guild-verify-done

Verify Guild runs by validating tests, scope, success criteria, blockers, and assumptions.

6|Updated Apr 24, 2026
One-click install
npx skills add https://github.com/lookatitude/guild --skill guild-verify-done
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: guild-verify-done
Source: https://github.com/lookatitude/guild/tree/main/skills/meta/verify-done
Command: npx skills add https://github.com/lookatitude/guild --skill guild-verify-done

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Verifies end-to-end task completion in a Guild run by checking tests, scope, blockers, and assumptions to ensure only fully verified work is closed.

Core Features & Use Cases

  • Five-check gate: tests pass, scope boundary, success-criteria match, no open blockers, and assumptions reviewed.
  • Generates a single .guild/runs/<run-id>/verify.md artifact for downstream handoff to guild:reflect.
  • Operates across multi-lane runs with receipts and .guild/runs/* artifacts to enforce governance.

Quick Start

Run the final gate after guild:review to produce the verify.md artifact and determine if the run can be closed.

Frequently Asked Questions about guild-verify-done

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

FAQPage Schema
How do I verify end-to-end task completion in a multi-lane workflow?

End-to-end task completion is verified by checking tests, scope boundaries, success criteria, open blockers, and assumption review across all specialist lanes. This ensures only fully verified work gets closed, enforcing governance across distributed run artifacts.

What is the best way to enforce a final verification gate before closing a run?

A final verification gate enforces run closure by validating five specific checks: passing tests, scope boundary adherence, success-criteria matching, zero open blockers, and completed assumption review. This prevents incomplete work from passing downstream.

How do I generate a verify.md artifact for a Guild run directory?

To generate a verify.md artifact, execute the final gate after the review phase. The process validates run receipts and artifacts stored under .guild/runs/<run-id> directories, producing a single verification artifact for downstream handoff.

Can I use end-to-end verification across multi-lane runs with different specialists?

End-to-end verification operates across multi-lane runs where several specialists contribute receipts. It aggregates artifacts from .guild/runs/* directories to enforce governance and validate task completion across all contributing lanes.

What happens after a successful end-to-end verification pass?

After a successful verification pass, the process generates a single verify.md artifact and creates a handoff to the reflection phase. This downstream handoff allows the workflow to analyze the completed run and extract insights.

Why does my run fail the verification gate when assumptions are not reviewed?

Run verification fails when assumptions remain unreviewed because assumption review is a mandatory check within the five-check gate. The verification process requires explicit assumption validation to ensure no unverified hypotheses remain before closing.