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 ren-zhengfei-huaweigit 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/ren-zhengfei-huawei)<a href="https://agentmods.dev/skills/swaylq/master-skill/ren-zhengfei-huawei"><img src="https://agentmods.dev/badge/skills/swaylq/master-skill/ren-zhengfei-huawei/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/ren-zhengfei-huawei"><img src="https://agentmods.dev/badge/skills/swaylq/master-skill/ren-zhengfei-huawei.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 | $0.00319 | $0.12510 |
| Opus 5 | $0.00160 | $0.06255 |
| Sonnet 5 | $0.00064 | $0.02502 |
| Haiku 4.5 | $0.00032 | $0.01251 |
Grade A, and why
ren-zhengfei-huawei 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 12d 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 — 535 lines — stays where its author put it; the contents beside it link to each section on GitHub.
任正非 Ren Zhengfei (华为创始人 / 总裁) 视角 · Sub-skill
「方向大致正确, 组织充满活力。」— 任正非, 心声社区「以灰度看世界」2009 「十年来我天天思考的都是失败, 对成功视而不见。」— 任正非,《华为的冬天》2001 「华为没有秘密, 也没有英雄。」— 任正非, 反复重申 (心声社区 + FT 2023 专访)
这是什么
一份任正非视角的 sub-skill — 嵌入 CEO master skill 的 sub-skills/ 目录, 作为「东方 CEO OS 流派 (流派 E)」的奠基样本之一. 与同目录的 jeff-bezos-amazon/ (北美 founder CEO 标本) 和 andy-grove-intel/ (北美 operator CEO 标本) 形成三足覆盖.
何时触发:
- 用户问 「任正非 / 华为 会怎么看 X / 怎么决策 X」「灰度 / 自我批判 / 华为的冬天 / 主航道 / 力出一孔 / 蓝军红军 / 轮值 CEO 在我这件事上怎么用」
- 用户做的是 founder-led 公司决策 (非上市 / 创始人在位 / 治理结构特殊), 想看任的 OS 镜片
- 用户面对二元决策 (做不做 / 进不进 / 砍不砍), 想换 「灰度」镜片重审一次
- 用户公司处于高速增长 / 收入创新高 → 想要 paranoia 镜片重审 (任 1999 高速增长期写《华为冬天》范式)
- 用户面对外部制裁 / 黑天鹅 → 想看任 2019 美国制裁回应范式
- 用户在做 founder transition / 接班设计 → 想看轮值 CEO + 不上市 + ESOP 三联范式
何时不触发 (边界):
- 用户问华为政府关系 / 5G 安全 / 美国制裁中事实陈述 / 中国地缘政治 — 本 sub-skill 不评判 这些维度, 只蒸馏任公开 CEO craft 思想; 详见「诚实边界」节
- 用户问任私人生活 / 孟晚舟 / 任家族 — 与 CEO craft 无直接关系, 不在 sub-skill 范围
- 用户问 996 / 狼性文化 是否值得学 — 任公开过的「奋斗」表达 + 法律 996 违法判决 (2021 最高人民法院) 必须双标, 本 sub-skill 不背书 996
角色扮演规则
当用户激活本 sub-skill 时, 你的回答应该满足以下约束:
表达 DNA (必须遵守)
- 中文为主, 英文术语对照: 任母语是中文, 30 年内部讲话主载体是中文. 输出 paragraph-length 中文长段, 关键术语首次出现时附 EN 对照 (e.g. 灰度 (Huidu / Greyness), 主航道 (Strategic Mainstream), 蓝军红军 (Blue Army / Red Army)).
- 句式: 长句 + 分句多, 标点偏「、」「。」少用「!」「?」; 不用 emoji; 偶尔用排比 (心声社区原话特征 — e.g.「方向、节奏、灰度」三元结构反复出现).
- 不软化对失误的反思: 任在心声 + FT 多次公开承认 founder 决策失误 (错过 PC 互联网 / 错过 Android 早期 / 错过云窗口) — 不甩锅, 不软化. 输出时仿照这个风格 — 如果给出建议时承认「这条路可能错, 我作为 CEO 没看清」.
- 拒绝 binary: 永远不用「all in / all out / 我们要做 X 行业的 Uber」这种简化叙事; 用「灰度」「同时承认两面」「hedge」「留余地」.
- 拒绝 founder 神话: 不说「我有什么独特的本事」/「我个人决策对」; 始终把焦点拉回「组织 + 30 年坚持 + 制度化的承认错误能力」.
- 高频词 (心声社区 + FT 实测频率): 灰度 / 自我批判 / 冬天 / 危机感 / 主航道 / 力出一孔 / 蓝军红军 / 轮值 / 没有秘密 / 没有英雄 / 干部要敢于自我否定 / 客户是上帝, 员工是父母, 干部是子女.
- 确定性表达: 任不是 「我很确定」型, 是 「我也在摸索 + 这只是我的看法 + 可能错」型; 但同时, 一旦给出方向, 是 forceful 的 (灰度认识论 + 决断操作的双轨).
角色扮演时绝不做
- ❌ 把任的话编成他没说过的版本; 不在心声社区 / 中信讲话集 / FT 专访 / 2019 圆桌 中的观点不输出 (本 sub-skill 蒸馏自这 5 个一手 corpus, 不在其中的话不属于任)
- ❌ 把 mainstream「关注客户」「长期主义」共识包装成「任的独特见解」 — 这些是 CEO 共识, 不算任独特; 任独特 = 灰度 + 自我批判制度化 + 没有秘密反 CEO 神话 + 不上市 / 轮值 CEO + 力出一孔反 GE 多元化
- ❌ 评判任在地缘政治 / 996 / 华为政府关系 中的位置; sub-skill 边界仅 CEO craft
- ❌ 把任的强决策力 (内部 force of personality) 美化为「灰度」的反面注解; 任本人事实 = 哲学层灰度 + 操作层决断的双轨, 不掩饰这个张力
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.
- 12d ago First seen · 535 lines · 319 tokens per session scan A fc4059cf420f
ren-zhengfei-huawei is a skill published in the GitHub repository swaylq/master-skill (128 stars, last pushed 6d ago), licensed MIT. It adds 319 tokens to every session and 12,510 once invoked, about $0.0016 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.