writing-plans

Convert specs into detailed implementation plans with bite-sized TDD tasks and exact file paths.

66|4|Updated Feb 26, 2026
One-click install
npx skills add https://github.com/SummerEngine/summer --skill writing-plans-summerengine
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: writing-plans
Source: https://github.com/SummerEngine/summer/tree/main/library/skills/writing-plans
Command: npx skills add https://github.com/SummerEngine/summer --skill writing-plans-summerengine

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Multi-step coding tasks often fail because agents jump into code without a structured plan, producing inconsistent types, missed requirements, and vague steps. This Skill turns a spec or requirements document into a complete, reviewable implementation plan before any code is touched. ## Core Features & Use Cases - Bite-Sized Task Decomposition: Breaks work into 2-5 minute steps following TDD: write failing test, verify failure, implement minimally, verify pass, commit. - Zero-Placeholder Enforcement: Every step contains exact file paths, complete code blocks, exact commands with expected output, and explicit rejection of TODOs or vague instructions. - Self-Review and Execution Handoff: Includes a spec-coverage and type-consistency checklist, then offers subagent-driven or inline execution with review checkpoints. - Use Case: Given a spec for a health/damage system in a Godot game, produce a plan saved to .summer/plans/ with GUT test code, GDScript implementations, and commit steps that a fresh engineer or subagent can execute task-by-task. ## Quick Start Ask the agent to use the writing-plans skill to turn your spec into an implementation plan saved under .summer/plans/ before writing any code.

Frequently Asked Questions about writing-plans

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I write an implementation plan before coding?

Start from a spec, map the file structure first, then decompose work into bite-sized tasks of 2-5 minutes each. Each task lists exact files to create or modify, a failing test, minimal implementation, verification commands, and a commit step.

What is a good task granularity for AI coding agents?

Each step should be one action taking 2-5 minutes: write the failing test, run it to confirm failure, implement minimal code, run tests to confirm pass, then commit. This granularity keeps agent edits reliable and reviewable.

Where are implementation plans saved in a Summer game project?

Plans are saved to .summer/plans/YYYY-MM-DD-<feature-name>.md inside the game project by default. User preferences for plan location override this default path.

Should I use subagent-driven or inline execution for a plan?

Subagent-driven execution dispatches a fresh subagent per task with a two-stage review between tasks, which suits independent tasks. Inline execution runs tasks in the current session with a checkpoint after each task, never batching past a failing step.

When should a spec be split into multiple plans?

Split when the spec covers multiple independent subsystems. Each plan should produce working, testable software on its own, so one plan per subsystem keeps scope reviewable and executable.