agentleFS
thalysjuvenalthalysjuvenal/advpl-specialist/skills/advpl-refactoring/SKILL.md

advpl-refactoring

Skill183 starsChanged 2 months agoMITView on GitHub

Use when the user asks to refactor, clean up, or restructure existing ADVPL/TLPP code on TOTVS Protheus without changing its behavior -- extracting long functions (>100 lines), simplifying deeply nested conditionals, removing dead code, improving variable naming (Hungarian notation), eliminating duplicated logic, or reducing functions with too many parameters. Also triggers on Portuguese phrasing like "refatorar rotina", "melhorar esse fonte", "extrair funcao", "remover codigo morto", "simplificar condicional", "reduzir complexidade", or "God function" complaints.

The file

Files
SKILL.md

ADVPL/TLPP Refactoring

This skill defines safe refactoring patterns (RF-001 through RF-006) for improving ADVPL/TLPP code structure without altering behavior: extract function, simplify conditionals with guard clauses, remove dead code, improve naming to Hungarian notation, eliminate duplication, and reduce function parameter count. It also defines the mandatory process -- analyze, prioritize, present a before/after plan, wait for user approval, apply one change at a time, verify -- and hard safety rules (never change business logic, never rename externally-used symbols without a caller check).

Activate this skill when the user wants existing, working code restructured for readability or maintainability: long functions, deep nesting, unclear names, copy-pasted blocks, or functions with excessive parameters. It does not cover fixing bugs or errors (see advpl-debugging), generating brand-new functionality (see advpl-code-generation), a formal quality/security audit (see advpl-code-review), or converting procedural .prw to object-oriented .tlpp (see advpl-to-tlpp-migration, which is a structural paradigm change rather than a behavior-preserving cleanup).

Reference fileRead when
reference.mdAlways -- the only file in this skill; contains all refactoring patterns (RF-001 to RF-006), the refactoring process, and safety rules

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.