reversa-coding

Executes actions.md plans into code while generating legacy-impact and regression-watch audit artifacts.

Updated Mar 23, 2026
One-click install
npx skills add https://github.com/Helcio-Nogueira/Painel_Inteligente_Hackaton_2026 --skill reversa-coding-helcio-nogueira
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: reversa-coding
Source: https://github.com/Helcio-Nogueira/Painel_Inteligente_Hackaton_2026/tree/main/.agents/skills/reversa-coding
Command: npx skills add https://github.com/Helcio-Nogueira/Painel_Inteligente_Hackaton_2026 --skill reversa-coding-helcio-nogueira

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? It turns a structured implementation plan (actions.md) into actual code changes while preserving traceability to a legacy reverse-engineering extraction, so every modification to legacy behavior is documented and watchable for regressions. ## Core Features & Use Cases - Phased Plan Execution: Executes pending actions phase by phase (Preparação, Testes, Núcleo, Integração, Polimento), respecting dependencies and parallel markers, updating checkboxes and appending to progress.jsonl. - Legacy Impact Report: Generates legacy-impact.md mapping touched files to architecture components, classifying impact type and severity, and listing preserved versus modified business rules. - Regression Watch List: Creates regression-watch.md with stable watch item IDs so future reverse extractions can verify that changed or removed rules behave as expected. - Use Case: After running /reversa-to-do to produce an actions.md plan for a new feature on a legacy codebase, invoke this skill to implement the plan and automatically produce audit artifacts linking code changes back to documented legacy rules. ## Quick Start Type /reversa-coding to execute the pending actions in the active feature plan and generate the legacy impact and regression watch reports.

Frequently Asked Questions about reversa-coding

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I execute an actions.md implementation plan with an AI agent?▼

Invoke /reversa-coding after generating actions.md with /reversa-to-do. The skill executes pending actions phase by phase, marks checkboxes as done, logs each action to progress.jsonl, and stops the phase if any action fails.

What is a legacy impact report in a reverse engineering workflow?▼

A legacy impact report maps each modified file to its component in the extracted architecture documentation, classifies the change type (rule altered, removed, new component, data delta) and assigns severity. It also lists which documented business rules were preserved or modified.

Can I run reversa-coding without the reverse extraction pipeline?▼

No. The skill strictly requires the _reversa_sdd directory containing architecture.md and domain.md. If either is missing, it aborts with an explanatory message and writes nothing to disk, since the audit artifacts would lose their anchor.

How do I limit execution to specific phases or action IDs?▼

Pass a free-text argument such as a phase name or an ID range like T001-T005. Without an argument, the skill executes all incomplete actions in the standard phase order.

What happens when an action fails during execution?▼

The failed action keeps its unchecked status, a failed entry is appended to progress.jsonl, and the current phase stops. The user receives a report and can resume later, since progress.jsonl is append-only and never rewritten.