verification-before-completion

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

Updated May 19, 2026
One-click install
npx skills add https://github.com/davidsunglee/pi-flow --skill verification-before-completion-davidsunglee
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: verification-before-completion
Source: https://github.com/davidsunglee/pi-flow/tree/main/packages/pi-flow-core/skills/verification-before-completion
Command: npx skills add https://github.com/davidsunglee/pi-flow --skill verification-before-completion-davidsunglee

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 fresh verification, leading to false status reports, broken commits, and wasted rework. ## Core Features & Use Cases - Evidence Gate: Defines a five-step gate (identify, run, read, verify, claim) that must be completed before any success claim is made. - Failure Pattern Catalog: Maps common claims (tests pass, build succeeds, bug fixed, agent completed) to the exact evidence required and what is not sufficient. - Rationalization Blocking: Lists red-flag phrases and excuses like "should work" or "agent said success" 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, verify the regression test fails without the fix, and only then report completion with evidence. ## Quick Start Before claiming any task is complete, run the relevant verification command, read the full output, and state the result with evidence.

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 work is complete before claiming success?▼

Identify the command that proves the claim, run it fresh and in full, read the entire output including exit code, and only then state the claim with that evidence. Skipping any step counts as an unverified claim.

What counts as sufficient evidence that tests pass?▼

Sufficient evidence is fresh test command output showing zero failures. Previous runs, partial checks, linter results, or assumptions like "should pass" do not qualify as verification.

How do I verify a regression test actually works?▼

Use a 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.

Can I trust a subagent's report that a task succeeded?▼

No. Agent success reports must be independently verified by checking the VCS diff and confirming the actual changes match the claimed outcome before reporting completion.

Why is linter output not enough to claim a build succeeds?▼

Linters check style and static issues but do not compile the code. A build claim requires running the build command and confirming exit code 0 from its output.