Brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requi...

Security Scan

Instructions and requirements match the stated purpose: this brainstorming skill is designed to read project context, produce a design document, and commit it to the repo — nothing in the bundle asks for unrelated secrets or external code installs.

Purpose & Capability

The name/description (brainstorming before creative work) aligns with the instructions: the skill asks the agent to understand project context, propose approaches, produce a design, and write/commit that design. Reading project files and git history and producing docs are appropriate capabilities for a development-focused brainstorming skill.

Instruction Scope

The SKILL.md explicitly instructs the agent to inspect the current project state (files, docs, recent commits), to write a validated design into docs/plans/YYYY-MM-DD-<topic>-design.md, and to commit that document to git. Those actions are consistent with the purpose but are actionful: they require reading repository contents and making changes (a commit). The instructions also reference other skills (elements-of-style, superpowers:using-git-worktrees, superpowers:writing-plans) which may expand what the agent does if those skills are present.

Install Mechanism

This is an instruction-only skill with no install spec and no code files. Nothing will be downloaded or written by an installer as part of skill installation.

Credentials

The skill declares no required environment variables or credentials, which is reasonable. However, it implicitly requires access to the repository files and a functional git client (ability to read files and create commits). Those are proportional to the stated purpose but are security-relevant capabilities the user should consider before enabling the skill in an environment with sensitive repositories.

Persistence & Privilege

The skill does not request always:true and does not modify other skills. However, its instructions expect the agent to write new files and commit changes to the repository. That means the agent (and any invoked helper skills) will need filesystem and git commit privileges — an operational/privilege consideration rather than a mismatch with purpose.

Assessment

This skill is internally coherent for dev work, but it will read your repository and create commits. Before enabling it: 1) ensure the agent is only given access to repositories you are comfortable exposing (avoid sensitive/private data unless you explicitly want the agent to use it); 2) confirm the agent will prompt before making commits or review diffs created by the skill (if possible); 3) verify the git client and filesystem access are restricted to appropriate working directories; 4) be cautious about also enabling the referenced helper skills (elements-of-style, superpowers:using-git-worktrees, superpowers:writing-plans) — they may introduce additional behavior/privileges; and 5) consider trying the skill in a sandbox or a throwaway branch/repo first so you can see exactly what changes it proposes before they reach production branches.

Brainstorming Ideas Into Designs

Overview

Help turn ideas into fully formed designs and specs through natural collaborative dialogue.

Start by understanding the current project context, then ask questions one at a time to refine the idea. Once you understand what you're building, present the design in small sections (200-300 words), checking after each section whether it looks right so far.

The Process

Understanding the idea:

• Check out the current project state first (files, docs, recent commits)
• Ask questions one at a time to refine the idea
• Prefer multiple choice questions when possible, but open-ended is fine too
• Only one question per message - if a topic needs more exploration, break it into multiple questions
• Focus on understanding: purpose, constraints, success criteria

Exploring approaches:

• Propose 2-3 different approaches with trade-offs
• Present options conversationally with your recommendation and reasoning
• Lead with your recommended option and explain why

Presenting the design:

• Once you believe you understand what you're building, present the design
• Break it into sections of 200-300 words
• Ask after each section whether it looks right so far
• Cover: architecture, components, data flow, error handling, testing
• Be ready to go back and clarify if something doesn't make sense

After the Design

Documentation:

• Write the validated design to docs/plans/YYYY-MM-DD-<topic>-design.md
• Use elements-of-style:writing-clearly-and-concisely skill if available
• Commit the design document to git

Implementation (if continuing):

• Ask: "Ready to set up for implementation?"
• Use superpowers:using-git-worktrees to create isolated workspace
• Use superpowers:writing-plans to create detailed implementation plan

Key Principles

• One question at a time - Don't overwhelm with multiple questions
• Multiple choice preferred - Easier to answer than open-ended when possible
• YAGNI ruthlessly - Remove unnecessary features from all designs
• Explore alternatives - Always propose 2-3 approaches before settling
• Incremental validation - Present design in sections, validate each
• Be flexible - Go back and clarify when something doesn't make sense