clawlist

MUST use for any multi-step project, long-running task, or infinite monitoring workflow. Plan, execute, track, and verify tasks with checkpoint validation. For projects, automation, and ongoing operations.

Install only if you want a strong planning workflow that may steer many agent tasks into a structured process. Before using long-running or infinite tasks, set explicit scope, cadence, allowed actions, stop conditions, and approval requirements, and periodically review memory/tasks/ongoing-tasks.md and saved plan reports.

Type: OpenClaw Skill Name: clawlist Version: 0.0.1 This skill bundle defines a comprehensive workflow for an AI agent, emphasizing structured planning, execution, and verification across multiple sub-skills. While the instructions contain strong directives ('MUST use', 'ALWAYS use') to enforce agent discipline and skill adherence, these are aimed at ensuring the agent follows its intended operational procedures, not at subverting its purpose. All file operations (reading/writing `memory/tasks/ongoing-tasks.md`, `memory/plans/<filename>.md`) are confined to the agent's workspace and are directly related to task management and documentation. There is no evidence of data exfiltration, malicious execution, persistence mechanisms, or prompt injection with a harmful objective.