Install
$ agentstack add skill-yinqd3-workbuddy-skills-using-superpowers ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Superpowers — WorkBuddy 版
基于 obra/superpowers 适配的软件工程方法论技能集。
核心理念
想法 → 头脑风暴 → 计划 → TDD 执行 → 代码审查 → 完成
不是建议,是强制管线。 "太简单不需要设计" —— 这是最危险的幻觉。
技能管线总览
| 阶段 | 技能 | 触发条件 | |:---|:---|:---| | 0. 入口 | using-superpowers | 任何编码任务开始时 | | 1. 设计 | brainstorming | 新功能/改动需求 → 先设计再动手 | | 2. 计划 | writing-plans | 设计确认后 → 写详细实现计划 | | 3. 执行 | executing-plans 或 subagent-driven-development | 按计划逐任务执行 | | 4. TDD | test-driven-development | 每个实现步骤强制 TDD | | 5. 调试 | systematic-debugging | Bug / 测试失败 → 四阶段系统调试 | | 6. 审查 | requesting-code-review / receiving-code-review | 代码变更后审查 | | 7. 验证 | verification-before-completion | 完成前强制验证 | | 8. 收尾 | finishing-a-development-branch | 所有任务完成,测试通过 | | 9. 并行 | dispatching-parallel-agents | 多子代理并行任务 | | 10. 元技能 | writing-skills | 编写/改进 Skill 本身 |
四条铁律
- 先设计再动手 → 没有例外,再简单的项目也要先过 brainstorming
- TDD 不可跳过 → 没有失败的测试,就没有生产代码
- 先根因再修复 → 没有根因调查,不许提修复方案
- 每一步都要验证 → 完成 ≠ 做完,验证通过才算完成
适配说明
原版为 Claude Code/Codex 设计,WorkBuddy 版做了以下适配:
- 子代理调度:
sessions_spawn→ WorkBuddyAgent工具 +TaskCreate - 代码审查:Claude Code Task → WorkBuddy
Agent(审查子代理) - 文件路径约定:
docs/superpowers/→docs/plans/ - 语言支持:中英双语描述,代码示例以 Python/TypeScript 为主
- 移除了
using-git-worktrees(WorkBuddy 场景不常用)
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: yinqd3
- Source: yinqd3/workbuddy-skills
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.