重要前提
安装AI Skills的关键前提是:必须科学上网,且开启TUN模式,这一点至关重要,直接决定安装能否顺利完成,在此郑重提醒三遍:科学上网,科学上网,科学上网。查看完整安装教程 →
verification-before-completion by guanyang/antigravity-skills
npx skills add https://github.com/guanyang/antigravity-skills --skill verification-before-completion未经验证就宣称工作已完成,这是不诚实的行为,而非高效。
核心原则: 先有证据,再作宣称,始终如此。
违反此规则的字面要求即违反其精神。
NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE
如果你没有在当前消息中运行验证命令,就不能宣称它已通过。
BEFORE claiming any status or expressing satisfaction:
1. IDENTIFY: What command proves this claim?
2. RUN: Execute the FULL command (fresh, complete)
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
| 宣称 | 要求 | 不充分 |
|---|---|---|
| 测试通过 | 测试命令输出:0 失败 |
广告位招租
在这里展示您的产品或服务
触达数万 AI 开发者,精准高效
| 之前的运行结果,"应该通过" |
| 代码检查通过 | 代码检查输出:0 错误 | 部分检查,推测 |
| 构建成功 | 构建命令:退出码 0 | 代码检查通过,日志看起来没问题 |
| Bug 已修复 | 测试原始症状:通过 | 代码已更改,假设已修复 |
| 回归测试有效 | 红绿循环已验证 | 测试通过一次 |
| 代理已完成 | VCS 差异显示更改 | 代理报告"成功" |
| 需求已满足 | 逐项核对清单 | 测试通过 |
| 借口 | 现实 |
|---|---|
| "现在应该可以了" | 运行验证 |
| "我有信心" | 信心 ≠ 证据 |
| "就这一次" | 没有例外 |
| "代码检查通过了" | 代码检查 ≠ 编译 |
| "代理说成功了" | 独立验证 |
| "我累了" | 疲惫 ≠ 借口 |
| "部分检查就够了" | 部分证明不了什么 |
| "措辞不同所以规则不适用" | 精神高于字面 |
测试:
✅ [运行测试命令] [查看:34/34 通过] "所有测试通过"
❌ "现在应该通过了" / "看起来正确"
回归测试(TDD 红绿循环):
✅ 编写 → 运行(通过)→ 撤销修复 → 运行(必须失败)→ 恢复 → 运行(通过)
❌ "我已经写了一个回归测试"(未进行红绿验证)
构建:
✅ [运行构建] [查看:退出码 0] "构建通过"
❌ "代码检查通过了"(代码检查不检查编译)
需求:
✅ 重读计划 → 创建核对清单 → 逐项验证 → 报告差距或完成情况
❌ "测试通过,阶段完成"
代理委派:
✅ 代理报告成功 → 检查 VCS 差异 → 验证更改 → 报告实际状态
❌ 信任代理报告
基于 24 次失败记忆:
总是在以下情况之前:
规则适用于:
验证没有捷径。
运行命令。阅读输出。然后宣称结果。
这是不可协商的。
每周安装量
48
仓库
GitHub 星标
508
首次出现
Jan 26, 2026
安全审计
安装于
opencode44
codex43
github-copilot42
cursor41
kimi-cli41
gemini-cli41
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.
NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE
If you haven't run the verification command in this message, you cannot claim it passes.
BEFORE claiming any status or expressing satisfaction:
1. IDENTIFY: What command proves this claim?
2. RUN: Execute the FULL command (fresh, complete)
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
| Claim | Requires | Not Sufficient |
|---|---|---|
| Tests pass | Test command output: 0 failures | Previous run, "should pass" |
| Linter clean | Linter output: 0 errors | Partial check, extrapolation |
| Build succeeds | Build command: exit 0 | Linter passing, logs look good |
| Bug fixed | Test original symptom: passes | Code changed, assumed fixed |
| Regression test works | Red-green cycle verified | Test passes once |
| Agent completed | VCS diff shows changes | Agent reports "success" |
| Requirements met | Line-by-line checklist | Tests passing |
| Excuse | Reality |
|---|---|
| "Should work now" | RUN the verification |
| "I'm confident" | Confidence ≠ evidence |
| "Just this once" | No exceptions |
| "Linter passed" | Linter ≠ compiler |
| "Agent said success" | Verify independently |
| "I'm tired" | Exhaustion ≠ excuse |
| "Partial check is enough" | Partial proves nothing |
| "Different words so rule doesn't apply" | Spirit over letter |
Tests:
✅ [Run test command] [See: 34/34 pass] "All tests pass"
❌ "Should pass now" / "Looks correct"
Regression tests (TDD Red-Green):
✅ Write → Run (pass) → Revert fix → Run (MUST FAIL) → Restore → Run (pass)
❌ "I've written a regression test" (without red-green verification)
Build:
✅ [Run build] [See: exit 0] "Build passes"
❌ "Linter passed" (linter doesn't check compilation)
Requirements:
✅ Re-read plan → Create checklist → Verify each → Report gaps or completion
❌ "Tests pass, phase complete"
Agent delegation:
✅ Agent reports success → Check VCS diff → Verify changes → Report actual state
❌ Trust agent report
From 24 failure memories:
ALWAYS before:
Rule applies to:
No shortcuts for verification.
Run the command. Read the output. THEN claim the result.
This is non-negotiable.
Weekly Installs
48
Repository
GitHub Stars
508
First Seen
Jan 26, 2026
Security Audits
Gen Agent Trust HubPassSocketPassSnykPass
Installed on
opencode44
codex43
github-copilot42
cursor41
kimi-cli41
gemini-cli41
后端测试指南:API端点、业务逻辑与数据库测试最佳实践
11,800 周安装