← 返回 Skills 市场
paudyyin

增强版写作计划

作者 paudyyin · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ 安全检测通过
64
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install writing-plans-enhanced
功能描述
Use when you have a spec or requirements for a multi-step task, before touching code. Enhanced version with milestone timelines, data flow diagrams, mockups,...
使用说明 (SKILL.md)

Writing Plans — Enhanced

Overview

Write comprehensive implementation plans assuming the engineer has zero context for our codebase. Document everything they need to know: which files to touch, data flow, mockups, risks. Give them the whole plan as bite-sized tasks.

Announce at start: "I'm using the writing-plans skill to create the implementation plan."

Save plans to: docs/plans/YYYY-MM-DD-\x3Cfeature-name>.md

Plan Document Header

Every plan MUST start with this header:

# [Feature Name] Implementation Plan

> **For Claude:** REQUIRED SUB-SKILL: Use superpowers:executing-plans 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]

**Effort:** ~N weeks | **Surfaces touched:** N packages | **New tables:** N | **Feature flag:** name

Milestone Timeline

Ship in slices, each independently reviewable and each behind the flag. Nothing is user-visible until the last slice.

### Milestone 1: Schema & API Contract (Week 1 · Mon–Tue)

New tables, migrations, and API stubs. No UI. Contract reviewed before anything else lands.

- `packages/db` — new migrations
- `packages/api` — tRPC router stubs

### Milestone 2: Core Component (Week 1 · Wed–Fri)

Static component rendered from fixtures. Optimistic insert on submit, rollback on failure.

- `apps/web` — new component
- `apps/storybook` — fixture stories

### Milestone 3: Realtime Integration (Week 2 · Mon–Wed)

Subscribe to changes. Track state for sidebar digest.

### Milestone 4: Notifications & Ramp (Week 2 · Thu–Fri)

Mention detection → notification row, email digest fallback, ramp feature flag.

Data Flow

Describe the data flow from client to persistence. Use ASCII diagrams with solid = request/response, dashed = realtime/async.

### Data Flow: Optimistic Write Path

Client                    API Server              Database
  │                          │                       │
  ├─► POST /tasks (optimistic)                       │
  │  ├─► update local cache immediately              │
  │  └─► send mutation ─────►┤                       │
  │                           ├─► validate ─────────►┤
  │                           │                       │
  │                           │◄─ 200 OK ─────────────┤
  │◄─ cache update ──────────┤                       │
  │                          │                       │

### Realtime Fan-Out (dashed path)

Database ─ ─ ─► WebSocket ─ ─ ─► Other clients
  │              │                  │
  └─► trigger ──►┤                  └─► re-render
                 └─► push notification

Mockups

Not pixel-final — just enough that the reviewer and implementer agree on layout and placement.

### A · Thread Inside an Open Task Card

┌──────────────────────────────────────┐
│  Ship onboarding empty-state rewrite  │
│  BIR-1142 · Assigned to Priya · Due  │
├──────────────────────────────────────┤
│  Priya: Should we add an illustration?│
│  You: Yes, let me mock it up          │
│                                       │
│  ┌─────────────────────────────────┐ │
│  │ Add a comment...          Post │ │
│  └─────────────────────────────────┘ │
└──────────────────────────────────────┘

### B · Sidebar Unread Digest

┌──────────────────────────────────────┐
│ 🔴 Jonah commented on BIR-1142       │
│    "Should the illustration swap..."  │
│ 🔵 Aiko mentioned you on BIR-1098    │
│    "@priya can you confirm..."        │
└──────────────────────────────────────┘

Risk Table

Risk Likelihood Impact Mitigation
Migration locks table during deploy Medium High Run with CONCURRENTLY; schedule off-peak
Realtime subscription leaks memory Low Medium Add max-subscription cap; monitor heap
Feature flag not ramped correctly Medium Medium Auto-alert if flag stuck > 3 days

Bite-Sized Task Granularity

Each step is one action (2-5 minutes):

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

Task Structure

### 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**
[code block]

**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**
[code block]

**Step 4: Run test to verify it passes**
Run: `pytest tests/path/test.py::test_name -v`
Expected: PASS

**Step 5: Commit**
```bash
git add tests/path/test.py src/path/file.py
git commit -m "feat: add specific feature"

Execution Handoff

After saving the plan, offer execution choice:

"Plan complete and saved to docs/plans/\x3Cfilename>.md. Two execution options:

  1. Subagent-Driven (this session) — I dispatch fresh subagent per task, review between tasks
  2. Parallel Session (separate) — Open new session with executing-plans, batch execution with checkpoints

Which approach?"

安全使用建议
This appears safe to use as a planning aid. Before reusing or committing generated plan files, review the header that tells Claude to use executing-plans, and choose subagent execution only when you are comfortable with the scope and review checkpoints.
功能分析
Type: OpenClaw Skill Name: writing-plans-enhanced Version: 1.0.0 The skill bundle provides a structured template and instructions for an AI agent to generate comprehensive software implementation plans. It includes sections for milestones, ASCII data flow diagrams, mockups, and risk tables, and directs the agent to save these plans to a local 'docs/plans/' directory. While it contains instructions for the agent to chain into an execution sub-skill ('superpowers:executing-plans'), this behavior is consistent with the stated purpose of a development orchestration tool and lacks any indicators of malicious intent or data exfiltration.
能力评估
Purpose & Capability
The artifacts coherently define a writing/planning skill, but the template also includes a visible execution handoff after the plan is saved.
Instruction Scope
The required plan header tells future Claude sessions to use another sub-skill; this can steer later agent behavior, but it is disclosed in the template and not automatically executed by this skill.
Install Mechanism
There is no install spec, no required binaries or environment variables, no credentials, and no code files; the static scan was clean.
Credentials
The only directed file write is a scoped plan document under docs/plans, which is proportionate to a planning skill.
Persistence & Privilege
Saved plan files can persist agent-directed instructions in the repository; no elevated privileges, background services, or credential use are shown.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install writing-plans-enhanced
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /writing-plans-enhanced 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
多步任务计划写作,支持里程碑/数据流/风险表/交互式HTML
元数据
Slug writing-plans-enhanced
版本 1.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

增强版写作计划 是什么?

Use when you have a spec or requirements for a multi-step task, before touching code. Enhanced version with milestone timelines, data flow diagrams, mockups,... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 64 次。

如何安装 增强版写作计划?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install writing-plans-enhanced」即可一键安装,无需额外配置。

增强版写作计划 是免费的吗?

是的,增强版写作计划 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

增强版写作计划 支持哪些平台?

增强版写作计划 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 增强版写作计划?

由 paudyyin(@paudyyin)开发并维护,当前版本 v1.0.0。

💬 留言讨论