build-until-pass

Automate iterative fixes to mechanical build failures until checks pass.

231|24|Updated Apr 11, 2026
One-click install
npx skills add https://github.com/LichAmnesia/lich-skills --skill build-until-pass
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: build-until-pass
Source: https://github.com/LichAmnesia/lich-skills/tree/main/skills/build-until-pass
Command: npx skills add https://github.com/LichAmnesia/lich-skills --skill build-until-pass

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill accelerates the process of getting a project from failing build/test to green by automatically running the appropriate check command, reading the errors, applying the smallest fix, and re-running until success or a hard cap.

Core Features & Use Cases

  • Automated cycle: run the check command, patch the minimal failing line, and re-run until exit code is 0.
  • Handles common failure modes across build, typecheck, lint, and test steps with an explicit attempt cap to prevent endless loops.
  • Use case: aCI pipeline that frequently red, enabling the agent to recover locally from failures without human intervention.

Quick Start

Run the check command you identified for your project, then let the agent iterate until the command exits with code 0.

Frequently Asked Questions about build-until-pass

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

FAQPage Schema
How do I automate fixing build failures until the check passes?

Automating build fixes involves running the check command, applying the smallest patch to errors, and re-running until exit code 0. This Skill handles iterative mechanical fixes across build, typecheck, lint, and test steps.

What is the best way to automatically recover a local CI pipeline from red to green?

Automatically recovering a CI pipeline uses an agent to run the check command, read errors, apply minimal patches, and re-run until success. This prevents frequent pipeline failures from requiring manual intervention.

Can I use automated build fixing for typecheck, lint, and test steps?

Yes, automated build fixing works for typecheck, lint, and test steps. The Skill targets sequential mechanical failures by running the specific project command and applying minimal fixes iteratively.

Does automated iterative debugging work with npm run build and go test commands?

Yes, automated iterative debugging works with identifiable project check commands like npm run build, tsc, and go test. The Skill requires the check command to be identifiable before starting the fix cycle.

What prevents an automated build fix loop from running endlessly?

An explicit attempt cap prevents the automated build fix loop from running endlessly. The Skill enforces a maximum attempt cap to guard against runaway loops when mechanical failures resist minimal patches.