Brainstorming
Analysis
This is a coherent instruction-only brainstorming skill that asks clarifying questions, writes a scoped design document, and hands it to a planning skill.
Findings (2)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.
Save to: `docs/design/YYYY-MM-DD-feature-name.md`
The skill instructs the agent to write a file, but the path is scoped to a design-docs directory and fits the stated purpose.
Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.
Pass design doc to writing-plans skill.
The workflow hands the generated design document to another skill. This is disclosed and purpose-aligned, but users should know project design context may be reused in the next planning step.