# First Principles

> >-

- **Type:** Skill
- **Install:** `agentstack add skill-yli769227-jpg-agent-discipline-first-principles`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [yli769227-jpg](https://agentstack.voostack.com/s/yli769227-jpg)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [yli769227-jpg](https://github.com/yli769227-jpg)
- **Source:** https://github.com/yli769227-jpg/agent-discipline/tree/main/skills/first-principles

## Install

```sh
agentstack add skill-yli769227-jpg-agent-discipline-first-principles
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# First Principles / 第一性原理

> "It's how it's usually done" is not a reason. Re-derive it, or don't claim it.
> "通常这么做"不是理由。要么重新推导,要么别用它当依据。

## The discipline / 纪律

Reason from first principles — not "how it's usually done", but "why it must be done this way":
从第一性原理出发——不靠"通常怎么做",靠"为什么必须这样做":

1. Define the problem down to its most basic form. / 把问题定义到最基本形态。
2. Find the facts that can't be reduced further. / 找到不可再简化的事实。
3. List your assumptions explicitly — and challenge them. / 显式列出并挑战所有假设。
4. Strip away convention, best practice, industry defaults. / 剥掉惯例、最佳实践、行业默认值。
5. Rebuild the solution from constraints and goals alone. / 仅从约束和目标重新构建方案。

**Forbidden:** "this is the usual approach" as a justification. Reasoning over recall.
**禁止:** 拿"这是通常做法"当理由。推理优先于回忆。

## When this triggers / 触发时机

- About to make an architecture / data-model / service-split / protocol choice.
- About to cite "usually / best practice / everyone does it this way" as a reason.
- About to copy a common template without saying why it fits *this* case.
- A design feels "weird" but you're unsure why it doesn't follow the common pattern.

## Done criterion (verifiable) / 完成判据（可验证）

✅ The approach lists three things: (a) the default/convention you're stripping away, (b) the specific constraint or fact that overturns it, and (c) how the conclusion would change if that constraint changed. Missing any one = not done.
⚠️ You leaned on convention because the constraints were unclear — name what you'd need to know to decide properly.
❌ The only reason given is "it's standard". Re-derive from constraints before committing.

## Worked examples / 实战反例

Real before/after cases for this discipline live in [EXAMPLES.md](./EXAMPLES.md) — read them before you act.
本纪律的真实 before/after 反例见 [EXAMPLES.md](./EXAMPLES.md) —— 动手前先对照。

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [yli769227-jpg](https://github.com/yli769227-jpg)
- **Source:** [yli769227-jpg/agent-discipline](https://github.com/yli769227-jpg/agent-discipline)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-yli769227-jpg-agent-discipline-first-principles
- Seller: https://agentstack.voostack.com/s/yli769227-jpg
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.