verification-before-completion

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

2|Updated Jul 25, 2026
One-click install
npx skills add https://github.com/ankaboot-source/boucle --skill verification-before-completion-ankaboot-source
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: verification-before-completion
Source: https://github.com/ankaboot-source/boucle/tree/main/.jcode/skills/verification-before-completion
Command: npx skills add https://github.com/ankaboot-source/boucle --skill verification-before-completion-ankaboot-source

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? AI agents and developers often claim work is complete, fixed, or passing without actually running the verification commands, leading to broken code shipped, lost trust, and wasted rework cycles. ## Core Features & Use Cases - Evidence-First Gate: Requires identifying, running, and reading the full output of a verification command before any success claim is made. - Claim-to-Evidence Mapping: Defines what proof each claim type requires, such as test output for passing tests, exit code 0 for builds, and red-green cycles for regression tests. - Rationalization Blocking: Lists common excuses like "should work now" or "linter passed" and counters each with the required verification action. - Use Case: Before committing a bug fix, run the test suite, confirm zero failures in the output, and only then state the fix is verified with the evidence attached. ## Quick Start Before claiming any task is done, run the relevant test or build command and report the actual output alongside your completion 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 code changes before committing?

Identify the command that proves your claim, such as the test suite or build command, run it fresh and completely, then read the full output and exit code. Only state the change works after the output confirms it, citing the evidence.

What counts as evidence that tests pass?

Evidence is the actual output of a freshly run test command showing zero failures, such as "34/34 pass". Previous runs, partial checks, or statements like "should pass" do not qualify as verification.

Does a passing linter mean the build succeeds?

No, a linter passing does not prove compilation succeeds. Linters check style and syntax patterns, not full compilation, so you must run the actual build command and confirm exit code 0.

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. Check the version control diff to confirm actual changes exist and run the relevant verification commands yourself before reporting the real state.