Agent-Skills.md

Agent Skills: 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.

UncategorizedID: a5c-ai/babysitter/writing-plans

Repository

a5c-ai/babysitter
a5c-aiLicense: MIT
1,52087

Install this agent skill to your local

pnpm dlx add-skill https://github.com/a5c-ai/babysitter/tree/HEAD/library/methodologies/superpowers/skills/writing-plans

Skill Files

Browse the full folder contents for writing-plans.

Download Skill

Loading file tree…

library/methodologies/superpowers/skills/writing-plans/SKILL.md

Skill Metadata

Name
writing-plans
Description
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.
  • 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