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 juliang-qianchuan-officialgit 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/juliang-qianchuan-official)<a href="https://agentmods.dev/skills/swaylq/master-skill/juliang-qianchuan-official"><img src="https://agentmods.dev/badge/skills/swaylq/master-skill/juliang-qianchuan-official/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/juliang-qianchuan-official"><img src="https://agentmods.dev/badge/skills/swaylq/master-skill/juliang-qianchuan-official.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 | $0.00067 | $0.02452 |
| Opus 5 | $0.00034 | $0.01226 |
| Sonnet 5 | $0.00013 | $0.00490 |
| Haiku 4.5 | $0.00007 | $0.00245 |
Grade A, and why
juliang-qianchuan-official-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.
How it starts
The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
巨量千川官方方法论视角 · Sub-skill
来源声明: 本 skill 基于巨量千川 / 巨量引擎 官方公开材料 (官方文档 / 巨量大学 / WILL keynote / 千川·乘方发布) 蒸馏. 不编造官方没说过的话.
角色背景
- 背景: 巨量千川是字节跳动旗下抖音电商核心广告平台
- 关键事件:
- 2021 千川上线
- 2025-03 整体并入抖音电商 (从巨量引擎商业化部门转出)
- 2025-12 千川·乘方发布 — 营销工具进入「智能化新阶段」
- 战略转向: 从「让商家拿曝光」到「让商家做经营」 — 流量服务于 GMV / ROI
心智模型 (4 个 PASS)
1. OCPM 智能出价是主流, 卡价时代过去
一句话: OCPM 让算法预估转化价值自动调整出价, 比手动卡价更高效. 老套路 (手动卡价 / 死磕定向) 跟不上算法迭代.
它说的是: 算法在前 50 转化里学习人群转化偏好, 后续自动给高价值用户溢价 / 低价值用户降价. 投手要做的是给算法好素材 + 等学习期, 不是手动微操.
应用方式:
- OCPM 是默认出价模式
- 学习期 (前 50 转化) 不动出价 / 定向 / 素材
- 学完后只动 1 个变量, 不要同时改
局限:
- 极少数极小预算 (¥ 100-500/天) 学习期长, 等不起
- 高客单类目转化数据少, 学习期不稳定
2. 5A 人群 + GTA 是中大品牌资产
一句话: GTA = GMV → 5A 人群积累 → 投放触点. 中大品牌品牌资产沉淀 + ROI 双优化的官方方法论.
它说的是: 5A 人群 (Z世代 / 精致妈妈 / 新锐白领 / 小镇青年 / 小镇中老年) 是定向底盘. 非大促节点累积 → 大促节点放大 — 实测 CPA 降 8% / ROI 升 30%.
应用方式:
- 月预算 ≥ ¥ 50k 才有意义跑 GTA
- 不同 5A 不同素材
- 千川·乘方 AI 自动跨人群分配预算
局限:
- 中小商家直接跑 ROAS 更实在
- 业态差异大 (本地生活 / 短剧 不适用)
3. 直播 3 阶段不同核心目标
一句话: 冷启动 (互动 + 人群标签) / 成长 (转化率 + UV 值) / 成熟 (GMV) — 阶段不同 KPI 不同, 不要混着追.
它说的是: 巨量千川官方明确给出 3 阶段 KPI. 多数商家失败因为冷启动期硬冲 GMV (但人群没建).
应用方式:
- 冷启动期 (前 7 天): 轻投 ¥ 500-2000/天, 看互动数据 + 人群标签
- 成长期 (≥ 50 转化, 7-30 天): 短视频引流 + 直播间承接双轮
- 成熟期 (≥ 30 天稳定): 全产品组合 + GTA 5A 人群
局限:
- 头部主播 (罗永浩 / 董宇辉 / 大杨哥) 不走 3 阶段
- 短期事件型直播 (1-3 天) 压缩 3 阶段
4. 千川·乘方 — AI 智能化是大方向 (2025-12 起)
一句话: 千川·乘方整合广告投放 + 智能优惠券 + 达人佣金结算 + AI 创意, 营销工具进入「智能化新阶段」.
它说的是: 2025-12 发布 千川·乘方 是千川并入抖音电商后的全面升级. AI 跨场景 (短视频 / 直播间 / 商品卡 / 搜索) 自动分配预算, 商家只需要给目标 (GMV / ROI), 算法做执行.
应用方式:
- 中大品牌优先用千川·乘方 全域推广 (跨场景一键投放)
- AI 创意工具 (智能脚本 / 智能剪辑) 节省 70% 创意人力
- 智能优惠券自动按人群分发
- 达人佣金结算自动化 (CPS 模式)
局限:
- 中小商家可能用不到全域推广 (预算门槛高)
- AI 创意全自动直发限流, 必须人工把关
决策规则 (6 条)
1. 如果新建千川计划
则OCPM 智能出价 + 学习期 (前 50 转化) 不动 — 让算法学完.
2. 如果月预算 ≥ ¥ 50k
则跑 GTA + 5A 人群 — 非大促累积人群, 大促放大投放.
3. 如果做直播间投流
则按 3 阶段不同 KPI: 冷启动看互动 + 人群 / 成长看转化 + UV / 成熟看 GMV.
4. 如果是中大品牌
则用千川·乘方 全域推广 (跨场景), 不要分散投流.
5. 如果用 AI 创意
则辅助 OK (脚本 / 剪辑 / 字幕), 但必须人工把关 — AI 全自动直发限流.
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.
- 13d ago First seen · 166 lines · 67 tokens per session scan A 497f78a229f7
juliang-qianchuan-official-perspective is a skill published in the GitHub repository swaylq/master-skill (128 stars, last pushed 6d ago), licensed MIT. It adds 67 tokens to every session and 2,452 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.
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…
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…
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.
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…
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.
byted-livesaas-master
A control tool for managing business livestreams, including rooms, comments, viewers, product cards, coupons, and live-session settings.