speckit-verify-tasks-run

Verify completed tasks in tasks.md against real implementation evidence.

Updated Mar 16, 2026
One-click install
npx skills add https://github.com/B0yZ4kr14/OrthoPlus-Enterprise --skill speckit-verify-tasks-run
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: speckit-verify-tasks-run
Source: https://github.com/B0yZ4kr14/OrthoPlus-Enterprise/tree/main/.specify-backups/20260518-141826/_agents/skills/speckit-verify-tasks-run
Command: npx skills add https://github.com/B0yZ4kr14/OrthoPlus-Enterprise --skill speckit-verify-tasks-run

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It verifies that tasks marked as completed in tasks.md are truly implemented, preventing misleading confirmations caused by phantom or stub-only work.

Core Features & Use Cases

  • Completed-task auditing: Parses all tasks marked with [X] and verifies file presence, code/diff cross-references, symbol existence, and wiring.
  • Dead-code detection: Detects symbols declared but never referenced using grep-based scanning to avoid tracked-file blind spots.
  • Semantic validation: Flags stubs and placeholder implementations by comparing code behavior against spec.md.

Quick Start

Run the skill with a fresh session by telling your AI to verify all completed tasks using the default scope.

Frequently Asked Questions about speckit-verify-tasks-run

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

FAQPage Schema
How do I verify that completed tasks in tasks.md are actually implemented in my code?

Task verification for spec-kit projects requires the .specify/ directory structure, a tasks.md file with completed items marked [X], and a corresponding spec.md file to perform semantic validation and cross-reference git diffs.

What is phantom task completion and how does dead code detection identify it?

Phantom task completion occurs when tasks.md marks items [X] without real implementation. The skill detects this by using grep-based scanning to find declared symbols never referenced, avoiding tracked-file blind spots in the codebase.

How do I audit completed tasks in a spec-kit project for stub-only implementations?

Auditing completed tasks in a spec-kit project involves parsing all [X] marked items, running prerequisite validation, checking file presence, matching symbol patterns, and flagging placeholder implementations through semantic verification against spec.md.

Can I filter task verification to specific task IDs and configure the evidence scope?

Yes, completed-task auditing supports optional filtering by specific task IDs and configurable evidence scope, allowing targeted verification of individual tasks marked [X] within the .specify/ structure.

What are the limitations of using git diff cross-references for task verification?

Git diff cross-references for task verification rely on tracked changes, meaning untracked files or symbols declared but never referenced might be missed unless combined with grep-based dead-code detection to scan the full codebase.