Entrepreneur Cognition
v1.0.0企业家认知 Skill —— SOUL五律适配创业决策，市场碰撞+商业模式验证+ pivot记忆
⭐ 0· 50·0 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
The name/description claim a cognitive framework for startup decisions; the SKILL.md contains guidelines, templates (decision_log/, pivot_history/, market_analysis/, financial_model/) and workflows that match that purpose. No unrelated binaries, env vars, or surprising capabilities are requested.
Instruction Scope
The instructions are high-level methodology and explicitly recommend creating/maintaining local memory files and folders for decisions and pivots. They do not instruct reading arbitrary system files or exfiltrating data, but they are open-ended about 'AI: market data analysis' and do not limit how the agent obtains market data — that could lead the agent to use network connectors or external tools if available. The guidance is otherwise scoped to business decision artifacts.
Install Mechanism
No install spec or code is included; the README shows a 'clawhub install' example but there is no installer provided in the bundle. As an instruction-only skill, there is no archive download or package installation risk from this package itself.
Credentials
The skill declares no required environment variables, no credentials, and no config paths. That aligns with a purely advisory/memory-keeping skill. There are no disproportionate secret requests.
Persistence & Privilege
always:false and no cross-skill config changes — appropriate. The skill explicitly encourages persistent local files (decision_log, pivot_history, etc.). This is reasonable for its purpose but users should be aware that sensitive business data will be persisted to the agent workspace unless the runtime is configured otherwise.
Assessment
This skill is primarily a set of decision-making templates and workflows and appears coherent with its stated purpose. Before enabling it: 1) Confirm where the agent stores its workspace files (decision_log/, pivot_history/, market_analysis/) and whether those locations are backed up or uploaded elsewhere — avoid storing sensitive secrets in those logs. 2) Check what runtime permissions your agent has (network access, file uploads, third-party tool connectors). Because the SKILL.md is open-ended about how the AI gathers 'market data', an agent with web/network access could fetch external data; limit that if you don't want automatic external queries. 3) The README mentions 'clawhub install' but no installer is bundled here — verify the install source (the repository URL) before running any installer. 4) If you plan to let the agent run autonomously, set retention and access controls for the memory files and review logs periodically. Overall the package itself is low-risk and coherent, but operational safeguards around persisted business data and agent network permissions are recommended.Like a lobster shell, security has layers — review code before you run it.
latestvk97b84gcdy2cswmphpne7k77sn83yam7
License
MIT-0
Free to use, modify, and redistribute. No attribution required.