wf-execute

Execute MD plan tasks sequentially with fresh subagents and two-stage reviews.

1|Updated Mar 16, 2026

Search Tags:#automation #subagent #plan #code-review #execute #spec-review

Ready to run

npx skills add https://github.com/andeart/dotfiles --skill wf-execute

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: wf-execute
Source: https://github.com/andeart/dotfiles/tree/main/agents/skills/wf-execute
Command: npx skills add https://github.com/andeart/dotfiles --skill wf-execute

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill orchestrates end-to-end execution of an MD plan by loading the plan, reviewing it, and dispatching fresh subagents to implement each task, with two-stage reviews after every task.

Core Features & Use Cases

Load a plan from an MD file, extract tasks with their full text, context, and acceptance criteria.
Dispatch a dedicated implementer subagent per task and perform spec compliance and code quality reviews sequentially.
Announce progress and ensure tasks are marked complete before moving to the next.

Quick Start

Provide the path to your plan MD file and the system will load, review, and execute tasks with per-task subagents.

Frequently Asked Questions about wf-execute

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

FAQPage Schema

How do I automate markdown plan execution with subagents?▼

Automate markdown plan execution by loading the MD file, extracting tasks with acceptance criteria, and dispatching a dedicated implementer subagent for each task sequentially. The system enforces spec compliance and code quality reviews after every task.

What is the best way to ensure spec compliance during automated code generation?▼

Ensure spec compliance during automated code generation by using a two-stage review process that validates each subagent's implementation against the extracted acceptance criteria before marking the task complete.

How does a subagent team handle complex multi-task plans?▼

A subagent team handles complex plans by processing tasks sequentially, dispatching a fresh subagent per task to maintain context isolation, and enforcing quality reviews before advancing to the next task.

Do I need to format my plan as an MD file to automate task execution?▼

Yes, you need to format your plan as an MD file because the system loads the plan, extracts full task text with context and acceptance criteria, and delegates implementation directly from that markdown structure.

Can I use automated plan execution for long and complex software engineering tasks?▼

Yes, you can use automated plan execution for long and complex software engineering tasks because the system applies subagent delegation and sequential two-stage reviews to plans of varying length and complexity.

Why does automated plan execution use fresh subagents for each task?▼

Automated plan execution uses fresh subagents for each task to isolate context, ensuring the implementer focuses strictly on the current task's specifications before undergoing mandatory spec and code quality reviews.