Refine conversation history by deleting useless/redundant/process exchanges. Keep explicit instructions, disciplines, important configs, skills learned (how)...

This skill will read chat transcripts and write persistent memory/summary files — but its included principles explicitly tell the agent to keep and persist 'Configs (API keys, models)' and other potentially sensitive data. Before installing or using it, consider: (1) Do not run it on transcripts that contain secrets (API keys, tokens, passwords) unless you trust and have reviewed the output destination. (2) Edit the SKILL.md or principles to explicitly redact or exclude secrets (e.g., remove the 'Configs (API keys, models)' line and add a redaction step). (3) Require user confirmation before writing memory files or make it user-invocable only (avoid autonomous invocation on sensitive corpora). (4) After use, inspect the created memory files and delete any secrets you find. (5) If you need automated redaction, add explicit redaction rules to the workflow (detect common key patterns and remove them). These mitigations reduce the risk of accidental secret persistence; without them, the skill's behavior is suspicious and potentially dangerous.

Type: OpenClaw Skill Name: chat-refiner Version: 0.1.0 The OpenClaw skill 'chat-refiner' is designed to summarize and clean chat history and memory files. All instructions in SKILL.md and references/principles.md align with this stated purpose, detailing how to read chat transcripts and write summarized content to memory files. There is no evidence of prompt injection attempts, unauthorized data access, exfiltration, or any other malicious or suspicious behavior. The file read/write operations are explicitly for the skill's core function, and instructions like 'Keep: Configs (API keys, models)' refer to preserving relevant information *within* the chat history, not accessing system-level configurations.