superpowers-verification
Use when about to claim any work is complete, fixed, passing, or successful - requires running fresh verification commands and reading actual output before making any success claims; evidence before assertions always
Best use case
superpowers-verification is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Use when about to claim any work is complete, fixed, passing, or successful - requires running fresh verification commands and reading actual output before making any success claims; evidence before assertions always
Teams using superpowers-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
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/superpowers-verification/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How superpowers-verification Compares
| Feature / Agent | superpowers-verification | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Use when about to claim any work is complete, fixed, passing, or successful - requires running fresh verification commands and reading actual output before making any success claims; evidence before assertions always
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.
Related Guides
AI Agents for Marketing
Discover AI agents for marketing workflows, from SEO and content production to campaign research, outreach, and analytics.
AI Agents for Startups
Explore AI agent skills for startup validation, product research, growth experiments, documentation, and fast execution with small teams.
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
SKILL.md Source
# Superpowers Verification - 证据先行原则 ## 核心准则 **声称工作完成前必须运行验证命令。未运行验证就声称成功 = 说谎，不是效率。** ``` 在声称任何状态之前： 1. 识别：哪个命令能证明这个说法？ 2. 运行：执行完整命令（全新、完整） 3. 读取：完整输出，检查退出码，统计失败数 4. 验证：输出是否证实了说法？ - 如果否：给出实际状态 + 证据 - 如果是：给出说法 + 证据 5. 只有这时：才能做出声称 跳过任何步骤 = 说谎，不是验证 ``` ## 常见验证要求 | 声称 | 需要 | 不够 | |------|------|------| | 测试通过 | 测试命令输出：0 failures | 之前运行过、"应该能过" | | Linter 干净 | Linter 输出：0 errors | 部分检查、推测 | | 构建成功 | 构建命令：exit 0 | Linter 通过、日志看起来正常 | | Bug 修复 | 原始症状测试：通过 | 代码改了、假定修复了 | | 回归测试正常 | 红绿循环验证过 | 测试通过了一次 | | Agent 完成了 | VCS diff 显示变更 | Agent 报告"成功" | | 需求满足 | 逐项检查清单 | 测试通过、阶段完成 | ## 红绿验证循环（Regression Test） ``` ✅ 写测试 → 运行（通过）→ 回滚修复 → 运行（必须失败）→ 恢复 → 运行（通过） ❌ "我写了回归测试"（没有红绿验证） ``` ## 禁止的措辞 以下措辞出现说明还没有验证： - 使用 "应该"、"大概"、"看起来" - 表达满意之前："很好！"、"完美！"、"完成了！"等 - 即将 commit/push/PR 但没有验证 - 信任 agent 的成功报告 - 依赖部分验证 ## 验证检查表（完成工作前必须打勾） - [ ] 运行了完整的测试命令 - [ ] 读取了完整输出 - [ ] 确认 0 failures / exit 0 - [ ] 其他相关测试仍然通过 - [ ] 报告包含实际证据（命令 + 输出摘要） 不能全部打勾？说明跳过了 TDD。从头开始。 ## 为什么这很重要 从 24 个失败记忆中： - 主人说"我不信你"——信任崩塌 - 未定义的函数被发出去——会崩溃 - 未完成的需求被发出去——功能缺失 - 虚假完成浪费时间 → 重新导向 → 返工 ## 何时应用 **永远在此之前：** - 任何成功/完成说法的变体 - 任何表达满意 - 任何正面工作状态描述 - Commit、PR 创建、任务完成 - 转向下一个任务 - 委托给 agents **规则适用于：** - 精确措辞 - 释义和同义词 - 成功/正确的任何暗示
Related Skills
superpowers-executing-plans
Use when executing a written implementation plan in the current session with sequential task execution and review checkpoints - for when subagent-driven mode is not available
superpowers-writing-plans
Use when you have a spec or requirements for a multi-step task, before touching code - guides writing comprehensive implementation plans with bite-sized tasks, TDD, and DRY/YAGNI principles
superpowers-tdd
Use when implementing any feature or bugfix, before writing implementation code - enforces RED-GREEN-REFACTOR cycle: write failing test first, verify it fails, write minimal code, verify it passes, then refactor
superpowers-systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior - enforces systematic four-phase debugging: root cause investigation, pattern analysis, hypothesis testing, and evidence-based fix verification
superpowers-subagent-dev
Use when executing implementation plans with independent tasks - coordinates task execution by dispatching subagents per task with verification checkpoints, adapted for OpenClaw's isolated session model
superpowers-parallel-agents
Use when facing 2 or more independent tasks that can be worked on without shared state - dispatches parallel subagents using sessions_spawn for concurrent investigation and execution, adapted for OpenClaw
superpowers-overview
Use when starting any development work or when unsure which superpowers development skill to use - provides entry point and navigation to the full superpowers skill suite for OpenClaw agents
superpowers-isolated-workspace
Use when starting feature work that needs isolation from current workspace - creates isolated git branches with clean setup and safety verification, adapted for OpenClaw environments
superpowers-finishing-branch
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - presents structured options for merge, PR, or cleanup; adapted for OpenClaw git workflow without worktrees
superpowers-brainstorming
Use before any creative work - creating features, building components, adding functionality, or modifying behavior - guides through exploration, questioning, design proposal, and spec documentation before any implementation
superpowers-requesting-code-review
Use when completing tasks, implementing major features, or before merging - dispatches code review subagent to catch issues before they cascade, adapted for OpenClaw sessions_spawn model
superpowers-receiving-code-review
Use when receiving code review feedback - requires technical verification before implementing suggestions, with reasoned pushback when feedback is technically questionable; no performative agreement