Agent Skills › HashWarlock/nobody-plans-for-pi › nobody-verifies-before-completion

nobody-verifies-before-completion

GitHub

强制在声称工作完成前执行验证命令并检查输出，禁止无证据断言成功。确保测试、构建或修复结果真实可靠，防止未经验证即提交或报告通过。

skills/nobody-verifies-before-completion/SKILL.md HashWarlock/nobody-plans-for-pi

触发场景

准备声明任务已完成确认Bug已修复报告测试或构建通过

安装

npx skills add HashWarlock/nobody-plans-for-pi --skill nobody-verifies-before-completion -g -y

更多选项

不安装直接使用

npx skills use HashWarlock/nobody-plans-for-pi@nobody-verifies-before-completion

指定 Agent (Claude Code)

npx skills add HashWarlock/nobody-plans-for-pi --skill nobody-verifies-before-completion -a claude-code -g -y

安装 repo 全部 skill

npx skills add HashWarlock/nobody-plans-for-pi --all -g -y

预览 repo 内 skill

npx skills add HashWarlock/nobody-plans-for-pi --list

SKILL.md

Frontmatter

{
    "name": "nobody-verifies-before-completion",
    "description": "Use when about to claim work is complete, fixed, or passing — requires running verification commands and confirming output before making any success claims"
}

Verification Before Completion

Overview

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

Core principle: Evidence before claims, always.

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

Before claiming ANY status:

IDENTIFY — What command proves this claim?
RUN — Execute the FULL command (fresh, complete)
READ — Full output, check exit code, count failures
VERIFY — Does output confirm the claim?
ONLY THEN — Make the claim

Skip any step = lying, not verifying.

Common Failures

Claim	Requires	Not Sufficient
Tests pass	Test command output: 0 failures	Previous run, "should pass"
Build succeeds	Build output: exit 0	Linter passing
Bug fixed	Original symptom test: passes	Code changed, assumed fixed
Requirements met	Line-by-line checklist	Tests passing

Red Flags — STOP

Using "should", "probably", "seems to"
Expressing satisfaction before verification ("Great!", "Done!")
About to commit/push without verification
Trusting subagent success reports without checking
Relying on partial verification

Rationalization Prevention

Excuse	Reality
"Should work now"	RUN the verification
"I'm confident"	Confidence ≠ evidence
"Just this once"	No exceptions
"Partial check is enough"	Partial proves nothing
"Agent said success"	Verify independently