vibe-test-runner

Run four-layer validation with Serena impact analysis, zsh, ShellCheck, bats, and review gating.

6|Updated Feb 5, 2026
One-click install
npx skills add https://github.com/jacobcy/vibe-coding-control-center --skill vibe-test-runner
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: vibe-test-runner
Source: https://github.com/jacobcy/vibe-coding-control-center/tree/main/supervisor/vibe-test-runner
Command: npx skills add https://github.com/jacobcy/vibe-coding-control-center --skill vibe-test-runner

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Ensures code changes to shell scripts and critical CLI tools are safe, correct, and conformant by running a four-layer validation pipeline that produces machine-readable evidence and attempts automated fixes up to three rounds before requiring human intervention.

Core Features & Use Cases

  • Serena Impact Analysis: Runs change impact discovery and emits .agent/reports/serena-impact.json to ensure call-site consistency when modifying functions or signatures.
  • Lint & Syntax Checks: Performs zsh syntax checks and ShellCheck error-level linting and auto-fixes issues when possible.
  • Test Execution and Repair Loop: Runs bats test suites, analyzes failures, attempts fixes, and repeats up to three rounds shared across lint and tests.
  • Strict Review Gate: Produces a reviewer-style outcome (Blocking/Major/Minor/Nit) with file/function, failure mode, and minimal fix suggestions.
  • Use Case: Pre-PR verification for changes to lib/*.sh or bin/vibe, CI orchestration premerge gates, and instrumented execution by the Vibe Orchestrator.

Quick Start

Run the orchestrator to execute the vibe-test-runner which performs Serena analysis, linting, tests, and a strict review gate with up to three automated repair rounds.

Frequently Asked Questions about vibe-test-runner

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

FAQPage Schema
How do I automate shell script linting and test repair before a PR?

Automated shell script validation runs zsh syntax checks, ShellCheck linting, and bats tests, attempting auto-fixes for up to three rounds before requiring human review.

What is Serena impact analysis for shell script modifications?

Serena impact analysis discovers change effects when modifying shell functions or signatures, emitting a machine-readable JSON report to ensure call-site consistency.

Can I use automated code review gating for CLI tool changes?

Automated review gating produces reviewer-style outcomes—Blocking, Major, Minor, or Nit—with file, function, failure mode, and minimal fix suggestions for CLI tool edits.

Does the validation pipeline auto-fix ShellCheck errors and bats test failures?

Yes, the pipeline analyzes ShellCheck errors and bats test failures, applying automated repairs and repeating the validation loop for up to three shared rounds.

When do I need a four-layer validation pipeline for code changes?

A four-layer validation pipeline is needed for pre-PR verification on shell scripts or CLI tools, CI premerge gates, and orchestrator-triggered execution flows requiring strict safety checks.

What are the limitations of automated repair rounds for shell scripts?

Automated repair is limited to three shared rounds across lint and test failures; if issues persist, the pipeline halts and requires human intervention via the strict review gate.