writing-plans

Use when you have a spec or requirements for a multi-step task, before touching code. Creates bite-sized TDD implementation plans with dependency tracking.

509 stars

Best use case

writing-plans is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Use when you have a spec or requirements for a multi-step task, before touching code. Creates bite-sized TDD implementation plans with dependency tracking.

Teams using writing-plans should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/writing-plans/SKILL.md --create-dirs "https://raw.githubusercontent.com/a5c-ai/babysitter/main/library/methodologies/superpowers/skills/writing-plans/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/writing-plans/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How writing-plans Compares

Feature / Agentwriting-plansStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Use when you have a spec or requirements for a multi-step task, before touching code. Creates bite-sized TDD implementation plans with dependency tracking.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# Writing Plans

## Overview

Create comprehensive implementation plans with bite-sized tasks (2-5 minutes each). Every task has exact file paths, complete code, verification steps, and TDD flow.

**Core principle:** Document everything the engineer needs. DRY. YAGNI. TDD. Frequent commits.

## When to Use

- After design approval (from brainstorming)
- When you have specs/requirements for multi-step work
- Before any implementation begins

## Task Structure

Each task follows: Write failing test -> Verify fail -> Implement minimal code -> Verify pass -> Commit

## Plan Format

- Header: Goal, Architecture, Tech Stack
- Tasks with exact file paths and complete code
- TDD steps with expected output
- Task persistence via `.tasks.json`

## Execution Handoff

After plan is written, choose:
1. **Subagent-Driven** - Fresh agent per task with two-stage review
2. **Batch Execution** - Execute in batches with human checkpoints

## Agents Used

- Process agents defined in `writing-plans.js`

## Tool Use

Invoke via babysitter process: `methodologies/superpowers/writing-plans`

Related Skills

tech-writing-lint

509
from a5c-ai/babysitter

Automated technical writing style and quality enforcement. Lint documentation with Vale, check for inclusive language, enforce style guides, and analyze readability metrics.

tech-writing-linter

509
from a5c-ai/babysitter

Lint technical documentation for style, consistency, and readability

academic-writing-publication

509
from a5c-ai/babysitter

Prepare manuscripts following APA, ASA, or discipline-specific guidelines with proper reporting standards and peer review navigation

philosophical-writing-argumentation

509
from a5c-ai/babysitter

Compose clear, rigorous philosophical prose with well-structured arguments, anticipation of objections, and proper scholarly engagement with existing literature

grant-narrative-writing

509
from a5c-ai/babysitter

Compose compelling research narratives for NEH, ACLS, and foundation funding proposals with clear significance statements

learning-objectives-writing

509
from a5c-ai/babysitter

Write measurable, SMART learning objectives using Bloom's Taxonomy cognitive levels aligned with desired outcomes and assessment strategies

interpretive-writing

509
from a5c-ai/babysitter

Create accessible interpretive content for diverse audiences including labels, wall text, catalog essays, educational materials, and digital content

grant-proposal-writing

509
from a5c-ai/babysitter

Develop compelling funding proposals for foundations, government agencies, and corporations including narrative development, budget creation, and compliance documentation

lyric-writing

509
from a5c-ai/babysitter

Write complete song lyrics with structural annotations and production notes optimized for AI music generation platforms like Suno and Udio

treatment-writing

509
from a5c-ai/babysitter

Develop narrative synopses that tell the complete story cinematically, serving as sales documents and production blueprints

scene-writing

509
from a5c-ai/babysitter

Write individual screenplay scenes with proper industry formatting, visual action, and dramatic structure

logline-writing

509
from a5c-ai/babysitter

Craft compelling one-sentence story hooks that capture protagonist, conflict, stakes, and unique appeal for film/TV pitches