skills.rest
Ruggery
RuggeryCOMMUNITY
Explore all skills by this author →
GitHub

reversa-to-do

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

Updated Aug 14, 2026
Search Tags:#roadmap#task decomposition#spec-driven development#dependency tracking#atomic tasks#reversa#actions.md
One-click install
npx skills add https://github.com/Ruggery/OCR_Cartorio --skill reversa-to-do-ruggery
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: reversa-to-do
Source: https://github.com/Ruggery/OCR_Cartorio/tree/main/.agents/skills/reversa-to-do
Command: npx skills add https://github.com/Ruggery/OCR_Cartorio --skill reversa-to-do-ruggery

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 stay implicit, and parallel work opportunities get missed. 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...), records explicit dependency columns, and marks parallelizable tasks with [//]. - Confidence inheritance: Carries 🟢 / 🟡 / 🔴 confidence markers from roadmap decisions into each action row. - Use Case: After running /reversa-plan on a feature, invoke this Skill to produce actions.md with per-phase tables, a summary of total and parallelizable actions, and the longest dependency chain, ready for /reversa-coding. ## Quick Start Ask the agent to run the reversa to-do step 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 feature roadmap into atomic tasks for an AI agent?▼

Run this Skill after generating a roadmap with /reversa-plan. It splits each roadmap item into tasks small enough to complete in one agent turn, assigns IDs like T001, and writes everything to actions.md with dependency and parallelism columns.

What makes a task atomic in the Reversa to-do decomposition?▼

A task is atomic when an agent can finish it in a single turn without human feedback. Tasks with more than five logical subpoints, touching more than three unrelated files, or containing sequential phrasing like "and then" are split further.

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

The Skill aborts with a clear message pointing to /reversa-plan. It does not attempt to fill in the roadmap itself, and it also aborts toward /reversa-requirements if active-requirements.json is absent.

How are parallelizable tasks marked in actions.md?▼

Tasks that touch different files and have no mutual dependencies are marked with [//] at the start of the line. The summary section also reports the total count of parallelizable actions and the longest dependency chain.

Can task IDs be reused or renumbered after actions.md is created?▼

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

Related Skills

Explore More Software Engineering Skills→
GleisonOliveiraGleisonOliveira

reversa-to-do

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

Community
Intermediate
bpawlakjbpawlakj
3

implement

Execute atomic T-NNN tasks with pre-check gates and test verification.

Community
Advanced
heltondoriaheltondoria
1

task-review

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

Community
Advanced
microsoftmicrosoft
1.4k

backlog-plan

Plans backlog work read-only across Azure DevOps, GitHub, and Jira trackers.

Official
Advanced