Get the FREE Ultimate OpenClaw Setup Guide →

writing-plans

Scanned
npx machina-cli add skill guanyang/antigravity-skills/writing-plans --openclaw
Files (1)
SKILL.md
3.2 KB

Writing Plans

Overview

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

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

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]

---

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**

```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**

```python
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**

```bash
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:

  • REQUIRED SUB-SKILL: Use superpowers: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
  • REQUIRED SUB-SKILL: New session uses superpowers:executing-plans

Source

git clone https://github.com/guanyang/antigravity-skills/blob/main/skills/writing-plans/SKILL.mdView on GitHub

Overview

Writing Plans creates a complete, implementation-ready plan from a spec before touching code. It assumes the engineer has zero context and requires documenting every detail: which files to touch, the code and tests to write, and how to verify the result. Plans are saved as docs/plans/YYYY-MM-DD-<feature-name>.md with bite-sized tasks.

How This Skill Works

A dedicated worktree is used to draft a plan that starts with the standard header and follows a task-by-task format. Each task describes exact files, actions, and commands (2-5 minute steps), aligned with DRY, YAGNI, and TDD principles, and wrapped up with a commit step. After saving, you can choose between subagent-driven or parallel execution modes.

When to Use It

  • When you have a spec or requirements for a multi-step task and want to lock in the plan before coding.
  • When you’re new to the codebase and need a zero-context guide covering files, tests, and docs.
  • When you require an auditable, step-by-step plan saved as docs/plans/YYYY-MM-DD-<feature-name>.md.
  • When you want to drive feature development with TDD, DRY, YAGNI, and frequent commits.
  • When coordinating cross-cutting tasks (tests, docs, and code) in a single plan before implementation.

Quick Start

  1. Step 1: Announce I’m using the writing-plans skill to create the implementation plan.
  2. Step 2: Spin up a dedicated worktree and draft the plan header and task structure.
  3. Step 3: Save the plan to docs/plans/YYYY-MM-DD-<feature-name>.md and present execution options.

Best Practices

  • Write each task as a single action (2-5 minutes).
  • List exact files to touch and exact commands, with concrete paths.
  • Announce start and reference relevant skills with @ syntax where needed.
  • Follow DRY, YAGNI, and TDD principles throughout the plan.
  • Commit frequently with meaningful messages and keep the plan self-contained.

Example Use Cases

  • Plan for adding user authentication: docs/plans/2026-03-08-add-auth.md
  • Plan for checkout flow with tests, docs, and migrations: docs/plans/2026-03-08-checkout-flow.md
  • Plan for API rate limiter: docs/plans/2026-03-08-api-rate-limiter.md
  • Plan for data model migration: docs/plans/2026-03-08-data-migration-v2.md
  • Plan for feature flagging: docs/plans/2026-03-08-feature-flags.md

Frequently Asked Questions

Add this skill to your agents
Sponsor this space

Reach thousands of developers