npx skills add https://github.com/aaaaqwq/agi-super-skills --skill 'Writing Plans'编写全面的实施计划,假设工程师对我们的代码库零了解且品味存疑。记录他们需要知道的一切:每个任务需要修改哪些文件、代码、可能需要查阅的测试和文档、如何测试。将整个计划分解为易于处理的小任务。遵循 DRY、YAGNI、TDD 原则。频繁提交。
假设他们是一名熟练的开发人员,但几乎不了解我们的工具集或问题领域。假设他们不太了解良好的测试设计。
开始时声明: "我正在使用 Writing Plans 技能来创建实施计划。"
上下文: 这应在专用工作树中运行(由头脑风暴技能创建)。
计划保存至: docs/plans/YYYY-MM-DD-<feature-name>.md
每个步骤是一个操作(2-5 分钟):
每个计划必须以此头部开始:
# [功能名称] 实施计划
> **给 Claude 的提示:** 使用 `${SUPERPOWERS_SKILLS_ROOT}/skills/collaboration/executing-plans/SKILL.md` 来按任务实施此计划。
**目标:** [一句话描述此计划构建的内容]
**架构:** [2-3 句话描述方法]
**技术栈:** [关键技术/库]
---
### 任务 N: [组件名称]
**文件:**
- 创建:`exact/path/to/file.py`
- 修改:`exact/path/to/existing.py:123-145`
- 测试:`tests/exact/path/to/test.py`
**步骤 1: 编写失败的测试**
```python
def test_specific_behavior():
result = function(input)
assert result == expected
广告位招租
在这里展示您的产品或服务
触达数万 AI 开发者,精准高效
步骤 2: 运行测试以验证其失败
运行:pytest tests/path/test.py::test_name -v 预期:失败并显示 "function not defined"
步骤 3: 编写最简实现
def function(input):
return expected
步骤 4: 运行测试以验证其通过
运行:pytest tests/path/test.py::test_name -v 预期:通过
步骤 5: 提交
git add tests/path/test.py src/path/file.py
git commit -m "feat: add specific feature"
## 记住
- 始终使用精确的文件路径
- 计划中包含完整代码(而不是 "添加验证")
- 精确的命令和预期输出
- 使用 @ 语法引用相关技能
- DRY、YAGNI、TDD、频繁提交
## 执行交接
保存计划后,提供执行选择:
**"计划已完成并保存至 `docs/plans/<filename>.md`。两种执行选项:**
**1. 子代理驱动(本次会话)** - 我为每个任务分派新的子代理,任务间进行审查,快速迭代
**2. 并行会话(独立)** - 使用 executing-plans 打开新会话,进行带检查点的批量执行
**选择哪种方式?"**
**如果选择子代理驱动:**
- 使用 skills/collaboration/subagent-driven-development
- 保持本次会话
- 每个任务使用新的子代理 + 代码审查
**如果选择并行会话:**
- 指导他们在工作树中打开新会话
- 新会话使用 skills/collaboration/executing-plans
每周安装数
0
仓库
GitHub 星标数
11
首次出现时间
Jan 1, 1970
安全审计
Write comprehensive implementation plans assuming the engineer has zero context for our codebase and questionable taste. Document everything they need to know: which files to touch for each task, code, testing, docs they might need to check, how to test it. Give them the whole plan as bite-sized tasks. DRY. YAGNI. TDD. Frequent commits.
Assume they are a skilled developer, but know almost nothing about our toolset or problem domain. Assume they don't know good test design very well.
Announce at start: "I'm using the Writing Plans skill to create the implementation plan."
Context: This should be run in a dedicated worktree (created by brainstorming skill).
Save plans to: docs/plans/YYYY-MM-DD-<feature-name>.md
Each step is one action (2-5 minutes):
Every plan MUST start with this header:
# [Feature Name] Implementation Plan
> **For Claude:** Use `${SUPERPOWERS_SKILLS_ROOT}/skills/collaboration/executing-plans/SKILL.md` to implement this plan task-by-task.
**Goal:** [One sentence describing what this builds]
**Architecture:** [2-3 sentences about approach]
**Tech Stack:** [Key technologies/libraries]
---
### Task N: [Component Name]
**Files:**
- Create: `exact/path/to/file.py`
- Modify: `exact/path/to/existing.py:123-145`
- Test: `tests/exact/path/to/test.py`
**Step 1: Write the failing test**
```python
def test_specific_behavior():
result = function(input)
assert result == expected
Step 2: Run test to verify it fails
Run: pytest tests/path/test.py::test_name -v Expected: FAIL with "function not defined"
Step 3: Write minimal implementation
def function(input):
return expected
Step 4: Run test to verify it passes
Run: pytest tests/path/test.py::test_name -v Expected: PASS
Step 5: Commit
git add tests/path/test.py src/path/file.py
git commit -m "feat: add specific feature"
## Remember
- Exact file paths always
- Complete code in plan (not "add validation")
- Exact commands with expected output
- Reference relevant skills with @ syntax
- DRY, YAGNI, TDD, frequent commits
## Execution Handoff
After saving the plan, offer execution choice:
**"Plan complete and saved to `docs/plans/<filename>.md`. Two execution options:**
**1. Subagent-Driven (this session)** - I dispatch fresh subagent per task, review between tasks, fast iteration
**2. Parallel Session (separate)** - Open new session with executing-plans, batch execution with checkpoints
**Which approach?"**
**If Subagent-Driven chosen:**
- Use skills/collaboration/subagent-driven-development
- Stay in this session
- Fresh subagent per task + code review
**If Parallel Session chosen:**
- Guide them to open new session in worktree
- New session uses skills/collaboration/executing-plans
Weekly Installs
0
Repository
GitHub Stars
11
First Seen
Jan 1, 1970
Security Audits
agent-browser 浏览器自动化工具 - Vercel Labs 命令行网页操作与测试
136,300 周安装