skills.rest
erwinv2k-TKG
erwinv2k-TKGCOMMUNITY
Explore all skills by this author →
GitHub

executing-plans

Executes written implementation plans task by task with verification checkpoints and review gates.

Updated Mar 26, 2026
Search Tags:#code review#workflow automation#software development#verification#implementation plan#git worktree#task execution
One-click install
npx skills add https://github.com/erwinv2k-TKG/AgentesVSC --skill executing-plans-erwinv2k-tkg
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: executing-plans
Source: https://github.com/erwinv2k-TKG/AgentesVSC/tree/main/packs/superpowers/skills/executing-plans
Command: npx skills add https://github.com/erwinv2k-TKG/AgentesVSC --skill executing-plans-erwinv2k-tkg

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? It turns a written implementation plan into completed work by executing each task in order, running the specified verifications, and stopping to ask for help instead of guessing when blockers appear. ## Core Features & Use Cases - Critical Plan Review: Reads the plan first, raises concerns with the human partner before writing any code, and only proceeds when the plan is sound. - Task-by-Task Execution: Tracks each task with TodoWrite, follows bite-sized steps exactly, and runs the verifications defined in the plan. - Defined Stop Conditions: Halts immediately on missing dependencies, failing tests, unclear instructions, or repeated verification failures rather than improvising. - Use Case: You have a multi-task refactoring plan written in a previous session. Hand it to this skill in a fresh session and it executes every task, verifies each one, and finishes the development branch. ## Quick Start Use the executing-plans skill to implement the plan in docs/refactor-plan.md, reviewing it critically first and stopping if anything is unclear.

Frequently Asked Questions about executing-plans

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

FAQPage Schema
How do I execute an implementation plan with an AI agent?▼

Provide the written plan file and invoke the executing-plans skill. It reviews the plan critically, raises concerns before starting, then executes each task in order, running the verifications specified in the plan and marking tasks complete as it goes.

What should an implementation plan contain before execution?▼

The plan should contain bite-sized tasks with explicit steps and verification commands for each task. Plans created with the superpowers writing-plans skill follow this structure and are designed to be executed by this skill.

What happens when a task in the plan fails verification?▼

Execution stops immediately when verification fails repeatedly, a dependency is missing, or an instruction is unclear. The skill asks the human partner for clarification rather than guessing or forcing through the blocker.

Does executing-plans work without subagent support?▼

Yes, it is designed for sessions without subagents. However, the skill notes that platforms with subagent support such as Claude Code or Codex produce higher quality results, and recommends subagent-driven-development when available.

When should I not use executing-plans?▼

Do not use it when no written plan exists yet, when the plan has critical gaps preventing a start, or when the fundamental approach needs rethinking. In those cases, return to plan writing or review with your human partner first.

Related Skills

Explore More Software Engineering Skills→
AIChuYAIChuY
1

writing-plans

Create detailed implementation plans with file lists, task sequencing, and verification commands.

Community
Advanced
whatswithaviwhatswithavi

finishing-a-development-branch

Guides completion of development branches through verified merge, pull request, or cleanup options.

Community
Intermediate
unorouterunorouter

bug-fix-expert

Coordinate multi-agent bug fixes with verification before code changes.

Official
Advanced
jaydubya818jaydubya818

subagent-driven-development

Delegate each task to a fresh subagent with two-stage reviews.

Community
Advanced