musts

Automate the musts validation loop for repositories with MUSTS.yml.

7|1|Updated May 13, 2026
One-click install
npx skills add https://github.com/bitomule/musts --skill musts
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: musts
Source: https://github.com/bitomule/musts/tree/main/skills/musts
Command: npx skills add https://github.com/bitomule/musts --skill musts

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

AI agents often forget to run all required verification steps (builds, tests, architecture checks) after making code changes, leading to incomplete work that fails during review or deployment.

Core Features & Use Cases

  • Automated Validation Loop: Guides you through running musts validate to get pending tasks, executing deterministic checks via musts run, and recording evidence for judgment checks via musts evidence until the report is clean.
  • Parallel Task Processing: Supports dispatching independent judgment tasks to subagents for parallel execution, while sequencing tasks that share limited resources like simulators or databases.
  • Noise Reduction: Includes guidance for adding .mustsignore files to exclude local artifacts from validation scope, preventing unnecessary re-validation of committed fixtures or generated files.
  • Use Case: For a Rust repository with a MUSTS.yml defining cargo test and lint checks, use this skill to automatically run all pending validation tasks after code changes, record test logs as evidence, and confirm the repo is ready for PR submission.

Quick Start

Use the musts skill to run the full validation loop for your recent code changes, execute all pending deterministic checks, record evidence for any judgment tasks, and confirm the repository is ready for submission.

Frequently Asked Questions about musts

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

FAQPage Schema
How do I automate CI checks for code changes in a Rust repository?

To automate CI checks for code changes, you can use a MUSTS.yml configuration file to define cargo and bazel validation tasks, then run an automated validation loop to execute pending checks and record evidence until all done criteria are met.

How does automated validation handle manual UI review checks?

Automated validation handles manual UI review checks as judgment tasks, allowing you to record verifiable evidence for completed checks while continuing to execute deterministic checks until no pending tasks remain in the validation report.

How do I exclude local artifacts from validation scope to prevent unnecessary re-validation?

You can exclude local artifacts from validation scope by adding a .mustsignore file to your repository, which prevents the validation loop from re-validating committed fixtures or generated files.

Can I run independent judgment checks in parallel during the validation loop?

Yes, you can dispatch independent judgment tasks to subagents for parallel execution during the validation loop, while sequencing tasks that share limited resources like simulators or databases to manage constraints.

What is the best way to verify all done criteria are met before a PR submission?

The best way to verify all done criteria are met before a PR submission is to execute all pending deterministic checks, record test logs as evidence for judgment checks, and repeat validation until the report is completely clean.

Do I need a MUSTS.yml file to enforce code verification checks?

Yes, you need a MUSTS.yml configuration file to define the deterministic and judgment checks required, which enables the automated validation loop to execute and track all verification tasks for your code changes.