verification

Path-conditional verification checklist (basic/standard/strict) with retry loop

16 stars

Best use case

verification is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Path-conditional verification checklist (basic/standard/strict) with retry loop

Teams using verification should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/verification/SKILL.md --create-dirs "https://raw.githubusercontent.com/diegosouzapw/awesome-omni-skill/main/skills/development/verification/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/verification/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How verification Compares

Feature / AgentverificationStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Path-conditional verification checklist (basic/standard/strict) with retry loop

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# 验证循环

## 工具

| 工具 | 类型 | 用法 | 调用方式 |
|:---|:---|:---|:---|
| Superpowers verification-before-completion | Plugin Skill | 完成前结构化检查 | 自动: V 阶段触发 |
| cunzhi MCP | MCP | 验证失败时寸止 | `cunzhi.confirm(VERIFY_FAIL)` |
| skill/debugging | VibeCoding Skill | 2 次失败后加载 | 按需 |

## 流程

```
1. → Superpowers verification-before-completion
2. 执行验证清单 (按 Path 选择)
3. 通过? → done.md (verified: true)
4. 失败?
   → 分析原因 → 修复 → 重试 (max 3)
   → 第 2 次失败: 加载 skill/debugging
   → 第 3 次失败: cunzhi [VERIFY_FAIL] 请求人工
```

## 验证清单 (按 Path 分级)

### Path A — 基础验证

```
□ 所有测试通过
□ Lint 通过
□ 无 console.log / debugger 残留
```

不检查 plan.md (Path A 无 P 阶段)。

### Path B — 标准验证

```
□ 所有测试通过
□ TypeScript 类型检查 (tsc --noEmit)
□ Lint 通过
□ plan.md 目标逐项覆盖
□ 验收标准逐项满足
□ 无 console.log / debugger 残留
□ 无注释掉的代码块
```

### Path C/D — 严格验证

```
□ Path B 全部清单
□ 覆盖率达标 (C: 80%, D: 85%)
□ 无未使用 import
□ 组件 <200 行
□ 单文件 <500 行
□ 安全检查通过 (无硬编码密钥/未验证输入)
```

## .ai_state

- 通过 → done.md 标记 `verified: true`
- 失败 → todo.md 追加修复子任务

## 降级

Superpowers 未安装 → 直接执行上述清单 (AI 自主检查)。

Related Skills

verification-before-completion

16
from diegosouzapw/awesome-omni-skill

Use when finishing any task. Final checklist before marking complete. Ensures nothing forgotten, all tests pass, documentation updated.

android_ui_verification

16
from diegosouzapw/awesome-omni-skill

Automated end-to-end UI testing and verification on an Android Emulator using ADB.

Verification & Quality Assurance

16
from diegosouzapw/awesome-omni-skill

Comprehensive truth scoring, code quality verification, and automatic rollback system with 0.95 accuracy threshold for ensuring high-quality agent outputs and codebase reliability.

acceptance-criteria-verification

16
from diegosouzapw/awesome-omni-skill

Use after implementing features - verifies each acceptance criterion with structured testing and posts verification reports to the GitHub issue

android-qa-verification

16
from diegosouzapw/awesome-omni-skill

This skill is used to verify Android features against acceptance criteria, catch regressions and define tests that reflect real device behaviour.

agent-ops-article-verification

16
from diegosouzapw/awesome-omni-skill

Systematically deconstruct written content into verifiable claims, validate each using search/documentation, and facilitate informed discussion through structured interviewing.

bgo

10
from diegosouzapw/awesome-omni-skill

Automates the complete Blender build-go workflow, from building and packaging your extension/add-on to removing old versions, installing, enabling, and launching Blender for quick testing and iteration.

Coding & Development

employment-contract-templates

16
from diegosouzapw/awesome-omni-skill

Create employment contracts, offer letters, and HR policy documents following legal best practices. Use when drafting employment agreements, creating HR policies, or standardizing employment docume...

eks

16
from diegosouzapw/awesome-omni-skill

AWS EKS Kubernetes management for clusters, node groups, and workloads. Use when creating clusters, configuring IRSA, managing node groups, deploying applications, or integrating with AWS services.

ecosystem-patterns

16
from diegosouzapw/awesome-omni-skill

Use this when creating new projects, generating documentation, cleaning/organizing a repo, suggesting architecture, deploying containers and services, naming files/folders, or when the user references 'ecosystem', 'patterns', or 'containers'. This skill outlines naming conventions, stack preferences, project organization (iMi worktrees), Docker patterns, and PRD structures from past conversations.

dpo-specialist

16
from diegosouzapw/awesome-omni-skill

Expert Data Protection Officer (Datenschutzbeauftragter) with deep knowledge of EU GDPR (DSGVO), German BDSG, and ISO 27701:2025/2019 (PIMS). Specializes in smart integration with existing ISMS infrastructure using Data Reuse principles. Automatically activated when user asks about data protection, privacy, GDPR/DSGVO, BDSG, personal data, DPIA/DSFA, consent, data subject rights, ISO 27701, PIMS, or data breaches.

dotnet-secrets-management

16
from diegosouzapw/awesome-omni-skill

Manages secrets and sensitive config. User secrets, environment variables, rotation.