AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Writing Plans

skill-jnlk-cn-superpowers-cn-writing-plans · by jnlk-cn

当拿到多步骤任务的规格说明或需求、准备动手写代码前,必须使用本技能制定完整实现计划

— No reviews yet
0 installs
30 views
0.0% view→install

Install

$ agentstack add skill-jnlk-cn-superpowers-cn-writing-plans

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No 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.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-jnlk-cn-superpowers-cn-writing-plans)

Reliability & compatibility

✓ Security review passed
0 installs to date
— no reviews yet
● 2mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

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 →
Are you the author of Writing Plans? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Writing Plans(编写实现计划)

Overview(概述)

撰写详尽的实现计划,并假设执行工程师对我们的代码库一无所知,且品味堪忧。需要记录他们所需的一切信息:每个任务要改动哪些文件、代码、测试、需要查阅的文档,以及如何进行测试。把整个计划拆成一口一个的小任务。遵循 DRY、YAGNI、TDD,频繁提交。

假设执行者是一位熟练的开发者,但几乎不了解我们的工具链或问题域,也不太擅长设计良好的测试。

开始时声明:"我正在使用 writing-plans 技能来创建实现计划。"

上下文: 如果在隔离 worktree 中工作,该 worktree 应在使用时通过 superpowers:using-git-worktrees 技能创建。

计划保存路径: docs/superpowers/plans/YYYY-MM-DD-.md

  • (用户对计划位置的偏好会覆盖此默认路径)

Scope Check(范围检查)

如果规格说明涉及多个相互独立的子系统,它本应在头脑风暴阶段被拆分为子项目规格。如果尚未拆分,建议将其拆分为独立的计划——每个子系统一份。每份计划都应能独立产出可运行、可测试的软件。

File Structure(文件结构)

在定义任务之前,先梳理将要创建或修改哪些文件,以及每个文件的职责。这里是分解决策被确定下来的地方。

  • 设计边界清晰、接口明确的单元。每个文件应有单一且清晰的职责。
  • 你能同时保持在上下文中的代码才最容易推理,文件越聚焦,编辑也越可靠。优先选择小而聚焦的文件,而非承担过多职责的大文件。
  • 一起变化的文件应该放在一起。按职责拆分,而不是按技术层级拆分。
  • 在已有代码库中,遵循已有模式。如果代码库本身使用大文件,不要单方面重构——但如果你要修改的文件已经臃肿,在计划中加入拆分是合理的。

这一结构会指导任务分解。每个任务都应产出独立自洽、可独立理解的变更。

Task Right-Sizing(任务大小划分)

任务应是最小可独立测试循环单元,并且值得一次新的评审关口。划分任务边界时:把搭建、配置、脚手架和文档步骤合并到真正需要它们的交付任务中;只在评审者可能拒绝任务 A 同时批准相邻任务 B 的地方进行拆分。每个任务都以一个可独立测试的交付物结束。

Bite-Sized Task Granularity(一口大小的任务粒度)

每一步都是单个动作(2-5 分钟):

  • "Write the failing test" — 一步
  • "Run it to make sure it fails" — 一步
  • "Implement the minimal code to make the test pass" — 一步
  • "Run the tests and make sure they pass" — 一步
  • "Commit" — 一步

Plan Document Header(计划文档头部)

每份计划必须以该头部开头:

# [Feature Name] Implementation Plan

> **For agentic workers:** REQUIRED SUB-SKILL: Use superpowers:subagent-driven-development (recommended) or superpowers:executing-plans to implement this plan task-by-task. Steps use checkbox (`- [ ]`) syntax for tracking.

**Goal:** [One sentence describing what this builds]

**Architecture:** [2-3 sentences about approach]

**Tech Stack:** [Key technologies/libraries]

## Global Constraints

[The spec's project-wide requirements — version floors, dependency limits,
naming and copy rules, platform requirements — one line each, with exact
values copied verbatim from the spec. Every task's requirements implicitly
include this section.]

---

Task Structure(任务结构)

````markdown

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

Interfaces:

  • Consumes: [what this task uses from earlier tasks — exact signatures]
  • Produces: [what later tasks rely on — exact function names, parameter

and return types. A task's implementer sees only their own task; this block is how they learn the names and types neighboring tasks use.]

  • [ ] Step 1: Write the failing test
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"

````

No Placeholders(禁止占位符)

每一步都必须包含工程师实际需要的具体内容。以下内容是计划失败项——绝对不要写:

  • "TBD"、"TODO"、"implement later"、"fill in details"
  • "Add appropriate error handling" / "add validation" / "handle edge cases"
  • "Write tests for the above"(没有给出实际测试代码)
  • "Similar to Task N"(重复代码——工程师可能会乱序阅读任务)
  • 只描述做什么、不展示怎么做的步骤(代码步骤必须附带代码块)
  • 引用任何任务中未定义的类型、函数或方法

Remember(谨记)

  • 始终使用精确文件路径
  • 每一步都给出完整代码——如果某一步修改代码,就展示代码
  • 精确命令及其预期输出
  • DRY、YAGNI、TDD、频繁提交

Self-Review(自我审阅)

完成整个计划后,用全新的眼光对照规格说明检查计划。这是你自己运行的检查清单——不是派发给子代理的。

1. Spec coverage(规格覆盖): 浏览规格说明的每个章节/需求。你能否指出实现它的任务?列出任何缺口。

2. Placeholder scan(占位符扫描): 在计划中搜索危险信号——即上面"No Placeholders"部分列出的任何模式。修复它们。

3. Type consistency(类型一致性): 你在后续任务中使用的类型、方法签名和属性名是否与前面任务定义的一致?Task 3 中叫 clearLayers(),Task 7 中却叫 clearFullLayers(),这就是 bug。

如果发现问题,直接就地修复。无需重新审阅——直接修复并继续。如果发现某个规格需求没有对应任务,就补上该任务。

Execution Handoff(执行交接)

保存计划后,提供执行选项:

"Plan complete and saved to docs/superpowers/plans/.md. Two execution options:

1. Subagent-Driven (recommended) - I dispatch a fresh subagent per task, review between tasks, fast iteration

2. Inline Execution - Execute tasks in this session using executing-plans, batch execution with checkpoints

Which approach?"

If Subagent-Driven chosen:

  • REQUIRED SUB-SKILL: Use superpowers:subagent-driven-development
  • Fresh subagent per task + two-stage review

If Inline Execution chosen:

  • REQUIRED SUB-SKILL: Use superpowers:executing-plans
  • Batch execution with checkpoints for review

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.