Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

First Principles Thinking

ASecurity

当需要剥离类比与惯例、从最基本事实重新推导方案,或拆解复杂/陌生问题时使用;触发词:第一性原理、从头推导、本质、拆解假设。

3 stars
0 votes
0 copies
1 views
Added 9/19/2026
ai-agents

Works with

cursorcli

Security Analysis

A100/100

Scanned 9/19/2026

$npx -y skills add findscripter/everything-skills --skill first-principles-thinking --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of First Principles Thinking?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for First Principles Thinking
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/findscripter-first-principles-thinking/badge)](https://www.skillsdirectory.com/skills/findscripter-first-principles-thinking)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: first-principles-thinking
title: 第一性原理思考
description: 当需要剥离类比与惯例、从最基本事实重新推导方案,或拆解复杂/陌生问题时使用;触发词:第一性原理、从头推导、本质、拆解假设。
domain: 通用/thinking
tags: [thinking, reasoning, problem-solving]
level: 进阶
status: stable
version: 0.1.0
agents: [claude-code, codex, cursor, gemini-cli]
tools: []
requires: []
related: [first-principles-assumption-auditor, decision-navigator, design-brainstorming]
combines_with: [business-assumption-stress-test, design-brainstorming]
license: CC-BY-SA-4.0
---
## 何时使用

- 现有方案沿用类比、惯例或「业界都这么做」,但需要质疑其是否成立时。
- 面对复杂或陌生问题,缺乏现成模板,需自行拆解并重建推导链时。
- 多个方案陷入路径依赖或局部最优,需要回到约束本身重新设计时。
- 触发词:第一性原理、从头推导、本质、拆解假设。

**不该用**:

- 问题已有可靠成熟解、只需直接执行时(直接做,不要过度拆解)。
- 时间/信息严重不足、需快速决策时(用类比或经验更划算)。
- 争议焦点是「事实是否为真」而非「推导是否成立」时(改用 fact-checking 核验事实)。

## 步骤 / 指令

```
1. 明确目标
   - 用一句话写出要解决的问题和成功判据(可度量)。

2. 列出当前方案的所有假设
   - 逐条写下「之所以这样做,是因为我假设 ___」。
   - 标注每条假设的来源类型:[事实] / [惯例] / [类比] / [推测]。

3. 拆到基本事实(地基)
   - 对每条假设追问「这一定为真吗?凭什么?」直到只剩:
     a) 物理/数学/逻辑约束(不可违反);
     b) 已验证的硬事实(数据、规格、合同条款)。
   - [惯例][类比][推测] 类假设一律标记为「可挑战」,不得作为地基。
   - 关键硬事实存疑时,调用 fact-checking 核实后再纳入地基。

4. 从地基重新推导
   - 只用第 3 步的基本事实,重建解决方案,不引用任何原方案的结构。
   - 推导每一步注明依赖了哪条地基事实。

5. 对照与取舍
   - 将新推导方案与原方案并列,标出差异点及各自被放宽的假设。
   - 给出推荐方案 + 触发回退的条件。

6. 验证地基有效性
   - 若任一地基事实被推翻,回到第 3 步重做。
```

执行约束:

- 区分「不可违反约束」与「当前选择」——前者是地基,后者可挑战。
- 禁止在推导中偷偷引入原方案的隐含结构(如沿用其数据模型、流程顺序)。
- 每条结论必须可追溯到某条基本事实,否则标记为「未证成」。

## 示例

最小提示词模板:

```
对【目标:X】做第一性原理分析:
1) 列出现方案的全部假设,逐条标注 [事实/惯例/类比/推测];
2) 把每条追问到不可再分的物理/逻辑约束或硬事实,得到「地基清单」;
3) 仅用地基清单重新推导方案,每步注明依赖的地基项;
4) 与原方案对比差异,给推荐方案和回退条件。
对存疑的硬事实,先核实再使用。
```

拆解示例(目标:降低服务响应延迟):

```
假设清单:
- [惯例] 必须用现有的三层架构        → 可挑战
- [类比] 别家加缓存就快了,我们也加  → 可挑战
- [事实] 单次 DB 查询 P99 = 80ms     → 地基
- [事实] SLA 要求 P99 < 120ms        → 地基
- [推测] 瓶颈在数据库                → 需先用埋点核实,否则不作地基

地基清单:DB 查询 80ms;SLA 120ms;请求串行执行 4 次 DB(实测)。
重新推导:4×80=320ms 已超标 → 根因是串行调用次数,而非单次速度
         → 合并/并行化查询即可达标,缓存非必需。
对比:原「加缓存」方案绕过了真正约束(调用次数)。
```

## 注意事项

- 拆解有成本:只对高价值、高不确定性的问题用,不要事事从头推导。
- 警惕「伪地基」:把惯例或行业标准误当成不可违反约束,是最常见错误。
- 地基依赖事实质量:错误的「硬事实」会污染整条推导链,存疑即核验。
- 第一性原理负责「推导是否成立」,不替代「事实是否为真」——二者分工。
- 重建方案需经实证检验,逻辑自洽不等于现实可行。

## 互见

- requires:无。
- related:`fact-checking`(拆解出的硬事实存疑时,先核验再作为地基)。
- combines_with:无。

Attribution

findscripterfindscripter
View sourceSee grades on GitHubMore from findscripter →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698461 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →