Tmp Soul Evolver

soul-evolver - AI Agent Memory Evolution System. Automatically analyzes memory files and evolves SOUL.md, USER.md, IDENTITY.md, and other workspace identity...

What to check before installing: - Understand data flow: this skill will read your workspace memory files (memory/*.md, .learnings/) and send extracted excerpts to the configured MiniMax API. Only install if you trust the MiniMax provider and are comfortable sending that data off-host. - Required env var: set MINIMAX_API_KEY (and optionally MINIMAX_BASE_URL). Note the package metadata shown earlier omitted this — rely on SKILL.md/code which do require the key. - Test with --dry-run first to see proposed changes without writing. Review outputs before allowing it to run automatically. - Scheduling: SKILL.md includes a scheduled hook (every 120m). If you enable automated scheduling, the skill will periodically analyze and may append updates; if you prefer manual control, do not enable the cron/hook. - Review workspace and backups: backups are stored under derived .soulforge-* directories inside the workspace; confirm the workspace path is correct so backups stay isolated. - Path/name mismatch: documentation refers to both 'soul-forge' and 'soul-evolver' locations; confirm the actual installed path and update commands accordingly. - If you need higher assurance, audit the full analyzer/evolver code (the network call and prompt composition are visible in analyzer.py) and consider running the skill in an isolated test workspace containing non-sensitive data first.

Type: OpenClaw Skill Name: soul-evolver Version: 1.0.1 The soul-evolver skill is a legitimate memory management system designed to analyze an agent's conversation logs and learning files to update its identity and behavioral guidelines (e.g., SOUL.md, USER.md). The code is well-structured, follows its stated purpose, and includes safety features such as incremental file appends (never overwriting), timestamped backups, and a dry-run mode. While it sends memory data to the MiniMax API (api.minimax.chat) for analysis, this is the core documented functionality and is handled via standard environment variables. No evidence of malicious intent, unauthorized data exfiltration, or harmful prompt injection was found.