execute

Load plans from docs/plans/ and review them against docs/SPEC.md.

1|Updated Apr 17, 2026
One-click install
npx skills add https://github.com/justincordova/agents --skill execute-justincordova
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: execute
Source: https://github.com/justincordova/agents/tree/main/skills/execute
Command: npx skills add https://github.com/justincordova/agents --skill execute-justincordova

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Coordinates end-to-end plan execution by loading the plan from docs/plans/ and reviewing it against context in docs/SPEC.md.

Core Features & Use Cases

  • Load and review plan from docs/plans/, compare against design context in docs/SPEC.md, and surface questions or concerns.
  • Batch tasks into smaller, verifiable units based on the guidelines to ensure safe progress and checkpoints.
  • Provide status updates, verification steps, and a clear path for next steps or blockers.

Quick Start

Provide a plan in docs/plans/ and let the skill execute tasks in small, reviewable batches.

Frequently Asked Questions about execute

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

FAQPage Schema
How do I execute a project plan in reviewable batches?

Batch processing for project execution works by loading your plan from docs/plans/ and comparing it against design context in docs/SPEC.md. It splits tasks into logical checkpoints, providing status updates and verification steps while pausing for human feedback between batches.

How does batch grouping work for project management workflows?

Batch grouping for project management works by splitting a loaded plan into smaller, verifiable units based on predefined guidelines. This creates logical checkpoints throughout the workflow, requiring human feedback and verification steps between each batch before proceeding to the next set of tasks.

Do I need a SPEC.md file to run plan execution?

Yes, you need a SPEC.md file to run plan execution because the system reviews your loaded plan against the design context provided in docs/SPEC.md. This comparison surfaces questions or concerns and ensures the batched tasks align with the overall project specifications before proceeding.

What happens when the plan execution hits a blocker or missing guidance?

When plan execution hits a blocker or missing guidance, the system stops processing immediately. It provides a clear path for next steps, delivers status updates on the current batch, and waits for human feedback to resolve the issue before attempting to resume the workflow.

What's the best way to coordinate end-to-end plan execution safely?

The best way to coordinate end-to-end plan execution safely is to use batch grouping rules that split work into logical checkpoints. Loading a plan from docs/plans/ and reviewing it against docs/SPEC.md ensures traceability with status updates and verifications while pausing for human feedback.