skills.rest
GleisonOliveira
GleisonOliveiraCOMMUNITY
Explore all skills by this author →
Website𝕏@classefinalGitHub

reversa-to-do

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

Updated May 22, 2026
Search Tags:#dependencies#roadmap#task decomposition#spec-driven development#parallelism#atomic tasks#reversa
One-click install
npx skills add https://github.com/GleisonOliveira/dockerpilot-mcp --skill reversa-to-do-gleisonoliveira
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: reversa-to-do
Source: https://github.com/GleisonOliveira/dockerpilot-mcp/tree/main/.agents/skills/reversa-to-do
Command: npx skills add https://github.com/GleisonOliveira/dockerpilot-mcp --skill reversa-to-do-gleisonoliveira

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Turning a high-level feature roadmap into an executable task list is error-prone: tasks end up too large, dependencies are implicit, and parallelizable work goes unmarked. This Skill converts a roadmap.md file into a structured actions.md with atomic, trackable tasks. ## Core Features & Use Cases - Atomic decomposition: Splits roadmap items 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 green/yellow/red confidence markers from roadmap decisions into each action row. - 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 feature roadmap into atomic tasks for an AI agent?▼

Run this Skill after generating a roadmap.md with /reversa-plan. It decomposes each roadmap item into tasks small enough to complete in one agent turn, assigning stable IDs like T001 and recording dependencies and target files in a table.

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. The Skill splits any action with more than five logical subpoints, more than three unrelated files, or sequencing words like 'and also' or 'then'.

Does reversa-to-do work without a roadmap file?▼

No. The Skill aborts with a clear message pointing to /reversa-plan if feature-dir/roadmap.md is missing, and it also requires .reversa/active-requirements.json from the earlier /reversa-requirements step.

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 reports the total number of parallelizable actions 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.

Related Skills

Explore More Software Engineering Skills→
lacsousalacsousa

reversa-to-do

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

Community
Intermediate
gfiresgfires

design-review

Audit live interfaces for visual inconsistencies and apply atomic fixes.

Community
Advanced
chohra-medchohra-med
28

spec-harness-tickets

Convert ticket tracker issues and ad-hoc plans into structured spec documents.

Community
Advanced
securityfortechsecurityfortech
6

ssti

Detect and exploit Server-Side Template Injection vulnerabilities in web applications.

Official
Advanced