verification-before-completion

Enforces running verification commands and reading output before claiming work is complete.

Updated Mar 26, 2026
One-click install
npx skills add https://github.com/LGJ-Jonathan/Jonathan_Global_Claude_Skills --skill verification-before-completion-lgj-jonathan
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: verification-before-completion
Source: https://github.com/LGJ-Jonathan/Jonathan_Global_Claude_Skills/tree/main/superpowers/skills/verification-before-completion
Command: npx skills add https://github.com/LGJ-Jonathan/Jonathan_Global_Claude_Skills --skill verification-before-completion-lgj-jonathan

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 mandatory five-step gate (identify, run, read, verify, claim) that must be completed before any completion statement. - Failure Pattern Catalog: Tables mapping common claims (tests pass, build succeeds, bug fixed) to the exact evidence required and what does not count as proof. - Rationalization Blocking: Explicit counterarguments for excuses like "should work now", "linter passed", or "agent said success". - Use Case: Before committing a bug fix, the agent runs the test suite, confirms zero failures in the output, and only then reports the fix as verified with the evidence attached. ## Quick Start Before claiming any task is done, run the relevant verification command, read the full output, and only then state the result with the evidence.

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 entire output including exit code, and confirm it matches your claim. Only then state the result, citing the evidence such as test counts or exit status.

What counts as evidence that tests pass?

Evidence is the actual output of a freshly run test command showing zero failures. Previous runs, assumptions like "should pass", partial checks, or linter results do not count as verification evidence.

How do I 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 test that never fails proves nothing.

Can I trust an agent's report that a task succeeded?

No. Agent success reports must be independently verified by checking the version control diff and confirming the actual changes exist. Trusting a report without inspection is a common source of false completion claims.

Why is linter output not enough to claim a build succeeds?

Linters check style and static issues but do not compile or link code. A build claim requires running the actual build command and confirming it exits with code zero.