shape-it-lite

Plans work by investigating the project and writing a markdown plan file.

Updated Aug 5, 2026
One-click install
npx skills add https://github.com/skkap/claude-skills --skill shape-it-lite-skkap
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: shape-it-lite
Source: https://github.com/skkap/claude-skills/tree/main/plugins/shape-it/skills/shape-it-lite
Command: npx skills add https://github.com/skkap/claude-skills --skill shape-it-lite-skkap

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Planning a feature in a repository with no domain model or decision log often means either over-asking the operator or guessing at decisions that are expensive to reverse. This Skill investigates the project first, decides everything the codebase already answers, and asks only the few questions that are costly to get wrong — ending with a written plan file, not a conversation. ## Core Features & Use Cases - Investigation before questions: Reads the task, CLAUDE.md/AGENTS.md, the nearest existing feature, README/docs, and code comments to settle what the project already answers. - Reversibility-based triage: Sorts every open decision on two axes (can the project answer it, is it expensive to undo) and asks only about vocabulary, schema, public API surface, scope boundaries, and business rules. - Plain-language checkpoint: States what the work is in five jargon-free lines — what it is, why now, effect, cost of skipping, and questions ahead — before asking anything. - Batched questions and a plan file: Asks up to four opinionated questions per round via AskUserQuestion, then writes a structured markdown plan (decisions, approach, out of scope, risks) and opens it in plannotator for annotation. - Use case: You are asked to add shipment splitting to a client's repo that has no DOMAIN.md. The Skill reads the checkout flow, asks four questions about naming, cancellation, API shape, and scope, then writes a plan to ~/.local/share/shape-it/ without touching the repository. ## Quick Start Ask the agent to plan a feature in this repository using shape-it-lite before writing any code.

Frequently Asked Questions about shape-it-lite

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

FAQPage Schema
How do I plan a feature before writing code in a repo?

Invoke the skill with the feature request and it investigates the project first — reading conventions, the nearest similar feature, and docs — then asks only the decisions that are expensive to reverse. It finishes by writing a structured markdown plan file rather than implementing anything.

What is the difference between shape-it and shape-it-lite?

shape-it-lite is for projects with no DOMAIN.md and no docs/decisions/ directory; it reads no domain model and writes none, so every settled decision lives only in the plan file. Use the full shape-it skill when those files exist, since reading them avoids re-asking answered questions.

Where does the plan file get written?

It writes to an existing plans directory in the repo if one exists, to a path the operator names, or otherwise to ~/.local/share/shape-it/<repo>/<slug>.md. It never creates a new directory inside a repository you do not own.

Does shape-it-lite implement the plan or enter plan mode?

No. It produces a plan as a file and stops — it does not enter plan mode, does not implement, and does not start even the obvious parts. After writing, it opens the plan in plannotator for annotation and applies the operator's markups.

When should I not use shape-it-lite?

Skip it for one-line fixes, tasks whose shape is already settled, or work where the approach was given. Also avoid it on your own project that keeps a DOMAIN.md — running it repeatedly there means the project has outgrown the lite version.