← Back to Skills Marketplace
OpenClaw Memory Fix Skill
by
githubxiaohei
· GitHub ↗
· v1.0.0
394
Downloads
0
Stars
3
Active Installs
1
Versions
Install in OpenClaw
/install openclaw-memory-fix-skill
Description
Provides a multi-layer memory system for OpenClaw, enabling AI to remember user preferences, learn from mistakes, and evolve continuously.
Usage Guidance
Do not blindly copy the provided config-files into your live ~/.openclaw/workspace. Before installing: 1) Inspect and sanitize files (especially TOOLS.md and any file with tokens or API keys); remove or rotate any hard-coded tokens. 2) Backup your workspace. 3) Test the package in an isolated sandbox or throwaway OpenClaw instance to see what files it writes and what behavior changes (heartbeats, subagent spawning, automatic external requests) it triggers. 4) Look for lines that tell the agent to 'Don't ask permission' or to read broad sets of files — those are red flags for undesired autonomous actions. 5) If you want only memory features, copy a minimal subset (e.g., the auto-memlog.sh and MEMORY.md templates) and avoid copying AGENTS.md / AUTONOMY.md / HEARTBEAT.md / TOOLS.md unless you understand and accept all their effects. If you are uncertain, treat this package as untrusted and run it in isolation.
Capability Analysis
Type: OpenClaw Skill
Name: openclaw-memory-fix-skill
Version: 1.0.0
The skill bundle contains a hardcoded Feishu app_token in 'config-files/TOOLS.md', which represents a significant credential leak and security risk. Additionally, the instructions in 'config-files/AGENTS.md' and 'SKILL.md' grant the AI agent high levels of autonomy with phrases like 'Don't ask permission. Just do it,' and include a 'BOOTSTRAP.md' self-deletion mechanism that could be used for stealthy initial configuration. While the bundle appears to be a sophisticated memory management framework with built-in security checks (e.g., in 'config-files/HEARTBEAT.md'), the combination of exposed secrets and broad autonomous instructions warrants a suspicious classification.
Capability Assessment
Purpose & Capability
The name/description claim a memory enhancement only, but the package includes many workspace configuration files that change agent policies, autonomy, heartbeats, multi-agent delegation, and tooling behavior. Copying the config into ~/.openclaw/workspace/ will alter the agent runtime and global behavior beyond a narrow 'memory fix', so the requested actions are broader than the stated purpose.
Instruction Scope
SKILL.md explicitly instructs the user to copy config-files/* into ~/.openclaw/workspace/, which will cause the agent to read/write many files, enable heartbeats, spawn subagents, run periodic maintenance, and adopt new autonomy rules. Several files instruct the agent to read many workspace files every session and to 'Don't ask permission. Just do it.' — this is scope creep: the instructions direct persistent modification of agent behavior and extensive file access not limited to memory data.
Install Mechanism
There is no formal install spec (lowest installer risk), but the runtime installation step is a manual copy of many files into the user's primary OpenClaw workspace. That still writes persistent files to disk and can override or augment existing configuration; this is effectively an install and should be treated as such.
Credentials
The registry metadata declares no required env vars or credentials, but the included files contain environment-like secrets (TOOLS.md contains a feishu app_token and table IDs). The skill also references external searches/APIs and automatic background checks without declaring or justifying credentials. Hard-coded tokens in shipped files are disproportionate and increase secret-exposure risk.
Persistence & Privilege
always:false and normal autonomous invocation are fine, but the skill's install instructions persistently add files that change the agent's rules (AGENTS.md, AUTONOMY.md, SECURITY.md, HEARTBEAT.md) and encourage automated heartbeats and subagent spawning. Although the skill does not set always:true, it gains persistent influence over the agent by modifying the workspace; that persistent presence is privileged and should be reviewed carefully.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install openclaw-memory-fix-skill - After installation, invoke the skill by name or use
/openclaw-memory-fix-skill - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
OpenClaw Memory Fix Skill v1.0.0
- Introduces a comprehensive memory system for OpenClaw, addressing AI "amnesia" and enabling continuous learning and growth.
- Implements a four-layer memory architecture: short-term, situational, semantic, and long-term.
- Adds 11 key features, including emotion detection, confidence assessment, self-reflection, and collaborative sharing.
- Optimizes performance with 7 enhancements such as hierarchical caching, dynamic reasoning, and context compression.
- Provides a clear configuration system (SOUL.md, USER.md, MEMORY.md, etc.) and easy setup steps.
- Enables automatic task logging and rule-based memory triggers to improve AI reliability and personalization.
Metadata
Frequently Asked Questions
What is OpenClaw Memory Fix Skill?
Provides a multi-layer memory system for OpenClaw, enabling AI to remember user preferences, learn from mistakes, and evolve continuously. It is an AI Agent Skill for Claude Code / OpenClaw, with 394 downloads so far.
How do I install OpenClaw Memory Fix Skill?
Run "/install openclaw-memory-fix-skill" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is OpenClaw Memory Fix Skill free?
Yes, OpenClaw Memory Fix Skill is completely free (open-source). You can download, install and use it at no cost.
Which platforms does OpenClaw Memory Fix Skill support?
OpenClaw Memory Fix Skill is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created OpenClaw Memory Fix Skill?
It is built and maintained by githubxiaohei (@githubxiaohei); the current version is v1.0.0.
More Skills