verification-before-completion

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

2|Updated May 30, 2026
One-click install
npx skills add https://github.com/virahitvin8/crafty-gis --skill verification-before-completion-virahitvin8
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: verification-before-completion
Source: https://github.com/virahitvin8/crafty-gis/tree/main/GIT_STAR/assignment-generator/antigravity-skills-main/antigravity-skills-main/skills/verification-before-completion
Command: npx skills add https://github.com/virahitvin8/crafty-gis --skill verification-before-completion-virahitvin8

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? It prevents false completion claims by requiring fresh verification evidence before stating that tests pass, builds succeed, bugs are fixed, or tasks are done. ## Core Features & Use Cases - Gate Function Workflow: Defines a five-step process (identify, run, read, verify, claim) that must be completed before any success statement. - Claim-to-Evidence Mapping: Specifies which command output is required for common claims such as passing tests, clean linting, successful builds, and fixed bugs. - Rationalization Detection: Lists red flags and common excuses like "should work" or "agent said success" that signal unverified claims. - Use Case: Before committing code or opening a pull request, run the full test suite, confirm zero failures in the output, and only then report that the work is complete. ## Quick Start Before claiming the fix is done, run the full test suite and show me the output confirming zero failures.

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, run it fresh and in full, read the complete output including exit code, and only then state the result. For example, run the test suite and confirm zero failures before saying tests pass.

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 assumptions like "should pass" do not qualify as verification evidence.

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

No, a linter passing does not prove compilation or build success. You must run the actual build command and confirm it exits with code 0 before claiming the build succeeds.

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.

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

No, agent success reports must be independently verified. Check the version control diff to confirm the changes actually exist and match the claimed work before reporting completion.