skills.rest
alex-jordan547
alex-jordan547COMMUNITY
Explore all skills by this author →
GitHub

verification-before-completion

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

Updated Jul 3, 2026
Search Tags:#code quality#testing#debugging#verification#evidence#ci#completion claims
One-click install
npx skills add https://github.com/alex-jordan547/agent-setup --skill verification-before-completion-alex-jordan547
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: verification-before-completion
Source: https://github.com/alex-jordan547/agent-setup/tree/main/archive/2026-09-10/verification-before-completion
Command: npx skills add https://github.com/alex-jordan547/agent-setup --skill verification-before-completion-alex-jordan547

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? AI agents and developers often claim work is done, tests pass, or bugs are fixed without actually running the verification commands, leading to broken code, lost trust, and wasted rework. This Skill blocks any completion claim until fresh command output proves it. ## Core Features & Use Cases - Evidence Gate: A five-step gate (identify, run, read, verify, claim) that must be completed before any success statement. - Claim-to-Command Mapping: A table matching common claims (tests pass, build succeeds, bug fixed) to the exact command output required as proof. - Rationalization Detection: Red-flag phrases and excuse patterns ("should work", "just this once", "agent said success") that trigger a stop. - Use Case: Before committing a bug fix, run the original failing test, confirm it passes, then state the fix works with the actual output as evidence. ## Quick Start Before claiming the task 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 completely, read the full output including exit code, then state your claim with that evidence. Never commit based on previous runs or assumptions.

How to confirm a bug is actually fixed?▼

Reproduce the original symptom with a test and confirm it now passes. Changing the code is not sufficient evidence; you must run the test that exercises the original failure and observe it pass.

Does a passing linter mean the build succeeds?▼

No, a linter passing does not prove compilation succeeds. Linters check style and some errors but do not verify the build; you must run the actual build command and confirm exit code 0.

How do I verify a regression test really works?▼

Use the red-green cycle: write the test, run it with the fix to see it pass, 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 success report without checking?▼

No, agent success reports must be verified independently. Check the version control diff to confirm actual changes were made and run the relevant verification commands yourself before reporting completion.

Related Skills

Explore More Software Engineering Skills→
viniciuscs84viniciuscs84

test-driven-development

Enforces red-green-refactor test-first workflow for implementing features and bugfixes.

Community
Intermediate
basicmachines-cobasicmachines-co
4.0k

pr-create

Creates or updates Basic Memory pull requests and runs the Codex review loop.

Official
Intermediate
nateanatea

shift-left-testing

Validate requirements and generate tests earlier in CI/CD pipelines.

Community
Advanced
0xmariowu0xmariowu
4

autoloop

Automate execution, verification, and shipping of pre-approved plans.

Community
Advanced