skills.rest
mercadona
mercadonaOFFICIAL
Explore all skills by this author →
WebsiteGitHub

ct-executing-plans

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

1|Updated Sep 8, 2026
Search Tags:#implementation#plan execution#git worktree#review checkpoints#code verification#task workflow#development branch
One-click install
npx skills add https://github.com/mercadona/control-tower --skill ct-executing-plans-mercadona
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ct-executing-plans
Source: https://github.com/mercadona/control-tower/tree/main/plugin/skills/ct-executing-plans
Command: npx skills add https://github.com/mercadona/control-tower --skill ct-executing-plans-mercadona

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? It turns a written implementation plan into completed work by loading the plan, reviewing it critically, executing each task in order, and stopping to ask for help instead of guessing when blocked. ## Core Features & Use Cases - Critical Plan Review: Reads the plan file first and raises questions or concerns with the human partner before any code is written. - Task-by-Task Execution: Marks each task in progress, follows its bite-sized steps exactly, runs the specified verifications, and marks it completed. - Controlled Handoff: After all tasks pass verification, it invokes the finishing-a-development-branch skill to verify tests and present completion options. - Use Case: You have a written plan for a new feature. Hand it to this skill in a separate session and it implements every task, stopping immediately if a dependency is missing, a test fails, or an instruction is unclear. ## Quick Start Ask the agent to execute the implementation plan in your plan file using the executing-plans skill and report when all tasks are complete.

Frequently Asked Questions about ct-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?▼

Write the plan as a file with bite-sized steps, then invoke this skill in a separate session. It reviews the plan critically, raises concerns before starting, executes each task with its verifications, and reports when everything is complete.

What happens when a plan step fails or is unclear?▼

Execution stops immediately when a blocker appears, such as a missing dependency, a failing test, or an unclear instruction. The skill asks for clarification rather than guessing, and returns to plan review if the approach needs rethinking.

Should I use executing-plans or subagent-driven development?▼

If subagents are available, as they are on Claude Code, the skill itself directs you to use ct-subagent-driven-development instead. Use executing-plans when subagents are not available and a single session must work through the plan.

Can I start implementation directly on the main branch?▼

No. The skill never starts implementation on main or master without explicit user consent, and it integrates with the git worktrees skill to ensure an isolated workspace before executing tasks.

What happens after all plan tasks are completed?▼

After every task is verified, the skill invokes ct-finishing-a-development-branch as a required sub-skill. That workflow verifies tests, presents completion options, and executes the chosen option.

Related Skills

Explore More Software Engineering Skills→
Jorge-IvanJorge-Ivan
1

executing-plans

Execute implementation plans with verification checkpoints and error handling.

Community
Advanced
MacroMan5MacroMan5

finishing-a-development-branch

Validates tests and presents four options for merging, PR, or discarding a branch.

Community
Intermediate
dEitY719dEitY719

ai-worktree:spawn

Create an isolated git worktree for the active AI agent.

Community
Advanced
PlazaCCPlazaCC
2

subagent-driven-development

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

Official
Advanced