From skills
Shapes a raw, in-your-head idea into a scoped, non-technical concept brief (IDEA.md) through a collaborative one-question-at-a-time interview — the pre-planning step that comes before there is any plan to refine. Use when the user has an unformed idea to flesh out or scope, says "brainstorm", "help me scope/shape this idea", or "I have an idea", or wants a feature/product concept captured before planning. For stress-testing a plan or document that already exists, use grill-me instead.
How this skill is triggered — by the user, by Claude, or both
Slash command
/skills:brainstormThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Turn a rough idea into an `IDEA.md` concept brief that downstream skills can refine. This is the front of the feature-docs pipeline:
Turn a rough idea into an IDEA.md concept brief that downstream skills can refine. This is the front of the feature-docs pipeline:
brainstorm → grill-me → create-prd → create-tech-spec
Stay at the user / feature / product level. Do not design architecture or choose technologies — that comes later.
Interview the user one question at a time. For each question, provide your recommended answer.
Infer a kebab-case feature name from the idea, propose docs/features/[feature-name]/, then build IDEA.md incrementally as decisions settle:
## Concept
[One paragraph: what the idea is.]
## Problem / Motivation
[The itch it scratches; why it matters now.]
## Target Users
[Who it is for.]
## Value / Success
[What good looks like, in plain terms.]
## Core Capabilities
[The handful of things a first version must do — feature level, not technical.]
## Scope
[In for a first version vs. explicitly out.]
## Open Questions
[What is still fuzzy, to resolve later in grill-me / create-prd.]
These sections map onto PRD.md, so create-prd can refine IDEA.md directly.
If IDEA.md already exists:
See ../create-tech-spec/REFERENCE.md for directory structure and document conventions.
npx claudepluginhub shiggydoodah/skills --plugin skillsProvides behavioral guidelines to reduce common LLM coding mistakes, focusing on simplicity, surgical changes, assumption surfacing, and verifiable success criteria.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.