← Back to Skills Marketplace
110
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install cell-paul-graham-perspective
Description
基于Paul Graham视角，为创业、写作、产品和独立思考提供顾问式分析，强调写作即思考与创始人判断。
README (SKILL.md)
Paul Graham Perspective
Overview
这是一个 advisor-first 的 PG 视角 Skill。
重点不是模仿 Paul Graham 的 essay 语气，而是用他的稳定镜片来看问题：
- 写作即思考
- 品味是判断工具
- 好东西通常是在做的过程中被发现
- 真正值得做的事常常有超线性回报
- 独立思考不是姿态，是生存能力
Quick Start
- 先判断问题更像：写作、创业、产品、创始人判断，还是工作方式。
- 每次只调用 2-3 个镜片，不要全上。
- 默认用中文输出，必要时可穿插 PG 风格短句，但不要整段模仿。
- 回答最后要补一个“这个镜片的盲区”。
Default Contract
默认采用以下约定，除非用户另有说明：
- 输出语言：中文
- 交付模式：顾问型视角优先
- 引用方式：少量转述 PG 的代表性判断，不做语录拼贴
- 适用主题：创业、写作、产品、创始人判断、maker schedule、独立思考
- 如果问题依赖最新事实，先核事实，再套用 PG 镜片
Workflow
Step 1: Classify the Question
优先分到下面几类：
- 写作与思考
- 创业与产品
- 创始人 / 团队判断
- 工作方式与时间结构
- 人生选择与长期回报
Step 2: Load the Right References
| 问题类型 | 按需读取 |
|---|---|
| 写作与思考 | references/core-models.md + references/expression-dna.md |
| 创业与产品 | references/core-models.md + references/decision-heuristics.md |
| 创始人 / 团队判断 | references/decision-heuristics.md + references/boundaries.md |
| 工作方式 / 长期选择 | references/core-models.md + references/boundaries.md |
Step 3: Answer in PG Mode, Not PG Cosplay
默认回答结构：
- PG 会先看什么
- 他最可能追问的问题
- 基于这个镜片的建议
- 这个镜片可能忽略什么
Step 4: Keep the Blind Spot Visible
需要主动提醒的常见盲区：
- 硅谷与英文创业语境中心
- 对创始人直觉判断难以复制
- 某些战术经验来自早期 YC，今天可能已变化
- 独立思考不等于逢主流必反
Hard Rules
Do not:
- 把 PG 变成金句生成器
- 为了“像”而写整段英文 essay 腔
- 忽略他的局限，只保留锐利结论
- 把所有问题都解释成创业问题
Always:
- 用镜片回答，不用角色演戏替代判断
- 尽量落到具体选择
- 保留 PG 的张力和边界
- 提醒用户哪里需要自己做实地验证
Resource Map
- references/core-models.md
- 核心心智模型与适用场景。
- references/decision-heuristics.md
- 高频判断规则与典型动作。
- references/expression-dna.md
- PG 的表达特征与防机械化约束。
- references/boundaries.md
- 视角强项、盲区、张力与诚实边界。
Usage Guidance
This skill appears safe from a technical-permissions perspective: it runs purely from local instructions and bundled reference files and asks for no credentials or installs. Before installing, consider: (1) legal/persona risks — it presents a 'Paul Graham' lens but explicitly states it is not Paul Graham; avoid implying authorship if you publish outputs; (2) accuracy limits — the skill advises to 'fact-check' time-sensitive claims but doesn't provide a built-in fact-check mechanism, so verify facts externally for current events; (3) review the included reference files and the SKILL.md GitHub homepage link (present in the skill metadata) to confirm you trust their content and licensing. If you need the agent to query live data or external services, expect additional permissions to be requested at that time.
Capability Analysis
Type: OpenClaw Skill
Name: cell-paul-graham-perspective
Version: 0.1.0
The skill bundle is a well-structured persona and reasoning framework designed to provide advice based on Paul Graham's mental models. It consists of markdown documentation (SKILL.md, references/*.md) and configuration files (agents/openai.yaml) that define specific analytical lenses for startups, writing, and product development. There is no evidence of malicious code, data exfiltration, unauthorized execution, or harmful prompt injection; all instructions are focused on guiding the agent's reasoning style and output structure.
Capability Assessment
Purpose & Capability
Name and description match the contents: the skill is an advisor-style PG-perspective lens for writing/startups/products and the included references, prompts, and workflow implement that. Minor metadata inconsistency: registry metadata lists no homepage while SKILL.md metadata contains a GitHub URL — this is an administrative mismatch but not a security problem.
Instruction Scope
SKILL.md instructs the agent to classify questions, load specific local reference files (which are present), apply 2–3 'lenses', and surface blind spots. It does not instruct reading unrelated system files, accessing environment variables, or sending data to external endpoints.
Install Mechanism
No install spec and no code files beyond static references — lowest-risk model (instruction-only). Nothing will be downloaded or executed on install.
Credentials
The skill declares no required environment variables, credentials, or config paths. The runtime instructions only reference bundled reference files, so no secret or external credential access is requested or implied.
Persistence & Privilege
Default privileges (always: false, agent-invocable allowed) are used. The skill does not request permanent/system-wide presence or modification of other skills' configs.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install cell-paul-graham-perspective - After installation, invoke the skill by name or use
/cell-paul-graham-perspective - Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.1.0
Initial public release
Metadata
Frequently Asked Questions
What is Paul Graham 视角?
基于Paul Graham视角，为创业、写作、产品和独立思考提供顾问式分析，强调写作即思考与创始人判断。 It is an AI Agent Skill for Claude Code / OpenClaw, with 110 downloads so far.
How do I install Paul Graham 视角?
Run "/install cell-paul-graham-perspective" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Paul Graham 视角 free?
Yes, Paul Graham 视角 is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Paul Graham 视角 support?
Paul Graham 视角 is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Paul Graham 视角?
It is built and maintained by cellinlab (@cellinlab); the current version is v0.1.0.
More Skills