executing-plans

Use when you have a written implementation plan to execute in a separate session with review checkpoints

31,392 stars
Complexity: easy

About this skill

The `executing-plans` skill empowers an AI agent to tackle complex, multi-step projects by breaking down a detailed implementation plan into manageable batches. Before starting, the agent will critically review the entire plan, identifying potential issues or questions and raising them with a human partner for clarification. Upon approval, it proceeds to execute tasks in default batches of three, pausing after each batch to report progress and await human review or approval. This core principle of 'Batch execution with checkpoints for architect review' ensures that complex implementations are carried out meticulously, with continuous human oversight, reducing errors and ensuring alignment with project goals. The agent explicitly announces its use of this skill at the outset.

Best use case

Systematic implementation of software features or complex code refactoring following a detailed specification. Executing multi-step infrastructure deployments or configuration changes from a runbook. Managing complex data migration or processing workflows where critical review points are essential. Any project requiring phased execution, continuous progress updates, and strict adherence to a pre-defined plan with human-in-the-loop oversight.

Use when you have a written implementation plan to execute in a separate session with review checkpoints

A systematically executed plan, broken into manageable batches with clearly communicated progress. Potential issues or ambiguities in the plan will be identified and addressed proactively. The project benefits from continuous human oversight, leading to higher quality outcomes and reduced risk in complex implementations.

Practical example

Example input

Please implement the attached `database_migration_plan.md` using a batched approach with review checkpoints.

Example output

I'm using the executing-plans skill to implement this plan.

**Step 1: Load and Review Plan**
Loaded `database_migration_plan.md`. Reviewed critically. Identified a potential ambiguity in 'Step 4: Schema update for legacy data types'. Suggest clarifying the exact transformation logic required. Awaiting your feedback before proceeding.

[After human feedback: 'Proceed with default transformation for now.']

No further concerns. Creating TodoWrite.

**Step 2: Execute Batch (Tasks 1-3)**
Executing:
1. Backup current database
2. Create new database instance
3. Migrate user authentication tables

Batch completed. Reporting for review. Database backup successful, new instance created and user authentication tables migrated. Please review and provide approval to proceed with the next batch.

When to use this skill

  • When you have a comprehensive, written implementation plan that needs to be followed precisely.
  • When the task is complex, multi-faceted, and would benefit from being broken down into smaller, reviewable chunks.
  • When critical review of the plan by a human partner is required before or during execution.
  • When ensuring adherence to architectural guidelines or project specifications is paramount.

When not to use this skill

  • For simple, single-step tasks that can be executed autonomously without need for checkpoints.
  • When the agent is expected to spontaneously generate a plan, rather than execute a given one.
  • When real-time, uninterrupted execution is critical and human intervention would introduce unacceptable delays.
  • With poorly defined, ambiguous, or incomplete plans that lack the detail required for critical review and batch execution.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/executing-plans/SKILL.md --create-dirs "https://raw.githubusercontent.com/sickn33/antigravity-awesome-skills/main/plugins/antigravity-awesome-skills-claude/skills/executing-plans/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/executing-plans/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How executing-plans Compares

Feature / Agentexecuting-plansStandard Approach
Platform SupportClaudeLimited / Varies
Context Awareness High Baseline
Installation ComplexityeasyN/A

Frequently Asked Questions

What does this skill do?

Use when you have a written implementation plan to execute in a separate session with review checkpoints

Which AI agents support this skill?

This skill is designed for Claude.

How difficult is it to install?

The installation complexity is rated as easy. You can find the installation instructions above.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

SKILL.md Source

# Executing Plans

## Overview

Load plan, review critically, execute tasks in batches, report for review between batches.

**Core principle:** Batch execution with checkpoints for architect review.

**Announce at start:** "I'm using the executing-plans skill to implement this plan."

## The Process

### Step 1: Load and Review Plan
1. Read plan file
2. Review critically - identify any questions or concerns about the plan
3. If concerns: Raise them with your human partner before starting
4. If no concerns: Create TodoWrite and proceed

### Step 2: Execute Batch
**Default: First 3 tasks**

For each task:
1. Mark as in_progress
2. Follow each step exactly (plan has bite-sized steps)
3. Run verifications as specified
4. Mark as completed

### Step 3: Report
When batch complete:
- Show what was implemented
- Show verification output
- Say: "Ready for feedback."

### Step 4: Continue
Based on feedback:
- Apply changes if needed
- Execute next batch
- Repeat until complete

### Step 5: Complete Development

After all tasks complete and verified:
- Announce: "I'm using the finishing-a-development-branch skill to complete this work."
- **REQUIRED SUB-SKILL:** Use superpowers:finishing-a-development-branch
- Follow that skill to verify tests, present options, execute choice

## When to Stop and Ask for Help

**STOP executing immediately when:**
- Hit a blocker mid-batch (missing dependency, test fails, instruction unclear)
- Plan has critical gaps preventing starting
- You don't understand an instruction
- Verification fails repeatedly

**Ask for clarification rather than guessing.**

## When to Revisit Earlier Steps

**Return to Review (Step 1) when:**
- Partner updates the plan based on your feedback
- Fundamental approach needs rethinking

**Don't force through blockers** - stop and ask.

## Remember
- Review plan critically first
- Follow plan steps exactly
- Don't skip verifications
- Reference skills when plan says to
- Between batches: just report and wait
- Stop when blocked, don't guess

## When to Use
This skill is applicable to execute the workflow or actions described in the overview.

Related Skills

monday-automation

31392
from sickn33/antigravity-awesome-skills

Automate Monday.com work management including boards, items, columns, groups, subitems, and updates via Rube MCP (Composio). Always search tools first for current schemas.

Project ManagementClaude

linear-claude-skill

31392
from sickn33/antigravity-awesome-skills

Manage Linear issues, projects, and teams

Project ManagementClaude

linear-automation

31392
from sickn33/antigravity-awesome-skills

Automate Linear tasks via Rube MCP (Composio): issues, projects, cycles, teams, labels. Always search tools first for current schemas.

Project ManagementClaude

jira-automation

31392
from sickn33/antigravity-awesome-skills

Automate Jira tasks via Rube MCP (Composio): issues, projects, sprints, boards, comments, users. Always search tools first for current schemas.

Project ManagementClaude

clickup-automation

31392
from sickn33/antigravity-awesome-skills

Automate ClickUp project management including tasks, spaces, folders, lists, comments, and team operations via Rube MCP (Composio). Always search tools first for current schemas.

Project ManagementClaude

build

31392
from sickn33/antigravity-awesome-skills

build

Project ManagementClaude

basecamp-automation

31392
from sickn33/antigravity-awesome-skills

Automate Basecamp project management, to-dos, messages, people, and to-do list organization via Rube MCP (Composio). Always search tools first for current schemas.

Project ManagementClaude

issue

41
from TaylorHuston/local-life-manager

Create standalone work items (TASK, BUG, or SPIKE) with AI-assisted type detection. Use when you need to track work that needs doing, exploration needed, or something broken.

Project ManagementClaude

nft-standards

31392
from sickn33/antigravity-awesome-skills

Master ERC-721 and ERC-1155 NFT standards, metadata best practices, and advanced NFT features.

Web3 & BlockchainClaude

nextjs-app-router-patterns

31392
from sickn33/antigravity-awesome-skills

Comprehensive patterns for Next.js 14+ App Router architecture, Server Components, and modern full-stack React development.

Web FrameworksClaude

new-rails-project

31392
from sickn33/antigravity-awesome-skills

Create a new Rails project

Code GenerationClaude

networkx

31392
from sickn33/antigravity-awesome-skills

NetworkX is a Python package for creating, manipulating, and analyzing complex networks and graphs.

Network AnalysisClaude