verify

Generate a canonical four-line UTC test verdict statefile with pass-fail rules.

5|Updated Apr 29, 2026
One-click install
npx skills add https://github.com/friedbotstudio/baseline --skill verify-friedbotstudio
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: verify
Source: https://github.com/friedbotstudio/baseline/tree/main/.claude/skills/verify
Command: npx skills add https://github.com/friedbotstudio/baseline --skill verify-friedbotstudio

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill standardizes the test verdict record used to gate verification writes, so every caller produces the same binding result without format drift or ambiguity.

Core Features & Use Cases

  • Canonical statefile format: Defines the exact four-line .claude/state/last_test_result structure that hooks and callers must preserve.
  • Deterministic verdict rules: Distinguishes PASS from FAIL based on exit code, test execution, crashes, timeouts, and output consistency.
  • Workflow coordination: Guides callers such as integrate, simplify, chore, and verify-tick to inline the same mechanical steps and report a human-readable summary.
  • Guard interaction: Supports the verify_pass_guard flow by keeping the byte format stable for enforcement and auditability.

Quick Start

Use the verify skill to generate the canonical test verdict statefile and matching report for the current project.

Frequently Asked Questions about verify

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

FAQPage Schema
How do I standardize test verdict statefiles for Claude Code hooks?

A standardized test verdict statefile enforces a strict four-line UTC format that captures the command, tracks the exit code, and writes atomically. This ensures consistent caller behavior and stable guard enforcement.

How does a statefile determine PASS or FAIL verdicts for automated workflows?

Deterministic verdict rules distinguish PASS from FAIL by checking the test exit code, execution status, crashes, timeouts, and output consistency. This prevents format drift and ambiguity across different workflow callers.

What is the canonical format for a last test result statefile?

The canonical format for a last test result statefile is an exact four-line UTC structure. It records the executed command and exit code, enabling atomic state writes to gate verification writes and support auditability.

Can I use the verify skill to gate verification writes across multiple workflows?

You can gate verification writes across multiple workflows like integrate, simplify, and chore. The skill keeps the byte format stable for enforcement, ensuring every caller produces the same binding result.

Why do my Claude Code hooks fail to read inconsistent test verdict formats?

Inconsistent test verdict formats cause hooks to fail due to format drift and ambiguity among callers. Standardizing the statefile into a strict four-line UTC structure ensures hooks can reliably enforce pass-fail rules.