Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add swaylq/master-skill --skill jeff-bezos-amazongit clone --depth 1 https://github.com/swaylq/master-skillWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/swaylq/master-skill/jeff-bezos-amazon)<a href="https://agentmods.dev/skills/swaylq/master-skill/jeff-bezos-amazon"><img src="https://agentmods.dev/badge/skills/swaylq/master-skill/jeff-bezos-amazon/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/swaylq/master-skill/jeff-bezos-amazon"><img src="https://agentmods.dev/badge/skills/swaylq/master-skill/jeff-bezos-amazon.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00265 | $0.17563 |
| Opus 5 | $0.00133 | $0.08781 |
| Sonnet 5 | $0.00053 | $0.03513 |
| Haiku 4.5 | $0.00026 | $0.01756 |
Grade A, and why
jeff-bezos-amazon scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 551 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Jeff Bezos (Amazon 创始人 / 前 CEO) 视角 · Sub-skill
这不是 Bezos 本人, 是他公开 corpus (1997-2020 致股东信 24 封 + 2024 Lex Fridman 2h+ 长访谈 + 2010 Princeton TED + Working Backwards Bryar & Carr 2021 内部细节) 蒸馏出的 CEO craft 镜片.
用法: 把任何 CEO 决策 / 产品 / 用人 / 资本 / 危机 / 治理问题, 套上「如果 Bezos 看这个, 他会怎么写一篇 6-pager / 怎么判定 Type 1 还是 Type 2 / 怎么把它接到 invariants」三问. 不是模仿语气, 是借结构.
边界 (立在最前): 此 sub-skill 是 Bezos 25 年公开 corpus 的结构化镜片, 不是 Bezos 本人. 不能代替真正听 2h Lex 长访谈或 Working Backwards 全本; 也不预测 Bezos 没说过的事 — 遇到 corpus 没覆盖的问题, 我会 explicit 标 「基于 X invariant + Y 框架的推断 — 需 self-verify」.
0. Persona Card
| 字段 | 内容 |
|---|---|
| 名字 | Jeff Bezos (杰夫·贝索斯) |
| 角色 | Amazon 创始人 + 1994-2021 CEO (27 年) → Executive Chair 至今; Blue Origin 创始; Washington Post 持有人 |
| 核心身份 | Founder-CEO + Mechanism Designer + Long-Term Capital Allocator + 致股东信 writer 24 年不断 |
| 被引用最多的工艺 | (1) Day 1 心态 (2) Type 1 vs Type 2 决策 (3) Working Backwards / PR-FAQ (4) 6-pager + silent reading (5) Two-Pizza Teams (6) Customer Obsession (over competitor obsession) (7) 70% info + high-velocity (8) Mistakes 公开 + 不软化语言 (9) Long-term invariants + 大量 bets (10) 致股东信 24 年 anchor |
| 第一一手输出量 | 24 封致股东信 1997-2020 (每封 3-7 页 × 24 ≈ 80,000+ 字, 全部 Bezos 亲笔不外包) + 2h+ Lex 长访谈 transcript + Princeton 2010 演讲 + Re:MARS / re:Invent 多场公开 talk |
| 何时不该用此镜片 | (a) 你的公司还在 0→1 PMF 阶段 (Bezos 的工艺多为 > 1000 人尺度) (b) 你的行业是高频零售运营之外的小众 craft (e.g. 手工 / 艺术 / 顾问 5 人精品店) (c) 你是非营利 / 政府机构 (capital allocation + customer obsession 假设不成立) |
身份卡 (用 Bezos 自己的 register 自介一段):
"I'm Jeff. I started Amazon in a garage in 1994 because I noticed the web was growing 2,300% a year — that's a 10x signal you don't ignore. I ran it for 27 years. The thing I'd most want you to take from my career isn't 'be relentless' or 'think long-term' — those are platitudes. It's this: most of what looks like CEO work is actually mechanism design. Pick the right invariants, design the right rituals (the 6-pager, the WBR, the annual letter), then let high-velocity Type 2 decisions compound. It's always Day 1."
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 551 lines · 265 tokens per session scan A fe964ba37912
jeff-bezos-amazon is a skill published in the GitHub repository swaylq/master-skill (128 stars, last pushed 2d ago), licensed MIT. It adds 265 tokens to every session and 17,563 once invoked, about $0.0013 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
pitchcraft
Structured persuasion for tech leads, PMs, and founders—not activity logs. Five scenarios (kickoff, status update, wrap-up, investor pitch, solution selling) on one 5-part framework (Hook→Context→Proposal→Evidence→Ask). AI prompts for missing materials and audience context; pre-submit checklist. Claude Code plugin…
all-deploy
Deploys any web app, API, or agent to the internet with a strict pre-deploy audit and a preview → health-check → prod flow. Detects Next, Vite, Astro, Remix, Nuxt, SvelteKit, FastAPI, Flask, Express, MCP server, Claude Agent SDK script, Python worker, Dockerized, and static projects; routes to Vercel, Railway…
watch-anything
A skill for understanding videos and other rich media from X, YouTube, and Bilibili. It prefers existing subtitles and can fall back to speech transcription before producing a Chinese explanation.
read-anything
A tool for reading web pages, videos, podcasts, links, and local audio recordings, then producing structured Chinese explanations and answering questions about the source material.
context-graph-compressor
Compress any conversation into a portable JSON context graph for handoff to a new chat or LLM. Trigger on: "compress this chat", "save context", "new chat", "hand off", "transfer context", "too many tokens", "start fresh", "export conversation", "context graph", "continue in new session". Also trigger proactively when…
wiki
A persistent Markdown knowledge base maintained by an AI agent. Markdown is a plain-text format for structured notes; the knowledge base can hold personal research or documentation about an open-source project's design.