plan-large

Plan a large feature as a DAG of increments with dependencies and file specs.

30|2|Updated Apr 28, 2026

Search Tags:#architecture #review #plan #dag #pull-request #increments

Ready to run

npx skills add https://github.com/hawkyre/hawk-skills --skill plan-large

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: plan-large
Source: https://github.com/hawkyre/hawk-skills/tree/main/skills/plan-large
Command: npx skills add https://github.com/hawkyre/hawk-skills --skill plan-large

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Plan-large helps teams design multi-PR work by producing a structured, incremental plan that can be executed across PRs, ensuring architectural decisions are captured upfront and traceable.

Core Features & Use Cases

DAG-based increment planning: model a large feature as a sequence of smaller increments with explicit dependencies.
Output artifacts: creates a .plans/<slug>/plan.md (and optional sibling files) that document decisions and implementation steps.
Multi-pass review: performs a code-search gate and a blind self-review pass to critique and improve the plan before presenting.

Quick Start

Provide a description of the large feature and I will generate a multi-increment plan in .plans/<slug>/plan.md.

Frequently Asked Questions about plan-large

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

FAQPage Schema

How do I plan a large feature as incremental pull requests with explicit dependencies?▼

To plan a large feature as incremental pull requests, you provide a feature description to generate a DAG of smaller increments. This produces a structured plan document specifying explicit dependencies, increment ordering, done criteria, and file specs for implementation.

What is a DAG-based increment plan and when do I need it for architecture review?▼

A DAG-based increment plan models a large feature as a sequence of smaller, ordered increments with explicit dependencies. You need it for architecture review when a feature spans multiple pull requests and requires upfront decisions to be traceable across the implementation pipeline.

How do I generate a structured plan document for multi-PR feature implementation?▼

You generate a structured plan document for multi-PR implementation by providing a feature description, which creates a .plans/<slug>/plan.md file. This file captures architectural decisions, increment ordering, done criteria, and file specifications for each stage of the work.

Does the plan generation process include automated code search and self-review?▼

Yes, the plan generation process includes a code-search-first gate followed by a blind self-review pass. These multi-pass reviews critique and improve the generated plan before presenting it, ensuring the increment ordering and file specifications are validated against the existing codebase.

What is the best way to break down large architecture changes into smaller increments?▼

The best way to break down large architecture changes is modeling the work as a directed acyclic graph where each node is a small increment. This captures architectural decisions upfront and ensures explicit dependencies, done criteria, and file specs are documented for traceable execution.

Can I use this incremental planning approach for features that require strict PR ordering?▼

Yes, you can use this incremental planning approach for features requiring strict PR ordering because it models increments as a DAG. This ensures explicit dependencies between increments are documented, allowing teams to execute pull requests in the correct sequence.