ClawHub

Greg Eisenberg

v1.0.0

Generate content ideas, business strategies, and startup concepts in the style of Greg Eisenberg (Startup Ideas Podcast). Use when brainstorming product idea...

⭐ 0· 86·0 current·0 all-time
by@finnmackay
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 skill's name and description (emulate Greg Eisenberg and generate startup ideas/strategies) match the SKILL.md content. The included reference notes about Claude Code and OpenClaw are consistent with that purpose (practical execution advice for building/monetizing AI agents). No unrelated binaries or credentials are requested.
ℹ
Instruction Scope
The runtime instructions are guidance and templates (tone, idea-structure, and operational best-practices). They reference workspace files (agents.md, soul.md, CLAUDE.md, heartbeat.md, memory.md) and describe actions like autosaving memory, cron scrapers, browser relay, and connecting Gmail/WhatsApp. The skill does not itself instruct the agent to read arbitrary system files or exfiltrate data, but it contains practical steps that in real deployments require elevated access/credentials—so following these recommendations could expand the agent's scope if the user later grants those capabilities.
✓
Install Mechanism
No install spec and no code files. This is instruction-only, so nothing will be downloaded or written to disk by the skill itself.
✓
Credentials
The skill declares no required environment variables, no credentials, and no config paths. It mentions using OAuth/OOTH and agent-owned accounts as recommendations, but it does not request or include secrets in the bundle.
✓
Persistence & Privilege
always is false and the skill is user-invocable. The skill does not request persistent installation or elevated privileges. Note: the content recommends persistent constructs (heartbeat autosave, cron jobs); these are operational recommendations but are not enacted by the skill itself.
Assessment
This skill is an advice/persona pack and is internally consistent with its stated purpose. It does not install code or ask for secrets. Before you act on its operational recommendations, be cautious: many of the setup items (cron scrapers, autosave heartbeats, browser relay that can access logged-in sessions, connecting Gmail/WhatsApp) require account credentials and can give an agent powerful access. If you implement them, follow the principle of least privilege: use separate agent-owned accounts, limit scope (one Notion page/one Gmail account rather than your whole workspace), review any cron/automation code before running, and avoid enabling browser takeover (Chrome Relay) on your primary browser. If you plan to let agents act autonomously, audit what access they actually have and monitor logs; revoke or rotate credentials used for agent integrations. Overall the skill itself is coherent and safe as long as you don't blindly apply its operational suggestions without proper access controls.

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

latestvk97ab1c1zp7mjzhx0grnnn7s298385ch

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Comments