verification-before-completion

Run verification commands and report results only when checks pass.

Updated Jan 7, 2026
One-click install
npx skills add https://github.com/miles990/claude-starter-kit --skill verification-before-completion-miles990
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: verification-before-completion
Source: https://github.com/miles990/claude-starter-kit/tree/main/.claude/skills/verification-before-completion
Command: npx skills add https://github.com/miles990/claude-starter-kit --skill verification-before-completion-miles990

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill prevents dishonest completion claims by mandating fresh verification evidence before any status updates or PRs, ensuring accountability and traceability.

Core Features & Use Cases

  • Verification mandate: Require running full verification commands and checking outputs before affirming success.
  • Evidence-driven claims: Ensure results are accompanied by verifiable evidence from tests, linters, builds, and reviews.
  • Workflow alignment: Suitable for development, code reviews, CI pipelines, and release tasks that require validated conclusions.

Quick Start

  • Run the full verification command for the current task and review the output to determine whether a claim is warranted.

Frequently Asked Questions about verification-before-completion

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

FAQPage Schema
How do I enforce verification before claiming a software task is complete?

To enforce verification before completion, you must run full verification commands, review their outputs, and check exit codes. A completion claim is only valid when accompanied by fresh evidence from tests, linters, or builds.

What is evidence-driven QA verification in a CI pipeline?

Evidence-driven QA verification requires running full tests and builds in your CI pipeline, then attaching the actual command outputs and exit codes as proof. This ensures accountability and traceability before updating any task status.

How do I prevent dishonest completion claims during code reviews?

Preventing dishonest completion claims during code reviews requires mandating fresh verification evidence. You must run the full test suite and validate the output to confirm that functional requirements are genuinely met before approving.

Does this verification mandate work for release tasks and builds?

Yes, this verification mandate works for release tasks and builds. It aligns with development workflows by requiring you to run verification commands, read the outputs, and report validated conclusions only when the exit codes confirm success.

When do I need to attach fresh evidence to a pull request?

You need to attach fresh evidence to a pull request whenever you claim a task is complete. This requires running full verification commands like tests and linters, then providing the verifiable results to prove the code is functional.