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· 109·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The name and description (brainstorming and turning ideas into designs) align with the runtime instructions. The skill's requested actions (inspect project files/commits, ask clarifying questions, produce design options, write a design doc, and invoke a follow-up writing-plans skill) are consistent with its purpose. There are no unrelated environment variables, binaries, or install steps.
Instruction Scope
The SKILL.md explicitly tells the agent to inspect the current project (files, docs, recent commits), produce a design, write the design to docs/plans/YYYY-MM-DD-<topic>-design.md, and commit it. Reading and writing the repository and committing changes are within scope for a brainstorming/design workflow, but these are persistent actions that require repository read/write and git commit privileges. Also, the doc suggests 'Use elements-of-style:writing-clearly-and-concisely skill if available' while elsewhere restricting which next skills may be invoked (it states only writing-plans should be invoked after brainstorming) — a minor inconsistency to be aware of.
Install Mechanism
Instruction-only skill with no install spec and no code files. This is low risk: nothing is downloaded or installed.
Credentials
The skill declares no required environment variables, credentials, or config paths. The operations it asks for (reading repo state and writing a design file) do not require additional secrets beyond normal repository access.
Persistence & Privilege
always:false (default) and autonomous invocation is allowed (platform default). The skill instructs the agent to write a file into the repository and commit it — this is a persistent, privileged action within the repo. Confirm that you are comfortable granting the agent repository write/commit rights and that any subsequent skill it invokes (writing-plans) is trusted.
Assessment
This skill appears to do what it says: examine your project, ask clarifying questions, produce a design, save it in docs/plans/, commit it, and then call a follow-up 'writing-plans' skill. Before installing, confirm the agent's repository permissions (it will read files and make commits) and that you trust the follow-up skill(s) it will invoke (writing-plans and optionally any writing-style helper). Note the small inconsistency where the doc recommends an additional writing-style skill but otherwise says only writing-plans should be invoked — consider whether you want to allow the agent to call other helper skills. If you are not comfortable with automatic commits, restrict the agent's repo write access or require manual approval before committing.Like a lobster shell, security has layers — review code before you run it.
latestvk9747nv7crfnkmc8ywqgyem2ws839yyz
License
MIT-0
Free to use, modify, and redistribute. No attribution required.