patch

Apply fix recipes to modify code in memory across affected repositories.

16|2|Updated Jun 17, 2026
One-click install
npx skills add https://github.com/pipecrew-ai/pipecrew --skill patch-pipecrew-ai
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: patch
Source: https://github.com/pipecrew-ai/pipecrew/tree/main/skills/patch
Command: npx skills add https://github.com/pipecrew-ai/pipecrew --skill patch-pipecrew-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

The patch Skill unit addresses the need for repetitive, small-scale code modifications by providing a memory-backed mechanism that uses fix recipes to apply changes without full pipeline execution.

Core Features & Use Cases

  • Fix Recipes: Utilize a library of fix recipes for small, recurring changes like codemods, convention enforcement, and mechanical migrations.
  • Recipe Detection: Apply fixes using match patterns across all affected repos with --recipe --sweep or select specific findings using --findings.
  • Interactive and Automated: Interactively select changes or automate the process with flags like --findings and --recipe.
  • Review Process: Incorporate a review step for non-trivial patches using --review for added rigor.

Quick Start

Apply a fix recipe to address audit findings: /patch --recipe=deliteralize-aws-account-id --sweep

Frequently Asked Questions about patch

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

FAQPage Schema
How do I automate code modifications across multiple repositories?

Automate code modifications across multiple repositories using recipe-based changes. Apply fix recipes with a sweep flag to target all affected repos, or select specific findings to update matching code patterns in bulk.

What is the best way to apply codemods without running a full delivery pipeline?

Apply codemods without a full delivery pipeline using memory-backed modifications. This mechanism executes lightweight, in-memory recipe changes to handle recurring code fixes directly without triggering heavier pipeline processes.

Can I review mechanical code migrations before they are applied automatically?

Review mechanical code migrations before final application using a dedicated review flag. Incorporate a review step for non-trivial patches to add rigor and verify automated recipe-based changes before committing them.

How do I enforce coding conventions across multiple affected repositories?

Enforce coding conventions across affected repositories by utilizing fix recipes. Use match patterns to detect convention violations and sweep all repositories, interactively selecting changes or automating the process with recipe flags.

Does recipe-based code modification support interactive selection of changes?

Recipe-based code modification supports interactive selection of changes. You can interactively choose which specific findings to patch, or switch to an automated mode using findings and recipe flags for bulk processing.

When should I use memory-backed modifications for repo-specific fixes?

Use memory-backed modifications for repo-specific fixes when you need to apply small-scale, repetitive changes. This approach is ideal for mechanical migrations and convention enforcement without the overhead of full pipeline execution.