← Back to Skills Marketplace
Openclaw Startup
by
Don Zurbrick
· GitHub ↗
· v1.0.3
· MIT-0
178
Downloads
0
Stars
0
Active Installs
4
Versions
Install in OpenClaw
/install openclaw-startup
Description
First-run setup wizard for new OpenClaw agents. Interviews the user to generate a tailored SOUL.md, scaffolds memory architecture, installs recommended crons...
Usage Guidance
This skill appears coherent and does what it says: it will ask the interview questions, generate SOUL/USER/IDENTITY/AGENTS files, create a workspace (default: $HOME/.openclaw/workspace or OPENCLAW_WORKSPACE), initialize a git repo, and optionally register crons via the openclaw CLI. Before running: (1) Confirm the workspace path it will write to — avoid pointing it at sensitive directories; (2) Review the generated SOUL.md/USER.md/IDENTITY.md when the agent shows them and only approve writes you expect; (3) Be aware the install script will run git init and create a local commit (it sets a local git identity if none exists); (4) Cron installation is only performed if you approve and if the openclaw CLI is available — review cron payloads/timings carefully; (5) The verify script performs local secret-pattern scanning and runs openclaw commands if available — it does not exfiltrate data, but review its output if it flags possible secrets. If you want extra assurance, run the included scripts yourself from a shell (inspect them first) rather than letting the agent run them autonomously.
Capability Analysis
Type: OpenClaw Skill
Name: openclaw-startup
Version: 1.0.3
The openclaw-startup bundle is a legitimate setup wizard designed to initialize an OpenClaw agent's workspace. It includes well-structured scripts for scaffolding directories (scripts/install.sh) and performing post-setup health and security checks (scripts/verify.sh), including a basic regex-based secret scanner. The instructions in SKILL.md and the provided templates (assets/soul-template.md, references/security-baseline.md) prioritize user consent and explicitly include defensive measures against prompt injection and unauthorized data exfiltration. No malicious intent, obfuscation, or unauthorized network activity was detected.
Capability Assessment
Purpose & Capability
Name/description match the provided files and scripts: templates, interview guide, memory scaffolding, cron recommendations, and post-setup verification. Required binaries (bash, mkdir, date) are appropriate for the tasks.
Instruction Scope
SKILL.md confines actions to interviewing the user, generating templates, creating a workspace, and optionally installing crons via the openclaw CLI. It explicitly requires user approval before writing. The included scripts create files and verify them; they do not read or transmit unrelated system secrets or call external endpoints.
Install Mechanism
No install spec — instruction-only with two local scripts. Scripts are included in the skill bundle (no remote downloads or third-party package installs). This minimizes install-time risk.
Credentials
The skill declares no required environment variables or credentials. The scripts optionally respect OPENCLAW_WORKSPACE if set; otherwise they write to a default $HOME/.openclaw/workspace. No unrelated credentials or secrets are requested.
Persistence & Privilege
always is false and the skill is user-invocable. The scripts create files and initialize a local git repo in the workspace (normal for scaffolding). The skill does not modify other skills' configs or request permanent platform-wide presence.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install openclaw-startup - After installation, invoke the skill by name or use
/openclaw-startup - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.3
- Updated companion skill recommendations: added `summarize`, removed `agent-memory-loop`, `battle-tested-agent`, `openclaw-guide`, and `agent-qa-gates`.
- Improved the companion skills table to reflect current best practices and available skills.
- No changes to core functionality or setup process.
v1.0.2
openclaw-startup 1.0.2
- Removed recommendation and install instructions for the "cron-doctor" skill from Phase 5 (Companion Skills).
- No other content or logic changes made.
v1.0.1
Added ClawHub links for all 8 companion skills in SKILL.md and README
v1.0.0
Initial release of openclaw-startup: a comprehensive setup wizard for new OpenClaw agents.
- Guides new users through a multi-phase, interview-driven agent setup process.
- Generates foundational files (SOUL.md, USER.md, IDENTITY.md, AGENTS.md) based on user input.
- Automates creation of memory scaffolding, log structures, and operational trackers.
- Reviews and optionally installs recommended operational crons for maintenance and security.
- Walks through a security baseline checklist to ensure safe initial configuration.
- Suggests and helps install companion skills tailored to user needs.
- Includes verification steps to confirm successful setup and agent health.
Metadata
Frequently Asked Questions
What is Openclaw Startup?
First-run setup wizard for new OpenClaw agents. Interviews the user to generate a tailored SOUL.md, scaffolds memory architecture, installs recommended crons... It is an AI Agent Skill for Claude Code / OpenClaw, with 178 downloads so far.
How do I install Openclaw Startup?
Run "/install openclaw-startup" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Openclaw Startup free?
Yes, Openclaw Startup is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Openclaw Startup support?
Openclaw Startup is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Openclaw Startup?
It is built and maintained by Don Zurbrick (@zurbrick); the current version is v1.0.3.
More Skills