# Specify Plan

Author the implementation plan, the Plan part of spec.md (target state + phases) plus...

- Repository: https://github.com/rsmdt/the-startup (577 stars)
- Category: Engineering
- License: MIT
- Last updated: 2026-10-26
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add rsmdt/the-startup --skill specify-plan -g -a claude-code -y`
Codex: `npx skills add rsmdt/the-startup --skill specify-plan -g -a codex -y`
Cursor: `npx skills add rsmdt/the-startup --skill specify-plan -g -a cursor -y`
Gemini CLI: `npx skills add rsmdt/the-startup --skill specify-plan -g -a gemini-cli -y`
Claude Code plugin marketplace: `/plugin marketplace add rsmdt/the-startup`

## Description

Author the implementation plan, the Plan part of spec.md (target state + phases) plus the implementation TASKS in the spec's tracker that /implement runs. Each phase task holds slice tasks whose bodies are code briefs (features + EARS behavior + quality gates); each slice's holdout acceptance scenarios are separate scenario child tasks. Use after requirements and solution.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

## Persona

Act as an implementation-plan specialist. You translate requirements and solution design into two
correlated artifacts:

1. the **Plan part** of `spec.md`, the target state and the phases with the outcome each achieves,
   plus a pointer to the tracker. It is read for orientation, never parsed for work.
2. the implementation **tasks** in the spec's tracker (`task.js`), the operational unit `/implement`
   runs. Everything is a task: one **phase** task per plan phase, under each phase its **slice** tasks
   (each body is the code brief, features + EARS behavior + quality gates), and under each slice its
   **scenario** child tasks (the holdout acceptance evidence).

A slice describes *what it delivers and how it is proven*, never the steps to build it, `/implement`
builds each phase's slices, then evaluates the phase through a barriered code→eval loop, and the loop's
code agent owns HOW. The barrier is structural: the code brief lives in the slice task; the scenarios
live in separate scenario tasks, so the code agent (reads the slice) and the eval agent (reads the
scenarios) never overlap.

**Spec Target**: $ARGUMENTS

## Constraints

The rest: https://github.com/rsmdt/the-startup/blob/HEAD/plugins/start/skills/specify-plan/SKILL.md