verify

Verify completed issues against acceptance criteria and post structured reports.

1|Updated Jan 25, 2026
One-click install
npx skills add https://github.com/Tubular-Health/mobius --skill verify-tubular-health
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: verify
Source: https://github.com/Tubular-Health/mobius/tree/main/.claude/skills/verify
Command: npx skills add https://github.com/Tubular-Health/mobius --skill verify-tubular-health

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill verifies a completed issue by comparing the implementation against acceptance criteria, running tests, and critiquing the work. It ensures accountability by documenting results on the ticket and aligning outcomes with project goals.

Core Features & Use Cases

  • Automated verification of implemented tasks against acceptance criteria.
  • Executes tests, type checks, and linting; aggregates results into a single review.
  • Posts a structured verification report as a comment on the parent ticket and, on success, marks verification as done.

Quick Start

Use the /verify command after an issue has been executed to trigger the verification process. Pass the parent issue identifier, for example /verify MOB-161.

Frequently Asked Questions about verify

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

FAQPage Schema
How do I verify completed Jira or Linear tickets against acceptance criteria?

To verify completed tickets, the skill compares the implementation against acceptance criteria, runs tests and linting, and posts a structured verification report as a comment on the parent ticket.

Can I automate reopening failing tasks during CI code review?

Yes, automated verification enforces autonomous actions like reopening failing tasks when tests or type checks fail, ensuring accountability before marking the verification sub-task as done.

How do I post code review results as a ticket comment automatically?

You can post code review results automatically by triggering the verification process, which aggregates sub-task statuses and produces a structured review comment on the parent ticket.

What's the best way to run tests and type checks before closing an issue?

The best way to verify an issue is triggering the verification command after execution, which executes tests, type checks, and linting, aggregating results to ensure quality before closure.

Does automated verification work with both Jira and Linear backends?

Yes, automated verification works with both Jira and Linear backends by reading contextual data and aggregating sub-task statuses to produce a structured review on the ticket.

When should I not use autonomous verification for completed tasks?

You should not use autonomous verification when contextual data is missing or sub-task statuses are incomplete, as the skill requires these to aggregate results and enforce reopening failing tasks.