An advisor-first skill that applies Paul Graham's core mental models—like writing as thinking and founder-over-idea judgment—to complex decision-making.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install cell-paul-graham-perspective
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install cell-paul-graham-perspective using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Paul Graham Perspective?
The Paul Graham Perspective skill is designed to move beyond mere imitation of an essayist's voice. It provides a structured reasoning framework based on PG's recurring lenses: the value of independent thought, the maker schedule, and the search for superlinear returns. By integrating these principles into Openclaw Skills, users can analyze startups, products, and writing through a battle-tested Silicon Valley perspective.
This skill prioritizes judgment over rhetoric. It helps AI agents act as high-level advisors that identify taste as a tool, discover good ideas through the process of doing, and maintain the tension between contrarianism and grounded reality.
Paul Graham Perspective Use Cases
- Evaluating startup viability using the founder-over-idea judgment lens.
- Refining complex writing projects by treating the drafting process as a form of thinking.
- Making high-stakes life or career choices based on the potential for superlinear returns.
- Managing technical work using the maker schedule vs. manager schedule distinction.
- Assessing product taste and iterative discovery paths for new features.
How Paul Graham Perspective Works
- The system classifies the user's query into categories such as Startup, Writing, Founder Judgment, or Work Style.
- It loads specific references from the Openclaw Skills library, such as core-models.md or decision-heuristics.md, based on the classification.
- The agent analyzes the problem to determine what PG would notice first and which questions he would likely ask.
- A response is generated that applies 2-3 specific mental lenses, providing actionable advice rather than generic quotes.
- The workflow concludes by identifying the blind spots of the applied lens, ensuring the user recognizes the limitations of the Silicon Valley context.
Paul Graham Perspective Setup
To add this perspective to your agent, use the following commands within your Openclaw Skills environment:
# Install the skill from the repository
openclaw install paul-graham-perspective
# Configure your agent to trigger the skill for startup or writing queries
openclaw configure --skill paul-graham-perspective
Paul Graham Perspective Data Schema & Taxonomy
| File Reference | Description |
|---|---|
core-models.md |
Documentation of core mental models and their applicable scenarios. |
decision-heuristics.md |
High-frequency judgment rules and typical action patterns. |
expression-dna.md |
PG's logical expression traits and constraints to prevent robotic imitation. |
boundaries.md |
Analysis of perspective strengths, blind spots, and honest boundaries. |
Paul Graham Perspective Advanced Features
- Selective Lens Application: Limits the agent to 2-3 core principles per response to maintain focus and clarity.
- Blind Spot Awareness: Automatically flags biases related to Silicon Valley contexts or outdated YC tactical experiences.
- Multi-Agent Compatibility: Can be used as a specialized reasoning module within a larger agentic workflow.
- Anti-Cosplay Guardrails: Hard rules that prevent the agent from mimicking PG's prose style at the expense of technical truth.
SKILL.md
Loading
Related Openclaw Skills
Naval Perspective
A strategic advisor skill that applies Naval Ravikant's core mental models to career, wealth, and decision-making challenges.
eNSP Topology Generator
Automates the creation of native Huawei eNSP .topo files for instant network simulation and infrastructure design.
eNSP Topology Generator
An automated utility for generating native Huawei Enterprise Network Simulation Platform (.topo) files through simple text descriptions.
Binance Trader Skill
A comprehensive trading integration for Binance that enables automated spot and futures transactions using Python.
A-Share Paper Trading Skill
A high-fidelity simulation and backtesting engine for the A-share market that strictly enforces T+1 settlement and price limit rules.
X Content Mentor
A strategic advisor that transforms raw ideas into high-performing X-native content while diagnosing growth bottlenecks for creators and indie builders.
Featured*
