Scale Frameworks

Scale systems, software architecture, and companies with bottleneck mapping, staged leverage plans, and risk-aware execution loops.

This skill appears coherent and low-risk, but before installing: (1) verify you are comfortable with the skill creating and updating files under ~/scale/ and inspect those files after use; (2) avoid entering secrets or credentials in prompts—the skill says it won't store them but you should not rely on that implicitly; (3) consider file permissions or backups for ~/scale/ if it will contain sensitive organizational notes; (4) note the agent can invoke skills autonomously by default (normal behavior), so confirm activation preferences in setup.md if you want to limit when it runs; and (5) if you later install related skills, review their declared env/config requirements to ensure no unexpected cross-skill access is introduced.

Type: OpenClaw Skill Name: scale Version: 1.0.0 The skill is designed as an advisory and planning tool, explicitly stating it does not perform infrastructure changes or network requests without user confirmation. The `SKILL.md` and `setup.md` files contain clear instructions for the AI agent to store data locally within `~/scale/`, to redact sensitive identifiers, and explicitly states 'None by default from this skill itself' for data leaving the machine. It also disclaims storing secrets or modifying files outside its designated memory path. The prompt injection elements are used to guide the agent's persona and enforce safe data handling practices, not to subvert security or exfiltrate data.