dong-yuhui-dongfangzhenxuan-perspective

dong-yuhui-dongfangzhenxuan-perspective is a skill for Claude Code, Codex from swaylq/master-skill. It costs 57 tokens per session (2,326 once invoked), scanned A, original, MIT.

A decision framework for content-led livestream selling, based on the public methods associated with Dong Yuhui and Dongfang Zhenxuan. It treats the livestream as both a content channel and a place to sell products.

In plain words
What is it for?
It is for making decisions about livestream content, presenter positioning, cultural product storytelling, audience relationships, and product categories such as food, farm goods, and books.
Why use it?
It helps plan livestreams around useful stories, knowledge, and a recognisable presenter instead of relying only on paid traffic or sales language.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It is for making decisions about livestream content, presenter positioning, cultural product storytelling, audience relationships, and product categories such as food, farm goods, and books.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/swaylq/master-skill/dong-yuhui-dongfangzhenxuan
Install

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.

Any agent
npx skills add swaylq/master-skill --skill dong-yuhui-dongfangzhenxuan
Clone the repo
git clone --depth 1 https://github.com/swaylq/master-skill

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for dong-yuhui-dongfangzhenxuan-perspective

README.md
[![agentmods](https://agentmods.dev/badge/skills/swaylq/master-skill/dong-yuhui-dongfangzhenxuan/github.svg)](https://agentmods.dev/skills/swaylq/master-skill/dong-yuhui-dongfangzhenxuan)
Your own site
<a href="https://agentmods.dev/skills/swaylq/master-skill/dong-yuhui-dongfangzhenxuan"><img src="https://agentmods.dev/badge/skills/swaylq/master-skill/dong-yuhui-dongfangzhenxuan/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.

agentmods 80×15 button for dong-yuhui-dongfangzhenxuan-perspective

Your own site · 80×15
<a href="https://agentmods.dev/skills/swaylq/master-skill/dong-yuhui-dongfangzhenxuan"><img src="https://agentmods.dev/badge/skills/swaylq/master-skill/dong-yuhui-dongfangzhenxuan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,326 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00057 $0.02326
Opus 5 $0.00028 $0.01163
Sonnet 5 $0.00011 $0.00465
Haiku 4.5 $0.00006 $0.00233

Measured 13d ago against content hash c811c37c7ff4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

dong-yuhui-dongfangzhenxuan-perspective 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 13d 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.

prototypes/short-video-ads-master/output/sub-skills/dong-yuhui-dongfangzhenxuan/SKILL.md · 165 lines

How it starts

The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.

董宇辉 / 东方甄选视角 · Sub-skill

来源声明: 本 skill 基于董宇辉 / 东方甄选 / 与辉同行 等公开材料 + 36氪 / 晚点 LatePost 长期跟踪报道蒸馏. 不编造他没说过的话.

角色背景

  • 背景: 董宇辉 (新东方英语老师 → 东方甄选 → 与辉同行)
  • 代表事件:
    • 2022-06 双语带货爆红 (新东方双语带货 → 东方甄选)
    • 2023 年 GMV 突破 100 亿
    • 2024 自立门户「与辉同行」 (跟东方甄选分家)
  • 特色: 内容驱动直播 + 文化带货 + 知识型主播 + 反共识打法

心智模型 (4 个 PASS)

1. 内容驱动 = 抗投流通胀

一句话: 多数直播间靠投流跑量, 内容同质化 → 投流 ROI 一直降. 内容差异化才能反 「投流通胀」.

它说的是: 抖音电商 2022-2026 投流 CPM 一直涨, ROAS 普遍降. 主播话术同质化, 用户审美疲劳. 东方甄选「双语带货 / 文化讲述」打开了新赛道 — 用户不只来买货, 来听内容.

应用方式:

  • 主播差异化 (个性 / 文化背景 / 知识储备)
  • 直播间不只是带货场, 也是内容场
  • 长直播 (4-8 小时) 让用户「消费时间」, 不只是「买完就走」

局限:

  • 内容驱动需要主播本人能力强 (董宇辉是新东方老师背景)
  • 短期 GMV 慢于纯投流跑量直播间
  • 类目差异 — 农产品 / 食品类 适合, 美妆 / 服饰 / 数码 不一定

2. 知识型主播 + 内容沉淀是新护城河

一句话: 头部主播的护城河不是流量 / 货 / 投流, 是「内容沉淀」 — 用户跟主播的长期关系.

它说的是: 董宇辉每场直播讲历史 / 文化 / 哲学 / 故事, 不只讲产品. 用户复购 + 留存高于行业均值. 这是「内容沉淀」给的复利.

应用方式:

  • 主播每场直播预留 30-50% 时间讲非产品内容 (故事 / 文化 / 知识)
  • 长期沉淀主播个人 IP — 用户跟主播的情感连接
  • 反对纯卖货话术, 不用「极限词 / 紧迫感 / 限定词」

局限:

  • 主播能力门槛高 (知识储备 / 表达能力)
  • 直播间 GMV 转化率短期可能低于纯卖货直播间

3. 文化带货 = 长期品牌资产

一句话: 把直播间做成「文化场」, 用户是「学习 + 购物」双目的, 跟纯投流直播间形成差异化.

它说的是: 东方甄选选品偏「农产品 / 文化产品 / 图书」 — 这些类目跟「文化带货」叙事天然契合. 用户买东方甄选不只是图便宜, 是图「认同感 + 文化共鸣」.

应用方式:

  • 选品: 跟主播文化叙事相关 (农产品 / 图书 / 文化衍生品)
  • 直播间设计: 文化氛围 (背景 / 话术 / 选品介绍)
  • 复盘: 不只看 GMV, 也看「内容互动 / 用户留言 / 复购率」

局限:

  • 文化带货受众有限 — 不适合全年龄段
  • 选品受文化叙事约束 — 商品扩品困难

4. 跟 MCN / 平台关系处理是头部主播必修课

一句话: 头部主播 IP 跟 MCN / 平台的关系处理不好, 可能反噬整个商业 — 董宇辉跟东方甄选分家就是案例.

它说的是: 2024 年董宇辉跟东方甄选分家成立「与辉同行」 — 头部主播 IP 个人价值 vs 公司价值的张力. 类似事件还有程十安跟上海缙嘉 (小红书).

应用方式:

  • 头部主播 IP 归属前置写清楚 (合同 + 股权)
  • 分家路径预先规划 (个人公司 + 矩阵号备份)
  • 跨平台备份 — 不押单平台单 MCN

局限:

  • 头部主播 IP 跟 MCN 处理是个案, 不是通用法则
  • 分家成本高 (用户迁移 / 法律风险)

决策规则 (6 条)

1. 如果做内容驱动直播

主播本人能力是核心, 不要简单复制套路.

2. 如果做选品

选品跟主播文化 / 知识背景契合 (农产品 / 图书 / 文化衍生品).

3. 如果做话术

预留 30-50% 时间讲非产品内容 (故事 / 文化 / 知识).

4. 如果做长期资产

主播个人 IP 长期沉淀是头部直播间护城河.

5. 如果做投流

内容驱动直播间投流 ROI 短期低, 但长期复购率高.

6. 如果跟 MCN 合作

头部主播 IP 归属前置写清楚, 分家路径预先规划.

Read the full file on GitHub · 165 lines

Changes

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.

  1. 13d ago First seen · 165 lines · 57 tokens per session scan A c811c37c7ff4

Subscribe to this mod's changes

dong-yuhui-dongfangzhenxuan-perspective is a skill published in the GitHub repository swaylq/master-skill (128 stars, last pushed 6d ago), licensed MIT. It adds 57 tokens to every session and 2,326 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

build-monetized-app

Use when the task is building a new app on Eliza Cloud that earns money — chat apps, agent apps, MCP-backed tools, anything that calls the cloud's chat/messages/inference endpoints on behalf of users. Covers app registration, container deploy, markup configuration, affiliate header, app charge requests, x402 payment…

elizaOS/eliza · 126 tokens

eliza-cloud-buy-domain

Use whenever a user wants to register or buy a custom domain for an Eliza Cloud app — including in the same request as building the app ("build me X and put it on Y.com"). Uses Cloudflare as registrar after explicit user confirmation, paid from the user's existing cloud credit balance. Pairs with build-monetized-app…

elizaOS/eliza · 125 tokens

ordercli

Foodora CLI for checking past orders and active order status. Use when the user asks to check food delivery orders, track a Foodora delivery, view order history, reorder a meal, look up past food orders, check delivery status, or manage Foodora sessions and authentication.

elizaOS/eliza · 58 tokens

personal-shopper

Personal advisor for a problem that might be solved by buying something — diagnoses the real need through conversation, then recommends products from the user's configured stores only when a purchase is the right answer. Recalls the user's sizes, budget, brands and restrictions across sessions, and records new ones as…

kirodotdev/KiroCrew · 98 tokens

meituan-deals

A Meituan assistant for finding food deals, collecting coupons, and placing restaurant group-buy orders. Meituan is a Chinese local-services platform for dining and other everyday purchases.

TencentCloud/Octop · 193 tokens

byted-livesaas-master

A control tool for managing business livestreams, including rooms, comments, viewers, product cards, coupons, and live-session settings.

bytedance/agentkit-samples · 160 tokens