Install
$ agentstack add skill-grasscaograss-awesomeweldoneskills-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 — Agent 开发方法论
源自 superpowers 的完整开发方法论,为编码 agent 提供结构化的工作流。
核心流程
头脑风暴 → 编写计划 → (子代理驱动 / 内联执行) → 完成分支
↕ ↕
TDD 循环 代码审查 (请求/接收)
↕
验证后完成 + 系统调试
模块索引
| 模块 | 用途 | 何时使用 | |------|------|----------| | [using-superpowers](references/using-superpowers.md) | 入口规则 | 任何对话开始时 | | [brainstorming](references/brainstorming.md) | 设计对话 | 实现任何创意工作之前 | | [writing-plans](references/writing-plans.md) | 编写计划 | 有需求/规格后,写代码前 | | [executing-plans](references/executing-plans.md) | 执行计划 | 有已写好的实现计划时 | | [subagent-driven-development](references/subagent-driven-development.md) | 子代理驱动 | 有独立任务的实现计划 | | [dispatching-parallel-agents](references/dispatching-parallel-agents.md) | 并行分派 | 2+ 个独立任务可并行时 | | [test-driven-development](references/test-driven-development.md) | TDD | 实现功能或修复 bug 前 | | [systematic-debugging](references/systematic-debugging.md) | 系统调试 | 遇到 bug、测试失败或异常行为时 | | [verification-before-completion](references/verification-before-completion.md) | 完成验证 | 声称工作完成/通过前 | | [requesting-code-review](references/requesting-code-review.md) | 请求审查 | 完成任务、实现功能或合并前 | | [receiving-code-review](references/receiving-code-review.md) | 接收审查 | 收到代码审查反馈时 | | [using-git-worktrees](references/using-git-worktrees.md) | 工作区隔离 | 需要隔离的功能开发前 | | [finishing-a-development-branch](references/finishing-a-development-branch.md) | 完成分支 | 实现完成、测试通过后 | | [writing-skills](references/writing-skills.md) | 编写技能 | 创建/编辑/验证 skill 时 |
优先级规则
- 用户的明确指令(CLAUDE.md、直接请求)— 最高优先级
- Superpowers 技能 — 覆盖默认系统行为
- 默认系统提示 — 最低优先级
如果认为某个模块可能适用(哪怕只有 1% 的可能性),就务必阅读该模块。
Source: superpowers by Jesse Vincent
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: grasscaograss
- Source: grasscaograss/AwesomeWeldoneSkills
- License: Apache-2.0
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.