corgispec-verify

Automate OpenSpec Task Group verification with tests, lint/build signals, and spec coverage.

113|9|Updated Apr 30, 2026
One-click install
npx skills add https://github.com/ricoyudog/Coding_Corgi_flow --skill corgispec-verify
Or copy as Structured Prompt for Agentโ–ผ
Please help me install this Agent Skill.
Skill: corgispec-verify
Source: https://github.com/ricoyudog/Coding_Corgi_flow/tree/main/.opencode/skills/molecules/corgispec-verify
Command: npx skills add https://github.com/ricoyudog/Coding_Corgi_flow --skill corgispec-verify

SYSTEM DOCUMENTATION & REQUIREMENTS

๐Ÿ’ก This Skill includes references (resource) components.

What problem does it solve?

Prevents fragile AI-generated changes from reaching human review by automatically running tests, checking spec coverage, and validating lint/build signals first.

Core Features & Use Cases

  • Automated verification gate between apply and review: Selects a change and the next completed Task Group eligible for verification, then runs evidence-gathering checks without requiring human input.
  • Best-effort test execution: Detects common test infrastructures (e.g., pytest, npm, bun, Go) and records full output; failures are captured as warnings rather than blocking logic except where build verification is critical.
  • Spec coverage assessment: Locates group specs under openspec/changes/<name>/specs/<capability>/spec.md and classifies each requirement as Full, Partial, or Missing based on implementation evidence.
  • Lint/build verification: Detects common linters and build commands; captures results to support the review decision.
  • Structured Verify Report + tracking-safe posting: Generates a consistent report and posts only a note to existing child issues when GitHub/GitLab tracking metadata is present.

Quick Start

Run verify for your next completed Task Group by asking the AI to execute the corgispec-verify skill for the currently selected change.

Frequently Asked Questions about corgispec-verify

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

FAQPage Schema
How do I automate spec verification for AI-generated code changes before human review?โ–ผ

Spec verification for AI-generated changes is automated by executing tests, validating lint/build signals, and measuring implementation coverage against OpenSpec specs to produce a structured PASS/WARN/FAIL verdict before review.

How does spec coverage assessment map code implementations to requirements?โ–ผ

Spec coverage assessment locates group specs under openspec/changes and classifies each requirement as Full, Partial, or Missing based on implementation evidence found during the automated verification phase.

Can I use automated test execution with pytest, npm, bun, or Go without manual configuration?โ–ผ

Automated test execution detects common infrastructures like pytest, npm, bun, and Go best-effort, running detected commands and recording full output without requiring manual configuration or blocking logic on failures.

What is the best way to gate AI coding workflow changes between apply and review phases?โ–ผ

The best way to gate AI coding workflow changes is running an automated verification phase between apply and review that selects completed Task Groups, gathers evidence, and generates a tracking-safe note for existing GitHub or GitLab child issues.

Does the verification gate work with GitHub and GitLab issue tracking metadata?โ–ผ

Yes, the verification gate works with GitHub and GitLab tracking metadata by posting only a note to existing child issues when tracking information is present, ensuring tracking-safe updates without creating duplicate tickets.

When do I need worktree isolation for running lint and build verification?โ–ผ

Worktree isolation for running lint and build verification is needed when openspec/config.yaml isolation settings require separating untracked changes during the verification phase to prevent conflicts with the main working directory.