Go Verification Before Completion

Name: Go Verification Before Completion
Author: Dankosik

ASecurity

Use for Go verification-only work or when deciding whether existing evidence supports a requested claim at its stated scope.

7 stars

0 votes

0 copies

0 views

Added 9/24/2026

developmentgo

Security Analysis

A100/100

Pro scans all 4 files and shows the line behind each finding

Scanned 9/24/2026

$npx -y skills add Dankosik/go-service-template-rest --skill go-verification-before-completion --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Go Verification Before Completion?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Go Verification Before Completion

[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/dankosik-go-verification-before-completion/badge)](https://www.skillsdirectory.com/skills/dankosik-go-verification-before-completion)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro

Files

SKILL.md

---
name: go-verification-before-completion
description: "Use for Go verification-only work or when deciding whether existing evidence supports a requested claim at its stated scope."
metadata:
  invocation: model
  kind: method
---

# Go Verification Before Completion

An **evidence boundary** is the behavior a proof would fail on. An empirical
claim cannot be wider than that boundary. Local development acceptance is a
separate sufficiency decision owned by [AGENTS.md](../../../AGENTS.md#validation-budget),
not a claim that every production path has been observed.

`claim -> observable -> command or procedure -> result -> exercised scope -> gap`

An Implemented task handoff claims code production, not verified behavior, and
does not trigger this method. Reaching final validation alone does not trigger
it either: use it when a proof boundary or claim-to-evidence match needs a
decision. [Implementation](../../../docs/spec-first-workflow/phases/implementation.md)
owns ledger feedback and final-validation timing.

Apply the [Evidence
Contract](../../../docs/spec-first-workflow/shared/evidence-contract.md) to the
claim or sufficiency question. This skill and its
references do not create new gates or authorize test infrastructure. For a
verification claim, name the observable whose absence or incorrectness would make the
selected proof fail. Record the exact command or procedure, relevant
preconditions, result, cached or fresh state, and scope actually exercised.

A passing command proves only the surfaces it observed. File presence, status,
an implementation summary, a skipped integration suite, a test pattern matching
zero tests, or an unrelated aggregate cannot carry the claim.

Complete when required claims are supported at their stated scope or returned
with the exact missing required proof and owner. Stop ordinary local work at its
accepted build/unit boundary; disclose material optional gaps without blocking
completion or repairing their environment. Never weaken an explicitly requested
runtime or CI result into local success. Return
[Evidence Result
V1](../../../docs/spec-first-workflow/interfaces/evidence-result-v1.md). Load a
matching [reference](references/index.md) only when the boundary is non-obvious.

Attribution

Dankosik

View source See grades on GitHub More from Dankosik →

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

--- name: go-verification-before-completion description: "Use for Go verification-only work or when deciding whether existing evidence supports a requested claim at its stated scope." metadata: invocation: model kind: method --- # Go Verification Before Completion An **evidence boundary** is the behavior a proof would fail on. An empirical claim cannot be wider than that boundary. Local development acceptance is a separate sufficiency decision owned by [AGENTS.md](../../../AGENTS.md#validation-budget), not a claim that every production path has been observed. `claim -> observable -> command or procedure -> result -> exercised scope -> gap` An Implemented task handoff claims code production, not verified behavior, and does not trigger this method. Reaching final validation alone does not trigger it either: use it when a proof boundary or claim-to-evidence match needs a decision. [Implementation](../../../docs/spec-first-workflow/phases/implementation.md) owns ledger feedback and final-validation timing. Apply the [Evidence Contract](../../../docs/spec-first-workflow/shared/evidence-contract.md) to the claim or sufficiency question. This skill and its references do not create new gates or authorize test infrastructure. For a verification claim, name the observable whose absence or incorrectness would make the selected proof fail. Record the exact command or procedure, relevant preconditions, result, cached or fresh state, and scope actually exercised. A passing command proves only the surfaces it observed. File presence, status, an implementation summary, a skipped integration suite, a test pattern matching zero tests, or an unrelated aggregate cannot carry the claim. Complete when required claims are supported at their stated scope or returned with the exact missing required proof and owner. Stop ordinary local work at its accepted build/unit boundary; disclose material optional gaps without blocking completion or repairing their environment. Never weaken an explicitly requested runtime or CI result into local success. Return [Evidence Result V1](../../../docs/spec-first-workflow/interfaces/evidence-result-v1.md). Load a matching [reference](references/index.md) only when the boundary is non-obvious.