recipe-code-assistant

Automate file reads, edits, shell commands, and git operations for TypeScript projects.

21|4|Updated Feb 19, 2026
One-click install
npx skills add https://github.com/tylerjrbuell/reactive-agents-ts --skill recipe-code-assistant
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: recipe-code-assistant
Source: https://github.com/tylerjrbuell/reactive-agents-ts/tree/main/apps/docs/skills/recipe-code-assistant
Command: npx skills add https://github.com/tylerjrbuell/reactive-agents-ts --skill recipe-code-assistant

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It automates end-to-end codebase change workflows that normally require manual file reads, edits, shell commands, and git operations so developers can fix bugs, run tests, and perform reviews faster and more reliably.

Core Features & Use Cases

  • Controlled shell execution: Run allowlisted commands with timeouts and output limits for builds, tests, and repository inspection.
  • File read/write and git integration: Read existing files before making focused edits, checkpoint plans, and use git status/diff to review and commit changes.
  • Sandboxing and observability: Optionally run commands in isolated environments, emit verbose live output for development, and support audit logging for production workflows.
  • Use Case: Fix failing tests by locating the relevant file, applying a minimal patch, running the test suite, and reporting the changes and results.

Quick Start

Have the agent fix the failing test in packages/auth/tests/login.test.ts by reading the file, applying a minimal edit, running tests, and summarizing the outcome.

Frequently Asked Questions about recipe-code-assistant

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

FAQPage Schema
How do I automate fixing failing tests in a TypeScript project?

To automate fixing failing tests, the Skill reads the relevant TypeScript test file, applies a minimal targeted patch, runs the test suite via controlled shell execution, and summarizes the outcome and applied changes.

Can I run shell commands and git operations safely during automated code review?

Yes, automated code review and git operations run safely using sandboxed shell execution, allowlisted commands, timeout controls, and optional audit logging to inspect repository status and commit reviewed changes.

What's the best way to automate code edits and run tests without breaking my CI workflow?

Automating code edits and tests safely requires reading existing files before making focused edits, running allowlisted shell commands with strict timeouts and output limits, and verifying results before committing to protect your CI workflow.

Does this code automation approach work with sandboxed environments and audit logging?

Sandboxed environments and audit logging are fully supported, allowing shell commands to execute in isolated environments with verbose live output for development and comprehensive audit logs for production workflows.

How do I perform iterative development with file read/write and git integration?

Iterative development uses file read and write tools to apply focused edits, checkpoint plans, and leverage git status and diff commands to review, verify, and commit code changes progressively.

What are the limitations of using allowlisted commands for shell execution in code workflows?

Shell execution is restricted to controlled allowlisted commands with enforced timeouts and output limits, preventing arbitrary command execution while maintaining safe, observable automation for builds and test suites.