verification-before-completion

Enforces running verification commands before claiming work is complete or passing.

Updated May 28, 2026
One-click install
npx skills add https://github.com/mpmf/SDD_Base --skill verification-before-completion-mpmf
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: verification-before-completion
Source: https://github.com/mpmf/SDD_Base/tree/main/.opencode/skills/superpowers/verification-before-completion
Command: npx skills add https://github.com/mpmf/SDD_Base --skill verification-before-completion-mpmf

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? AI agents and developers often claim work is complete, tests pass, or bugs are fixed without actually running verification commands, leading to broken builds, shipped defects, and lost trust. This Skill enforces an evidence-first discipline so no success claim is made without fresh command output. ## Core Features & Use Cases - Verification Gate: A five-step gate function (identify, run, read, verify, claim) that must be completed before any completion statement. - Claim-to-Evidence Mapping: A table mapping common claims (tests pass, build succeeds, bug fixed) to the exact command output required to support them. - Rationalization Blocking: Red-flag phrases and excuse patterns ("should work", "just this once", "agent said success") that trigger mandatory re-verification. - Use Case: Before committing a bug fix, run the test suite, confirm zero failures in the output, and only then state that the fix works, citing the evidence. ## Quick Start Before claiming any task is done, run the relevant verification command and report the actual output alongside your claim.

Frequently Asked Questions about verification-before-completion

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

FAQPage Schema
How do I verify work is complete before committing code?▼

Identify the command that proves your claim, run it fresh and in full, read the complete output including exit code, and only then state the result with that evidence. Never commit based on previous runs or assumptions.

How to verify a regression test actually works?▼

Use the red-green cycle: write the test, run it to confirm it passes with the fix, revert the fix and confirm the test fails, then restore the fix and confirm it passes again. A single passing run does not prove the test catches the bug.

Does a passing linter mean the build succeeds?▼

No. A linter checks style and static issues but does not verify compilation. You must run the actual build command and confirm exit code 0 before claiming the build succeeds.

Can I trust an agent's success report without checking?▼

No. Agent success reports must be independently verified by inspecting the VCS diff and confirming the actual changes match the claimed work before reporting completion.

When should verification be skipped for small changes?▼

Never. The rule has no exceptions: partial checks, confidence, fatigue, and "just this once" reasoning are explicitly listed as rationalizations that violate the evidence-before-claims principle.