skills.rest
cristoslc
cristoslcCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

executing-plans

Executes written implementation plans in batches with review checkpoints between batches.

Updated Dec 20, 2025
Search Tags:#code review#implementation#verification#plan execution#git worktree#task tracking#batch workflow
One-click install
npx skills add https://github.com/cristoslc/LLM-personal-agent-patterns --skill executing-plans-cristoslc
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: executing-plans
Source: https://github.com/cristoslc/LLM-personal-agent-patterns/tree/main/L3-agents-core/.agents/skills/executing-plans
Command: npx skills add https://github.com/cristoslc/LLM-personal-agent-patterns --skill executing-plans-cristoslc

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Written implementation plans often fail when executed all at once without review, leading to drift from the plan, skipped verifications, and undetected errors. This Skill enforces disciplined batch execution with checkpoints so a human partner can review progress before work continues. ## Core Features & Use Cases - Critical Plan Review: Loads the plan file and raises questions or concerns with the human partner before any implementation begins. - Batched Task Execution: Executes tasks in batches (default first 3), marking each in progress, following steps exactly, and running specified verifications. - Checkpoint Reporting: Reports implemented work and verification output after each batch, then waits for feedback before continuing. - Use Case: After a planning session produces a detailed implementation plan, hand it to a fresh session that executes three tasks, shows verification output, pauses for architect review, and repeats until the plan is complete. ## Quick Start Use the executing-plans skill to implement the plan in docs/plans/feature-auth.md, executing the first three tasks and reporting back for review.

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 coding agent?▼

Load the plan file, review it critically, and raise concerns before starting. Then execute tasks in batches of three, running each specified verification, and report results for human review between batches.

How many tasks should be executed before pausing for review?▼

The default batch size is the first three tasks. After completing a batch with verifications, report what was implemented and wait for feedback before executing the next batch.

What should I do when a plan step is blocked or unclear?▼

Stop executing immediately when hitting a blocker, unclear instruction, or repeated verification failure. Ask the human partner for clarification rather than guessing or forcing through the issue.

Can I start implementing a plan directly on the main branch?▼

No. Never start implementation on main or master without explicit user consent. The workflow requires setting up an isolated workspace, such as a git worktree, before beginning execution.

What happens after all plan tasks are complete?▼

After all tasks complete and verifications pass, hand off to the finishing-a-development-branch workflow. That step verifies tests, presents merge options, and executes the chosen completion path.

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
darkmatterdarkmatter
1

finishing-a-development-branch

Verify tests and complete a development branch via merge, pull request, keep, or discard.

Official
Advanced
dEitY719dEitY719

ai-worktree:spawn

Create an isolated git worktree for the active AI agent.

Community
Advanced
jacobrocks1212jacobrocks1212

executing-plans

Coordinate plan execution with task creation, batch work, and review checkpoints.

Community
Advanced