reversa-to-do

Decomposes a roadmap into atomic tasks with sequential IDs, dependencies, and parallelism markers.

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

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Turning a high-level roadmap into an executable task list is error-prone: tasks end up too large, dependencies are unclear, and parallel work opportunities are missed. This Skill converts a roadmap.md file into a structured actions.md with atomic, trackable tasks. ## Core Features & Use Cases - Atomic decomposition: Breaks each roadmap item into tasks executable in a single agent turn, organized into five phases (preparation, tests, core, integration, polish). - Stable IDs and dependencies: Assigns zero-padded IDs (T001, T002...) that are never recycled, with explicit dependency columns and a [//] marker for parallelizable tasks. - Confidence inheritance: Carries over confidence indicators from the roadmap decisions and generates a summary with totals and the longest dependency chain. - Use Case: After running /reversa-plan to produce a roadmap, invoke this Skill to generate an actionable checklist that coding agents can execute in order or in parallel. ## Quick Start Ask the agent to run /reversa-to-do to decompose the current roadmap into an executable actions.md task list.

Frequently Asked Questions about reversa-to-do

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

FAQPage Schema
How do I break a software roadmap into atomic tasks?▼

Run the reversa-to-do skill after generating a roadmap.md. It decomposes each roadmap item into tasks small enough to complete in one agent turn, assigns zero-padded IDs like T001, and records dependencies and target files in a table.

What makes a task atomic in task decomposition?▼

A task is atomic when an agent can finish it in a single turn without human feedback. The skill splits any action with more than five logical subpoints, touching more than three unrelated files, or containing sequential phrasing like 'and then'.

What happens if roadmap.md is missing when running reversa-to-do?▼

The skill aborts with a clear message pointing to /reversa-plan, since the roadmap is a required input. It also checks for active-requirements.json first and directs you to /reversa-requirements if that is absent.

How are parallelizable tasks marked in the generated task list?▼

Tasks that touch different files and have no interdependencies are marked with [//] at the start of the line. The summary in actions.md reports the total number of parallelizable tasks and the longest dependency chain.

Can task IDs be reused or renumbered after generation?▼

No. IDs are never recycled, even if a task is removed in a later review. Renumbering only happens when the actions.md document is generated for the first time, keeping references stable across revisions.