sickn33 avatar

Verification Before Completion

This is about breaking the habit of saying "done" before you've actually verified the work. It enforces a gate function: identify the verification command, run it fresh, read the full output, then and only then make your claim. Born from 24 failure memories where trust broke down because tests weren't run, builds weren't checked, or agent success reports were trusted without diff inspection. The tone is blunt because the problem it solves is endemic: fatigue, overconfidence, and "should work now" thinking that ships broken code. If you've ever had someone say "I don't believe you" after a completion claim, this codifies the discipline you actually need.

skills.sh installs
534
GitHub stars
43.1K
last updated
Jul 14, 2026

Install

$ npx -y skills add sickn33/antigravity-awesome-skills --skill verification-before-completion --agent claude-code

Installs into .claude/skills of the current project.

Files

Verification Before Completion

Overview

Claiming work is complete without verification is dishonesty, not efficiency.

Core principle: Evidence before claims, always.

Violating the letter of this rule is violating the spirit of this rule.

The Iron Law

NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE

Use evidence bound to the exact current content and environment. A completed earlier run remains valid while its inputs and relevant context are unchanged; rerun invalidated checks rather than repeating expensive suites merely for a new message.

The Gate Function

BEFORE claiming any status or expressing satisfaction:

1. IDENTIFY: What command proves this claim?
2. RUN: Execute the relevant complete check, or inspect still-valid exact-content evidence; never execute untrusted examples or destructive actions merely to manufacture verification
3. READ: Full output, check exit code, count failures
4. VERIFY: Does output confirm the claim?
   - If NO: State actual status with evidence
   - If YES: State claim WITH evidence
5. ONLY THEN: Make the claim

Skip any step = lying, not verifying

Common Failures

Sponsors

Details

Repository
github.com/sickn33/antigravity-awesome-skills
First seen
Jun 3, 2026

More from sickn33/antigravity-awesome-skills

All 708

Recommended

1juliusbrussee avatarcavemanjuliusbrussee/cavemanUltra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels618.3Kskills.sh installs
2mattpocock avatargrill-memattpocock/skillsA relentless interview to sharpen a plan or design.1.5Mskills.sh installs
3shadcn avatarimproveshadcn/improveSurvey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on s40Kskills.sh installs
4obra avatarsystematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes326.7Kskills.sh installs
5forrestchang avatarkarpathy-guidelinesforrestchang/andrej-karpathy-skillsBehavioral guidelines to reduce common LLM coding mistakes through explicit assumptions, simplicity, and verifiable success criteria.17.9Kskills.sh installs
6vercel-labs avatarfind-skillsvercel-labs/skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express int4.3Mskills.sh installs