brainstorming
v2.56.0Pre-implementation brainstorming process: deep interview protocol, approach exploration, and design doc generation. Provides process knowledge for `/workflow...
⭐ 0· 140·0 current·0 all-time
byIlia Alshanetsky@iliaal
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
Capability signals
These labels describe what authority the skill may exercise. They are separate from suspicious or malicious moderation verdicts.
OpenClaw
Benign
high confidencePurpose & Capability
Name/description (brainstorming, design doc generation) matches the SKILL.md instructions. The steps (ask clarifying questions, propose approaches, produce a design doc) legitimately require reading project artifacts when 'applicable', so no unexpected capabilities are requested.
Instruction Scope
Instructions explicitly tell the agent to read relevant files, docs, and recent commits when the brainstorm relates to existing code — this is coherent with the skill's purpose. Note: because it asks the agent to 'ground in the codebase', the agent will attempt to access project files and commit history available to it; ensure the agent's file/VC access policies align with that behavior. The SKILL.md also includes a clear Hard Gate forbidding implementation until approval, which limits scope.
Install Mechanism
No install spec and no code files — instruction-only skill. This minimizes on-disk risk; nothing is downloaded or installed.
Credentials
No required environment variables, credentials, or config paths are declared or referenced. The skill's data access needs (reading project files/docs) are proportionate to a brainstorming/design-doc facilitator.
Persistence & Privilege
always is false and the skill is user-invocable (normal). It does not request permanent presence or modify other skills' configs. Autonomous invocation is allowed (platform default) but is not combined with other concerning privileges here.
Assessment
This skill is low-risk and internally consistent: it contains a structured interviewing/brainstorming protocol and asks the agent to read relevant project files when needed. Before installing, confirm that your agent's file and VCS access policies are acceptable (the skill will read code/docs if available), and ensure you trust the agent runtime to respect the SKILL.md 'Hard Gate' (no implementation until explicit approval). If you want stricter limits, run the skill only in sessions where the agent has read-only access to the repository or restrict it to non-code contexts.Like a lobster shell, security has layers — review code before you run it.
latestvk97dmpa2pxfp4nwgma0sdm25jh84vey8
License
MIT-0
Free to use, modify, and redistribute. No attribution required.