agentsclimarketplace

Verification before completion

Skill Yco-0314/strata/skills/l4-review/verification-before-completion

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs — requires running verification commands and confirming output before any success claim; evidence before assertions always.From its SKILL.md

Install
npx -y skills add Yco-0314/strata --skill verification-before-completion

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its file declares

Copied from the file, not written here

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

2.6 KB, 506 tokens by cl100k_base, as published. Nobody here has run it

Verification before completion — L4 evidence gate

Claiming work is done without verification is dishonesty, not efficiency. Every "it works" in this framework routes through this gate.

The Iron Law

NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE

If you haven't run the verification command in this message, you cannot claim it passes.

The gate function

Before claiming any status or expressing satisfaction:

  1. Identify — what command proves this claim?
  2. Run — execute the full command, fresh and complete.
  3. Read — full output, exit code, failure count.
  4. Verify — does the output confirm the claim? No → state the actual status with the evidence. Yes → state the claim with the evidence.

Skipping any step is lying, not verifying.

What each claim actually requires

ClaimRequiresNot sufficient
Tests passTest output: 0 failures"should pass", a previous run
Linter cleanLinter output: 0 errorspartial check, extrapolation
Build succeedsBuild exit 0linter passing, "logs look good"
Bug fixedOriginal symptom re-tested: passescode changed, assumed fixed
Regression test worksRed→green cycle verified (revert fix → must fail → restore → pass)test passes once
Subagent completedVCS diff shows the changesthe agent reported "success"
Requirements metLine-by-line checklisttests passing

Red flags — stop

"should" / "probably" / "seems to"; "Great!"/"Perfect!"/"Done!" before evidence; about to commit/push/PR unverified; trusting an agent's success report; "just this once"; tired and wanting it over. Any wording implying success without having run the check.

ExcuseReality
"Should work now"Run the verification.
"I'm confident"Confidence ≠ evidence.
"Linter passed"Linter ≠ compiler.
"Agent said success"Verify independently (check the diff).
"Partial check is enough"Partial proves nothing.

Run the command. Read the output. Then claim the result. Non-negotiable.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Keep looking

Skills are one crate of 326,834. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.