Onboarding
v1.0.1Set up your Personal OS in 15 minutes through a conversational interview. Creates SOUL.md, USER.md, IDENTITY.md, AGENTS.md, and MEMORY.md — the foundation fi...
⭐ 0· 48·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name and description claim to run a conversational onboarding and produce five local foundation files; the SKILL.md precisely describes creating those files and asking relevant questions. There are no unrelated credentials, binaries, or installs requested, so the declared purpose aligns with the requested capabilities.
Instruction Scope
The instructions tell the agent to run a few local checks (ls to see existing files, uname -s, date +%Z, and look for 'openclaw' or 'claude' on PATH) and then create SOUL.md, USER.md, IDENTITY.md, AGENTS.md, and MEMORY.md populated with personal data collected in the interview. Reading OS/timezone and PATH is reasonable for tailoring prompts, but the SKILL.md also instructs 'Detect silently (don't announce)' — users should be aware the agent will inspect local environment and filesystem state without explicit user-facing disclosure during the run. The directive 'Run this before any other skill' is advisory but could cause ordering expectations; it's not inherently dangerous but is noteworthy.
Install Mechanism
This is an instruction-only skill with no install spec and no code files; nothing is written to disk by an installer. Risk from installation is minimal because no external packages or downloads are performed.
Credentials
The skill requests no environment variables, no credentials, and no config paths. The runtime instructions access local system information (filesystem, uname, date, PATH) which is proportionate to an onboarding flow that detects OS/timezone and existing setup files.
Persistence & Privilege
The skill does not request always:true and does not modify other skills or global agent settings. It will create local files that the agent is intended to read on subsequent sessions (expected for onboarding). Autonomous invocation is allowed by default but is not combined with elevated privileges here.
Assessment
This skill appears to do what it says: run a guided interview and create five local files (SOUL.md, USER.md, IDENTITY.md, AGENTS.md, MEMORY.md) that the agent will read each session. Before installing or running it, be aware: (1) it will inspect the current working directory and a few local system details (OS, timezone, whether certain agent runtimes are on your PATH) — this is normal for tailoring the flow but happens 'silently' per the instructions; (2) the files it creates will contain personal profile and preferences, so store them where you expect (they're plain text by default) and ensure any filesystem or repo you use for your workspace is trusted; (3) review the generated files after the run and remove or redact any sensitive data you don't want stored in plaintext. If you want stricter behavior, ask the skill to explicitly confirm before reading environment details or creating files, or run it in a directory you control (e.g., a dedicated onboarding folder).Like a lobster shell, security has layers — review code before you run it.
latestvk97212xn834d04e3qer8dam5c983y1asonboardingvk97212xn834d04e3qer8dam5c983y1aspersonal-osvk97212xn834d04e3qer8dam5c983y1as
License
MIT-0
Free to use, modify, and redistribute. No attribution required.