Memory Onboarding Wizard

v1.0.0

Bootstrap a new OpenClaw agent's memory system in one command. Sets up MEMORY.md, daily memory files, HEARTBEAT.md, and USER.md by asking 3 quick questions....

0· 81·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
Purpose & Capability
The name/description match the included Python script and SKILL.md: the tool bootstraps MEMORY.md, daily notes, HEARTBEAT.md, and USER.md. There are no unrelated environment variables, binaries, or resources requested.
Instruction Scope
Runtime instructions are limited to running the included Python script from the OpenClaw workspace. The script only reads/writes files under the workspace, prompts the user for three simple answers, and prints a validation summary. It does not attempt to read other system files, environment secrets, or transmit data externally.
Install Mechanism
No install spec is provided (instruction-only with a shipped script). The script is local and does not download or extract remote code, so there is no elevated install risk.
Credentials
No required environment variables, credentials, or config paths are declared or used. The script uses only standard filesystem paths under the specified workspace and user-provided answers — this is proportional to the skill's purpose.
Persistence & Privilege
The skill is user-invocable and not always-enabled. It writes only its own workspace files and does not modify other skills or global agent settings. It does not request persistent elevated privileges.
Assessment
This skill is internally consistent: it creates simple memory files in the OpenClaw workspace and avoids network/secret access. Before running, confirm the workspace path (default ~/.openclaw/workspace) is correct, and review the generated USER.md/MEMORY.md to avoid accidentally storing sensitive information. If you want stricter control, run with --workspace pointing to a sandboxed directory or use --non-interactive to avoid prompts.

Like a lobster shell, security has layers — review code before you run it.

latestvk9721zg5zzskq9jnhmjw9g6prs83b2p5

License

MIT-0
Free to use, modify, and redistribute. No attribution required.

Comments