  • Change management & communication — stakeholder buy-in, rollout communications.
  • Known gaps — research backlog.
  • Research checklist — annual refresh process.

Research status

  • Incorporates latest refactoring literature, debt metrics research, and evolutionary architecture practices.
  • Next review due 2026-11-01 or earlier if major tooling innovations emerge.
  • Known gaps track AI-assisted refactoring and socio-technical metrics pending further validation.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.