do

Execute phased implementation plans by coordinating subagents for verification and code quality review.

1|Updated May 16, 2026
One-click install
npx skills add https://github.com/enigmaicon-eng/AI-Enterprise-OS --skill do-enigmaicon-eng
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: do
Source: https://github.com/enigmaicon-eng/AI-Enterprise-OS/tree/main/examples/claude-mem/plugin/skills/do
Command: npx skills add https://github.com/enigmaicon-eng/AI-Enterprise-OS --skill do-enigmaicon-eng

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps you execute a multi-phase plan safely by delegating each phase to dedicated subagents and validating that each step matches the plan.

Core Features & Use Cases

  • Phased subagent orchestration: Runs the plan through discrete phases (implementation, verification, anti-pattern checks, code quality review, and committing only after approval).
  • Evidence-based completion: Requires each subagent to provide evidence such as commands run, outputs, and files changed before the orchestrator advances.
  • Guardrails against assumptions: Prevents inventing APIs or undocumented parameters by verifying against documentation and stopping when uncertainty is found.
  • Use Case: When you have a repository change plan created by a planner, use this Skill to carry out the implementation while ensuring verification, quality review, and guarded committing.

Quick Start

Use the do skill when you need to execute the phased implementation plan by coordinating subagents to complete each checklist step and verify results before committing.

Frequently Asked Questions about do

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

FAQPage Schema
How do I execute a multi-phase implementation plan with subagent orchestration?

Phased subagent orchestration executes a multi-phase implementation plan by delegating implementation, verification, and code quality review to dedicated subagents. Each subagent completes checklist steps and provides evidence before the orchestrator advances to the next phase.

What is evidence-based completion for code verification?

Evidence-based completion requires each subagent to provide commands run, outputs, and files changed before advancing. This verification process ensures that implementation steps are validated against actual results rather than assumptions, preventing unverified code from progressing.

How do I prevent undocumented API usage during code implementation?

Guardrails against assumptions prevent inventing APIs or undocumented parameters by verifying against documentation and stopping when uncertainty is found. This ensures implementation is anchored to verified documentation throughout the execution workflow.

Can I commit code changes before verification passes in a phased workflow?

No, commit gating ensures code is committed only after verification, anti-pattern detection, and code quality review pass. This phased approach preserves checklist order and requires evidence-based completion across phases and branches before any commit occurs.

What's the best way to coordinate specialized subagents for plan-driven development?

Coordinating specialized subagents for plan-driven development requires running discrete phases for implementation, verification, anti-pattern checks, and code quality review. Fresh subagents are spawned per phase when needed, ensuring each step matches the plan through evidence collection.

Does subagent orchestration work without a pre-existing repository change plan?

No, this Skill requires a repository change plan created by a planner as input. It carries out the implementation by executing the phased plan, coordinating subagents to complete each checklist step and verify results before committing.