verifier

Validates implemented code against phase requirements with empirical evidence checks.

1|Updated Sep 3, 2026
One-click install
npx skills add https://github.com/amanpal3/SKILLs --skill verifier-amanpal3
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: verifier
Source: https://github.com/amanpal3/SKILLs/tree/main/.agent/plugins/gsd/.agents/skills/verifier
Command: npx skills add https://github.com/amanpal3/SKILLs --skill verifier-amanpal3

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Development teams often mark work as complete based on claims rather than proof, leading to stub code, unwired components, and unmet requirements slipping through. This Skill verifies that implemented work actually achieves the stated phase goal by checking artifacts, wiring, and observable behaviors. ## Core Features & Use Cases - Three-Level Artifact Verification: Checks that files exist, contain substantive implementations (not stubs or placeholders), and are properly wired into the codebase. - Stub and Anti-Pattern Detection: Scans for TODO comments, placeholder text, empty handlers, and disconnected fetch calls across React components and API routes. - Structured Gap Reporting: Produces a VERIFICATION.md with pass/fail status per truth, artifact, and key link, plus structured YAML gaps consumable by planning workflows. - Use Case: After a coding agent finishes a chat feature phase, run verification to confirm Chat.tsx actually fetches from /api/chat, renders messages from state, and contains no placeholder UI before marking the phase complete. ## Quick Start Verify phase 3 of my project against its PLAN and ROADMAP goals and generate a VERIFICATION.md report.

Frequently Asked Questions about verifier

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

FAQPage Schema
How do I verify that implemented code actually meets requirements?▼

Define must-haves as observable truths, required artifacts, and key links, then check each artifact at three levels: existence, substantive implementation, and wiring. The verifier produces a VERIFICATION.md report with per-item status and evidence.

How to detect stub code and placeholder implementations in a codebase?▼

Scan for patterns like TODO and FIXME comments, placeholder text, empty return statements, and handlers that only call preventDefault. React stubs include components returning static divs, while API stubs return hardcoded responses without database queries.

What is the difference between re-verification and initial verification?▼

Initial verification establishes must-haves from the phase goal and runs full checks on everything. Re-verification parses the previous VERIFICATION.md, runs full three-level checks only on previously failed items, and performs quick regression checks on passed items.

Can automated verification check visual appearance and user flows?▼

No, visual layout, user flow completion, real-time behavior like WebSockets, and external service integration require human verification. The verifier flags these items in a dedicated section with test steps and expected outcomes for manual review.

What happens when verification finds gaps in the implementation?▼

Gaps are structured in YAML format listing each failed truth, the reason, affected artifacts, and missing pieces. This output is designed to feed directly into planning workflows so gaps can be addressed in a follow-up plan.