verification-before-completion

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

Updated Aug 2, 2026
One-click install
npx skills add https://github.com/leonardoacosta/skills --skill verification-before-completion-leonardoacosta
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: verification-before-completion
Source: https://github.com/leonardoacosta/skills/tree/main/leo-core/skills/verification-before-completion
Command: npx skills add https://github.com/leonardoacosta/skills --skill verification-before-completion-leonardoacosta

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? AI agents and developers often claim work is done, fixed, or passing based on assumptions, partial checks, or stale results rather than fresh evidence. This Skill enforces a strict rule: no completion claims without running the actual verification command and reading its full output first. ## Core Features & Use Cases - Evidence-First Claims: Maps common claims (tests pass, build succeeds, bug fixed) to the exact command output required to justify them, and lists what does not count as proof. - Rationalization Detection: Provides a table of common excuses ("should work now", "linter passed", "agent said success") and explains why each one fails the verification gate. - Red-Green Regression Checks: Defines the full TDD cycle for regression tests, requiring the test to fail without the fix before it counts. - Use Case: Before committing a bug fix, run the test suite fresh, confirm zero failures in the output, then state the result with that evidence instead of saying it "should pass". ## Quick Start Before claiming any task is complete, run the verification command for your claim and report the result together with the actual 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 verify code changes before committing?

Identify the command that proves your claim, such as the test suite or build command, run it fresh, and read the full output. Only state the claim after confirming the result, for example zero test failures or exit code 0.

What counts as evidence that tests pass?

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

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 only passes once is not verified.

Can I trust a linter passing as proof the build works?

No. A linter does not check compilation, so linter success is not evidence the build succeeds. Run the actual build command and confirm it exits with code 0 before claiming the build passes.

Should I trust another agent's success report?

No. Agent success reports are claims, not evidence. Check the version control diff to confirm the changes exist and independently verify the result before reporting the actual state.