executing-plans

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

Updated Jun 20, 2026
One-click install
npx skills add https://github.com/dchavez3395/Puchica-hydrogen --skill executing-plans-dchavez3395
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: executing-plans
Source: https://github.com/dchavez3395/Puchica-hydrogen/tree/main/docs/superpowers/skills/openclaw-ports/executing-plans
Command: npx skills add https://github.com/dchavez3395/Puchica-hydrogen --skill executing-plans-dchavez3395

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Turning a written implementation plan into completed code often drifts: steps get skipped, verifications are forgotten, and blockers get worked around instead of surfaced. This Skill enforces a disciplined loop of loading the plan, reviewing it critically, executing each task with its specified verifications, and stopping to ask when blocked. ## Core Features & Use Cases - Critical plan review before execution: Reads the plan file, raises concerns with the human partner before starting, and registers each task as a tracked plan step. - Checkpointed task execution: Marks one task in progress at a time, follows bite-sized steps exactly, runs the specified verifications, and hands off to a finishing-a-development-branch workflow when all tasks complete. - Explicit stop conditions: Halts and asks for clarification on blockers, unclear instructions, repeated verification failures, or low wallet budget instead of guessing. - Use Case: You have a multi-task plan saved at docs/superpowers/plans/2025-01-15-checkout-fix.md for a Shopify Hydrogen storefront. This Skill loads it, executes each task in order with verifications, and completes the development branch when done. ## Quick Start Ask the agent to execute the implementation plan at docs/superpowers/plans/2025-01-15-checkout-fix.md using the executing-plans skill.

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?▼

Save the plan as a markdown file with bite-sized tasks, then invoke the executing-plans skill. It reviews the plan critically, registers each task as a tracked step, executes them one at a time with verifications, and reports when complete.

What should an implementation plan include before execution?▼

The plan should contain bite-sized tasks with exact steps and specified verifications for each. The skill reviews the plan critically first and raises concerns with you before starting if anything is unclear or missing.

When should I use subagent-driven execution instead of executing-plans?▼

For plans with more than five tasks, subagent-driven execution with a fresh context per task is preferred. The executing-plans skill keeps one session with checkpoints, which suits smaller plans where inline execution is sufficient.

What happens when a task verification fails during plan execution?▼

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

Can I start plan execution directly on the main branch?▼

No. The skill requires explicit user consent before starting implementation on main or master, and integrates with a git worktree skill to ensure an isolated workspace before executing tasks.