Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

Verification Before Completion · jnmetacode | DecimalAI

testingby jnmetacode

Verification Before Completion

jnmetacode/verification-before-completion

Source jnmetacode/superpowers-zh ↗License MIT

在宣称工作完成、已修复或测试通过之前使用，在提交或创建 PR 之前——必须运行验证命令并确认输出后才能声称成功；始终用证据支撑断言

NewMaintained

Automatic

QA & Test Engineering pack

Last verified 8/11/2026

What it changes

Passed 7 of 21 test cases with the skill, and 14 of 21 without it.

Without skill67%

With skill33%

0 fixed4 passed either way14 still failing4 broke

Pass-rate lift: -33 pp
Tokens: +59%
Agent turns: 0%
Response time: -17%

Model gemini-3.6-flashMeasured 8/11/2026v24 of 22 cases passed with skill · 21 comparable

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/jnmetacode-verification-before-completion/SKILL.md https://app.decimal.ai/s/jnmetacode-verification-before-completion/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add jnmetacode-verification-before-completion, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/jnmetacode-verification-before-completion/ and pins it in .decimal/skills.lock

decimalai skills add jnmetacode-verification-before-completion

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/jnmetacode-verification-before-completion/SKILL.md https://app.decimal.ai/s/jnmetacode-verification-before-completion/SKILL.md

Raw file: /s/jnmetacode-verification-before-completion/SKILL.md ↗ · machine-readable summary at /s/jnmetacode-verification-before-completion.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

What's inside

The instructions your model reads when the skill loads.

SKILL.md115 linessingle file

完成前验证

概述

核心原则： 始终用证据支撑结论。

对这条规则敷衍了事，就等于违背了它的精神。

铁律

没有新鲜的验证证据，不许宣称完成

如果你在这条消息中没有运行验证命令，就不能声称测试通过。

门控函数

在宣称任何状态或表达满意之前：

1. 确定：什么命令能证明这个结论？
2. 运行：执行完整命令（重新运行，完整执行）
3. 阅读：完整输出，检查退出码，统计失败数
4. 验证：输出是否支持这个结论？
   - 如果否：用证据说明实际状态
   - 如果是：带证据陈述结论
5. 只有这时：才能做出结论

跳过任何一步 = 说谎，不是验证

常见失败模式

结论	需要	不够格
测试通过	测试命令输出：0 failures	之前的运行结果、"应该会通过"
Linter 无报错	Linter 输出：0 errors	部分检查、推断
构建成功	构建命令：exit 0	linter 通过、日志看起来没问题
Bug 已修复	测试原始症状：通过	代码改了，假设已修复

Track record

Benchmark

7 / 21

test cases passed, vs 14 / 21 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/10/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

jnmetacode / superpowers-zh

skills/verification-before-completion/SKILL.md

View on GitHub ↗

License MITImported 8/10/2026Version v2

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

More skills from the same source and nearby in the registry, with their headline benchmark lift.