verification-before-completion

Require fresh command execution and evidence before reporting completion status.

6|Updated Mar 21, 2026
One-click install
npx skills add https://github.com/caitengwei/my-skills --skill verification-before-completion-caitengwei
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: verification-before-completion
Source: https://github.com/caitengwei/my-skills/tree/main/superpowers/skills/verification-before-completion
Command: npx skills add https://github.com/caitengwei/my-skills --skill verification-before-completion-caitengwei

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It prevents false “done/passing/complete” claims by forcing evidence-based verification before any success or completion statement is made.

Core Features & Use Cases

  • Evidence-before-claims guardrail: Requires identifying a specific verification command, running it fresh, and using the full output to support any completion statement.
  • Anti-rationalization checks: Flags common failure patterns like “should work,” trusting agent reports, partial checks, and expressing satisfaction without verification.
  • Practical workflow enforcement: Applies to tasks like tests, linting, builds, bug fixes, regression verification, requirements checklists, and release/PR readiness decisions.

Quick Start

Use this skill before you commit, open a PR, or say the work is complete by first running the full verification command and then reporting the actual results with evidence from the command output.

Frequently Asked Questions about verification-before-completion

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

FAQPage Schema
How do I prevent false completion claims before opening a pull request?▼

Preventing false completion claims requires evidence-based verification by running a fresh test or build command and reviewing the full output before asserting any passing status.

What is evidence-based reporting for software delivery workflows?▼

Evidence-based reporting enforces a full command execution and exit-code review, ensuring every readiness or completion statement is backed by actual verification output.

How do I verify bug fixes and regression confirmation before committing?▼

Verifying bug fixes requires identifying a specific verification command, running it fresh, and using the full command output to support the completion statement before committing.

Does this verification approach work with linting and build readiness checks?▼

This verification approach applies directly to linting, building, and regression confirmation by enforcing fresh command execution and evidence-backed status reporting for readiness decisions.

What are common anti-rationalization checks for premature completion claims?▼

Anti-rationalization checks flag common failure patterns like stating "should work," trusting agent reports without verification, performing partial checks, or expressing satisfaction without fresh evidence.

When should I not use an evidence-first verification workflow?▼

Evidence-first verification is not suitable for exploratory drafting or rapid prototyping phases where code changes too rapidly to justify running full verification commands before every statement.