files-memory-systemMulti-context memory management system for OpenClaw agents with group-isolated storage, global shared memory, workspace organization, and group-specific skil...
Install via ClawdBot CLI:
clawdbot install wxwzl/files-memory-systemGrade Good — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Potentially destructive shell commands in tool definitions
rm -rf /Calls external URL not in known-safe list
https://github.com/user/projectAI Analysis
The skill primarily manages local file systems and memory organization with no evidence of data exfiltration or credential harvesting. The main risks are potential misuse of shell commands (like rm -rf) if improperly invoked, but these appear to be documented for legitimate system management. External URL references are for standard git operations, consistent with the skill's purpose.
Audited Apr 17, 2026 · audit v1.0
Generated May 8, 2026
Deploy AI agents across multiple group chats with isolated memory per group. Each group retains its own context and history without mixing with others, while global memory is shared across all groups.
When a user in a group chat asks to clone a repository, the agent uses the auto-clone script to clone it into the group-specific memory directory, preventing cross-group pollution and ensuring organized access.
At the start of each session, the agent automatically loads the appropriate memory files (group or private) and global memory, ensuring it has full context from previous conversations.
Install and manage skills per group so each group uses only the skills relevant to its purpose, preventing interference and keeping the workspace clean.
Provide memory management as a service where teams pay per group or channel, benefiting from isolated contexts and shared global memory.
Offer on-premise installation and customization for enterprises requiring strict data isolation and compliance across departments.
Create a marketplace where third-party developers sell skills that are pre-configured for group isolation, with revenue sharing.
💬 Integration Tip
Ensure metadata contains 'is_group_chat' and 'conversation_label' fields; run install.sh to enable auto-discovery and registration in AGENTS.md.
Scored Jun 27, 2026
Structured reasoning through sequential thinking — break complex problems into steps, solve each independently, verify consistency, synthesize conclusions wi...
LLM-driven epistemic reasoning engine. Evaluates claims against evidence, outputs calibrated confidence and structured belief state (VERIFIED/CONTESTED/UNCER...
Loads and manages company context for all C-suite advisor skills. Reads ~/.claude/company-context.md, detects stale context (>90 days), enriches context duri...
Turn scattered local sources into a source-constrained evidence notebook for incident, release, and maintainer decisions.
三级记忆管理系统 (Three-Tier Memory Management)。用于管理 AI 代理的短期、中期、长期记忆。包括：(1) 滑动窗口式短期记忆，(2) 自动摘要生成中期记忆，(3) 向量检索长期记忆 (RAG)。当需要管理对话历史、优化上下文、构建个人知识库、或实现记忆持久化时使用此 Skill。
Store secrets, long-term memory, daily logs, and anything custom in your Convex backend instead of local files