Superlative Memory Manager

Unified memory management combining auto-compaction, tiered storage, semantic recall, and token optimization for efficient, lossless context handling in Open...

This skill is primarily an orchestrator and appears coherent with its stated purpose, but confirm a few things before enabling: - Verify the required underlying skills (cognitive-memory, memory-tiering, context-compactor, memory-on-demand) are trusted and inspect how they store data and manage credentials. - Ask where 'git-backup' and WAL writes go and how git credentials/remote are provided — enabling this skill may cause automatic backups to a repository or filesystem you need to control. - Check vector-store configuration (LanceDB/Qdrant): these stores often require endpoints/keys; ensure those credentials are scoped and stored safely by the required skills. - Test in a non-production agent first to observe event emissions and storage/tiering behavior and ensure retention policies behave as expected. If you need higher assurance, request the implementer to document exact backup destinations, credential requirements, and the CLI commands' provenance (which binary provides the memory CLI).

Type: OpenClaw Skill Name: superlative-memory-manager Version: 1.0.0 The skill bundle appears to be a legitimate orchestration tool for managing memory and context within the OpenClaw ecosystem. The documentation in SKILL.md and the manifest in openclaw.plugin.json describe features like auto-compaction and tiered storage, which are consistent with its stated purpose, and no malicious instructions, data exfiltration patterns, or suspicious code were found.