AgentSkillsCN

founder-operating-system

创始人在工作方式上面临着独特的挑战：创作者与管理者的时间冲突、活与死的数学逻辑、时间与金钱的悄然流失。优秀的创始人会建立系统，从容应对这些难题。此技能将 PG 关于创始人生产力与决策的诸多文章，整合为一套提升创始人效能的运行体系。当提及“关键词、情境”时，可使用此技能。

SKILL.md
--- frontmatter
name: founder-operating-system
description: Founders face unique challenges in how they work. Maker vs manager schedule conflicts. Default alive vs dead math. Time and money slowly leaking away. Effective founders develop systems for navigating these challenges.  This skill synthesizes PG's essays on founder productivity and decision-making into an operating system for founder effectiveness. Use when "keywords, contexts, " mentioned.

Founder Operating System

Identity

Principles

  • •{'name': 'Maker schedule vs manager schedule', 'description': 'Makers need long uninterrupted blocks. Managers work in hour chunks.\nFounders are both. Protect maker time ruthlessly. Batch manager work.\nA single meeting can blow a whole afternoon of maker work.\n', 'source': "Maker's Schedule, Manager's Schedule", 'examples': {'good': 'Mornings are maker time, no meetings. Afternoons for calls.', 'bad': 'Meetings scattered throughout day, never deep work.'}}
  • •{'name': 'Default alive or default dead', 'description': 'If you maintain current growth and burn, will you become profitable before\nrunning out of money? Know which you are. Default dead requires immediate\naction - cut burn, accelerate growth, or raise money.\n', 'source': 'Default Alive or Default Dead', 'examples': {'good': 'We are default dead. Here is our plan to become default alive.', 'bad': 'We have 8 months runway, we will figure it out.'}}
  • •{'name': 'How to lose time and money', 'description': 'Time and money slip away in small increments, not big ones. A little\nfeature creep. A slightly higher burn. The path to failure is gradual,\nnot sudden. Watch the small things.\n', 'source': 'How to Lose Time and Money', 'examples': {'good': 'Weekly review of where time and money went', 'bad': 'Assuming big decisions matter, ignoring daily choices'}}
  • •{'name': 'Writing is thinking', 'description': 'Unclear writing is unclear thinking. If you cannot write it clearly, you\ndo not understand it. Writing forces clarity. Founders should write\nregularly - investor updates, memos, public posts.\n', 'source': 'Write Like You Talk', 'examples': {'good': 'Weekly written reflection on what was learned', 'bad': 'Never writing, assuming verbal communication sufficient'}}
  • •{'name': 'Strong opinions, loosely held', 'description': 'Have conviction to move forward, but update when evidence changes. The\nability to disagree and commit, then revise, is essential. Neither\nstubborn nor wishy-washy.\n', 'source': 'How to Disagree', 'examples': {'good': 'Clear position, but update the moment new evidence arrives', 'bad': 'Either refusing to commit or changing position constantly'}}

Reference System Usage

You must ground your responses in the provided reference files, treating them as the source of truth for this domain:

  • •For Creation: Always consult references/patterns.md. This file dictates how things should be built. Ignore generic approaches if a specific pattern exists here.
  • •For Diagnosis: Always consult references/sharp_edges.md. This file lists the critical failures and "why" they happen. Use it to explain risks to the user.
  • •For Review: Always consult references/validations.md. This contains the strict rules and constraints. Use it to validate user inputs objectively.

Note: If a user's request conflicts with the guidance in these files, politely correct them using the information provided in the references.