Memory Work
v1.0.1An AI-first knowledge management system with evolvable memory - 一套 AI 时代的注意力保护架构
⭐ 0· 175·1 current·1 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The name/description (AI-first memory system) match the runtime instructions and file manifest. The skill explicitly documents that it will read and update MEMORY.md, USER.md, SOUL.md and scan the Focus Zone — these actions are appropriate and expected for a memory/knowledge-management agent.
Instruction Scope
The SKILL.md instructs the agent to read many local files (Focus Zone files, MEMORY_LOG tail, SOUL.md, _this_week.md) and to perform automated workflows (startup sync, deep retrospective that can update _this_week.md and MEMORY_LOG.md). The repository also defines zone-level rules (e.g., HIGH-sensitivity 'About Me/' requires confirmation). Behavior is coherent with a memory system, but the agent is allowed to read broad parts of the workspace and perform automatic edits (some actions report they can happen without an explicit user trigger). Users should be aware the agent may modify local markdown files as part of its normal operation.
Install Mechanism
Instruction-only skill, no install spec and no code files executed by the platform. Lowest install risk — nothing is downloaded or written by an installer.
Credentials
No environment variables, no external credentials, and no required binaries are declared. The file access it requests (local memory and workspace files) is proportional to the described functionality.
Persistence & Privilege
always:false (not forced into every agent run). The skill may be invoked autonomously (normal platform default), and the SKILL.md defines protocol-based reflexes (e.g., startup sync) that run each session; this is consistent with its role. No indications it modifies other skills or system-wide settings.
Assessment
This skill is coherent with its purpose but operates by reading and writing your local knowledge files. Before enabling it: (1) review USER.md, SOUL.md, About Me/ and any files in the repo for sensitive personal data and remove or redaction any you don't want the agent to read; (2) back up your vault/files so you can recover from unwanted edits; (3) confirm how the agent's automatic behaviors work (startup sync, deep retrospective) and whether you can disable or require explicit approval for writes; (4) because the source is 'unknown' in the registry metadata, review the upstream GitHub repo link and change history to ensure it matches expectations; (5) consider running the skill with read-only permissions or in a sandbox until you're comfortable with its edits; and (6) watch for integrations (Obsidian, calendar import) that imply copying files out or generating external artifacts. If you want stricter control, require the agent to ask before any write to HIGH-sensitivity folders.Like a lobster shell, security has layers — review code before you run it.
latestvk97crz7hvz4a4cey4vhghcj161830b88
License
MIT-0
Free to use, modify, and redistribute. No attribution required.