verification-before-completion

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

3|1|Updated Jul 12, 2026
One-click install
npx skills add https://github.com/DuckKota/my-opencode-setup --skill verification-before-completion-duckkota
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: verification-before-completion
Source: https://github.com/DuckKota/my-opencode-setup/tree/main/src/skills/verification-before-completion
Command: npx skills add https://github.com/DuckKota/my-opencode-setup --skill verification-before-completion-duckkota

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 commits and false status reports. This Skill enforces an evidence-before-claims discipline so no success statement is made without fresh command output. ## Core Features & Use Cases - Verification Gate: A five-step gate function (identify, run, read, verify, claim) that must be completed before any completion claim. - Failure Pattern Tables: Concrete mappings of claims (tests pass, build succeeds, bug fixed) to the exact evidence required, plus common rationalizations to reject. - Red-Green Regression Checks: Requires reverting a fix to confirm a regression test actually fails before trusting it. - Use Case: Before committing a bug fix, the agent runs the full test suite, confirms zero failures in the output, and only then reports the fix as verified with the evidence attached. ## Quick Start Ask the agent to verify the fix by running the full test suite and only claim completion after confirming the output shows 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?▼

Run the full verification command for your claim, such as the test suite or build, and read the complete output including exit code and failure count. Only state the claim after the output confirms it, citing the evidence alongside the claim.

How to confirm a bug is actually fixed?▼

Reproduce the original symptom with a test and confirm it passes after the fix. For regression tests, use a red-green cycle: revert the fix, confirm the test fails, restore the fix, and confirm it passes again.

Does a passing linter mean the build succeeds?▼

No, a linter passing does not prove compilation succeeds. Linters check style and static issues but do not run the compiler, so you must execute the build command and confirm exit code 0 before claiming the build passes.

Can I trust an agent's success report without checking?▼

No, agent success reports must be verified independently. Inspect the version control diff to confirm the claimed changes actually exist and run the relevant verification commands before reporting the actual state.

When should verification run in a development workflow?▼

Run verification before any completion claim, expression of satisfaction, commit, pull request, task handoff, or delegation to another agent. The rule applies to exact phrases, paraphrases, and any wording implying success.