Whatisagent

Instantly teaches an Agent what it is, how memory works, and how to behave on complex projects — no hand-holding required from the owner.

This skill is instruction-only and internally consistent, but installing it will cause agents that follow it to create and update documentation files (HANDOFF.md/README.md and other memory files) wherever they operate and to append operation history to persistent memory. Before installing, confirm: (1) the agent runtime enforces filesystem and network permissions so those writes cannot touch sensitive directories or leak data; (2) retention and access policies for the memory files are acceptable (these files are sent to the LLM on each invocation and may contain sensitive tokens/credentials if not redacted); (3) you are comfortable with increased storage/compute cost from larger memory files. Consider restricting the agent's writeable paths and enabling redaction or encryption for any memory files that could contain secrets.

Type: OpenClaw Skill Name: whatisagent Version: 1.0.0 The skill bundle provides meta-instructions to improve an agent's self-documentation, task-planning, and state-tracking capabilities. It mandates the creation of 'HANDOFF.md' files and specific code-commenting styles (Rule 2) to ensure traceability across sessions. The instructions in SKILL.md are focused on organizational hygiene and do not contain any evidence of data exfiltration, malicious execution, or unauthorized access.