A sophisticated investment analysis skill that applies Howard Marks' framework to challenge market consensus and identify mispriced assets.
The fastest way to install a skill directly from the registry.
npx clawhub@latest install second-level-thinking
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
Copy this prompt to OpenClaw to install it automatically.
Help me install second-level-thinking using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Get the raw skill files in a ZIP archive.
Second Level Thinking is a specialized analytical skill designed to help investors move beyond surface-level observations. By channeling the philosophy of legendary investor Howard Marks, this tool assists in identifying what the market is missing, emphasizing that outperformance requires being both different and right. It serves as a rigorous framework for those utilizing Openclaw Skills to stress-test convictions and uncover structural mispricings.
This skill focuses on the market as a discounting machine, forcing users to evaluate whether a current price is justified by data or merely driven by sentiment. It moves past simple qualitative analysis by incorporating deep research into SEC filings, unit economics, and supply-side bottlenecks to provide a contrarian yet grounded perspective on any investment thesis.
To integrate this framework into your workflow, ensure your environment is configured to allow Openclaw Skills to access financial data sources.
# Install the skill into your local agent environment
openclaw install second-level-thinking
# Configure research parameters for SEC and earnings transcript access
openclaw configure second-level-thinking --research-depth high
You may also need to provide API keys for specialized financial data providers if you require real-time 10-K and 10-Q analysis beyond public filings.
The skill organizes its analysis into a structured taxonomy to ensure repeatability and technical rigor. Data is categorized as follows:
| Data Category | Sources | Key Metrics |
|---|---|---|
| Consensus Data | Analyst reports, Price action | Implied Revenue Growth, Terminal Value, Sentiment |
| Supply Economics | SEC Filings, FERC, BLS | Capex-to-revenue, ROIIC trends, Lead times |
| Risk Profile | Historical base rates | Probability-weighted upside/downside, WACC |
| Behavioral Context | News flow, Credit spreads | Pendulum position (Greed vs. Fear) |
Loading
Turn your community into a growth engine with AI-powered social media amplification and authentic conversation discovery.

A composable skills framework that provides coding agents with structured development workflows including TDD, systematic debugging, and subagent-driven execution.

A secure orchestration plugin for running always-on AI assistants in policy-enforced sandboxes using NVIDIA OpenShell.

A comprehensive diagnostic tool for reviewing, testing, and optimizing the structural integrity of complex agentic architectures and multi-agent systems.

A TypeScript-based tool for AI agents to generate and host interactive web pages, dashboards, and data reports via public URLs.

A comprehensive automation skill for interacting with the Rhaios staging API to manage DeFi yield operations through discovery, preparation, and secure execution.








































