Brainstorming
v1.0.0You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requi...
⭐ 0· 1.4k·3 current·3 all-time
by@tazio7
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & 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.Like a lobster shell, security has layers — review code before you run it.
latestvk97acf2knx652sm2q2cvdtzjhs82mffj
License
MIT-0
Free to use, modify, and redistribute. No attribution required.