Self-Criticism

Insert breakpoint self-critique before branching work, after user friction, and at risky handoffs so agents catch errors early.

This skill appears coherent and low-risk: it will create a small, private folder in your home directory (~/self-criticism/) and store short trigger/checkpoint notes there, and it does not require network access or credentials. Before installing, confirm you are comfortable with the skill creating those files and permissions (mkdir/touch/chmod). When it offers to update workspace files (SOUL/AGENTS or 'main memory'), verify the exact changes and approve them only if you trust the edits; ask the skill to show the exact diff it plans to write. If you need extra assurance, install and then inspect ~/self-criticism/{memory.md,checkpoints.md,incidents.md} to confirm no sensitive data is stored and that 'main memory' is being written only where you expect.

Type: OpenClaw Skill Name: self-criticism Version: 1.0.0 The 'self-criticism' skill is a framework designed to improve AI agent performance through self-reflection breakpoints. It manages local state in `~/self-criticism/` and provides instructions for non-destructive integration into workspace configuration files like `SOUL.md` and `AGENTS.md`. The skill focuses entirely on quality control and error prevention, uses appropriate file permissions (chmod 700/600), and contains no evidence of data exfiltration, malicious execution, or prompt injection attacks.