skills.rest
lacsousa
lacsousaCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

reversa-to-do

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

Updated Jun 12, 2026
Search Tags:#agent workflow#roadmap#task decomposition#spec-driven development#dependency tracking#atomic tasks#reversa
One-click install
npx skills add https://github.com/lacsousa/mediclaw-system --skill reversa-to-do-lacsousa
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: reversa-to-do
Source: https://github.com/lacsousa/mediclaw-system/tree/main/.agents/skills/reversa-to-do
Command: npx skills add https://github.com/lacsousa/mediclaw-system --skill reversa-to-do-lacsousa

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 parallelizable work goes unmarked. This Skill converts a roadmap.md 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, split across five standard 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 the 🟢/🟡/🔴 confidence markers from roadmap decisions into each derived action. - Use Case: After running /reversa-plan to produce a roadmap for a payments feature, run this Skill to generate actions.md with 25 atomic tasks, 8 marked parallelizable, ready for /reversa-coding. ## Quick Start Ask the agent to run the reversa-to-do skill to decompose the current feature roadmap into an atomic 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 this Skill after generating a roadmap.md with /reversa-plan. It splits each roadmap item into tasks executable in a single agent turn, organized into five phases: preparation, tests, core, integration, and polish.

What makes a task atomic in spec-driven development?▼

A task is atomic when an agent can complete it in one turn without human feedback. This Skill splits any action with more than five logical subpoints, more than three unrelated files, or sequential wording like "and then".

What happens if roadmap.md is missing when running this Skill?▼

The Skill aborts with a message pointing to /reversa-plan, since the roadmap is a required input. It also aborts toward /reversa-requirements if .reversa/active-requirements.json is absent.

How are parallelizable tasks marked in the generated actions.md?▼

Tasks that touch different files and have no interdependencies are prefixed with a [//] marker. The summary section also reports the total count of parallelizable actions and the longest dependency chain.

Are task IDs reused when the actions list is revised?▼

No. IDs are never recycled, even if a task is removed in a later review. Numbering is assigned only once, when the document is first generated.

Related Skills

Explore More Software Engineering Skills→
Pabloprogramador23Pabloprogramador23

reversa-to-do

Decompose roadmaps into atomic tasks with stable IDs, dependencies, and parallelism markers.

Community
Advanced
wellcrafted-devwellcrafted-dev
35

spec-execution

Execute specification documents through planned waves of parallel and sequential changes.

Official
Advanced
heltondoriaheltondoria
1

task-review

Validate task lists against quality criteria, TDD structure, and source specifications.

Community
Advanced
tamnguyentommy-rgbtamnguyentommy-rgb
2

product-manager

Generate structured PRDs, user stories, and roadmaps with prioritization templates.

Community
Advanced